add resilience tests

Author: tomfrenken

packages/langchain/src/orchestration/client.test.ts

@@ -1 +1,98 @@
-// test timeout & maxRetries with mocked target
+import nock from 'nock';
+import { constructCompletionPostRequest } from '@sap-ai-sdk/orchestration/internal.js';
+import {
+  mockClientCredentialsGrantCall,
+  mockDeploymentsList,
+  mockInference,
+  parseMockResponse
+} from '../../../../test-util/mock-http.js';
+import { OrchestrationClient } from './client.js';
+import type {
+  CompletionPostResponse,
+  OrchestrationModuleConfig
+} from '@sap-ai-sdk/orchestration';
+
+describe('orchestration service client', () => {
+  beforeEach(() => {
+    mockClientCredentialsGrantCall();
+    mockDeploymentsList({ scenarioId: 'orchestration' }, { id: '1234' });
+  });
+
+  afterEach(() => {
+    nock.cleanAll();
+  });
+
+  it('calls chatCompletion with minimum configuration', async () => {
+    const config: OrchestrationModuleConfig = {
+      llm: {
+        model_name: 'gpt-35-turbo-16k',
+        model_params: { max_tokens: 50, temperature: 0.1 }
+      },
+      templating: {
+        template: [{ role: 'user', content: 'Hello!' }]
+      }
+    };
+
+    const mockResponse = await parseMockResponse<CompletionPostResponse>(
+      'orchestration',
+      'orchestration-chat-completion-success-response.json'
+    );
+
+    mockInference(
+      {
+        data: constructCompletionPostRequest(config, { messagesHistory: [] })
+      },
+      {
+        data: mockResponse,
+        status: 200
+      },
+      {
+        url: 'inference/deployments/1234/completion'
+      },
+      { retry: 3 }
+    );
+    const response = await new OrchestrationClient(config, {
+      maxRetries: 5
+    }).invoke([], { timeout: 1 });
+
+    // expect(nock.isDone()).toBe(true);
+    expect(response).toMatchInlineSnapshot(`
+     {
+       "id": [
+         "langchain_core",
+         "messages",
+         "OrchestrationMessage",
+       ],
+       "kwargs": {
+         "additional_kwargs": {
+           "finish_reason": "stop",
+           "function_call": undefined,
+           "index": 0,
+           "tool_calls": undefined,
+         },
+         "content": "Hello! How can I assist you today?",
+         "invalid_tool_calls": [],
+         "response_metadata": {
+           "created": 172,
+           "finish_reason": "stop",
+           "function_call": undefined,
+           "id": "orchestration-id",
+           "index": 0,
+           "model": "gpt-35-turbo",
+           "object": "chat.completion",
+           "system_fingerprint": undefined,
+           "tokenUsage": {
+             "completionTokens": 9,
+             "promptTokens": 9,
+             "totalTokens": 18,
+           },
+           "tool_calls": undefined,
+         },
+         "tool_calls": [],
+       },
+       "lc": 1,
+       "type": "constructor",
+     }
+    `);
+  });
+});

packages/langchain/src/orchestration/client.ts

@@ -54,7 +54,6 @@ export class OrchestrationClient extends BaseChatModel<
     Exclude<NewRunOutput, Error>,
     OrchestrationCallOptions
   > {
-    // Delegate to the superclass pipe method and narrow the type.
     return super.pipe(coerceable) as Runnable<
       BaseLanguageModelInput,
       Exclude<NewRunOutput, Error>,

test-util/mock-http.ts

@@ -2,18 +2,18 @@ import { readFile } from 'node:fs/promises';
 import path from 'node:path';
 import { fileURLToPath } from 'node:url';
 import nock from 'nock';
-import { type EndpointOptions } from '@sap-ai-sdk/core';
-import {
-  type FoundationModel,
-  type DeploymentResolutionOptions
-} from '@sap-ai-sdk/ai-api/internal.js';
-import { dummyToken } from './mock-jwt.js';
 import {
   registerDestination,
   type DestinationAuthToken,
   type HttpDestination,
   type ServiceCredentials
 } from '@sap-cloud-sdk/connectivity';
+import { type EndpointOptions } from '@sap-ai-sdk/core';
+import {
+  type FoundationModel,
+  type DeploymentResolutionOptions
+} from '@sap-ai-sdk/ai-api/internal.js';
+import { dummyToken } from './mock-jwt.js';
 
 // Get the directory of this file
 const __filename = fileURLToPath(import.meta.url);
@@ -98,19 +98,33 @@ export function mockInference(
     data: any;
     status?: number;
   },
-  endpoint: EndpointOptions = mockEndpoint
+  endpoint: EndpointOptions = mockEndpoint,
+  resilienceOptions?: {
+    delay?: number;
+    retry?: number;
+  }
 ): nock.Scope {
   const { url, apiVersion, resourceGroup = 'default' } = endpoint;
   const destination = getMockedAiCoreDestination();
-  return nock(destination.url, {
+  const scope = nock(destination.url, {
     reqheaders: {
       'ai-resource-group': resourceGroup,
       authorization: `Bearer ${destination.authTokens?.[0].value}`
     }
-  })
-    .post(`/v2/${url}`, request.data)
-    .query(apiVersion ? { 'api-version': apiVersion } : {})
-    .reply(response.status, response.data);
+  });
+
+  let interceptor = scope.post(`/v2/${url}`, request.data).query(apiVersion ? { 'api-version': apiVersion } : {});
+
+  if (resilienceOptions?.retry) {
+    interceptor.times(resilienceOptions.retry).reply(500);
+    interceptor = scope.post(`/v2/${url}`, request.data).query(apiVersion ? { 'api-version': apiVersion } : {});
+  }
+
+  if (resilienceOptions?.delay) {
+    interceptor = interceptor.delay(resilienceOptions.delay);
+  }
+
+  return interceptor.reply(response.status, response.data);
 }
 
 /**