@cloudbase/agent-adapter-adp 0.0.15 → 0.0.18

package/README.md

@@ -15,6 +15,7 @@ npm install @cloudbase/agent-agents @cloudbase/agent-adapter-adp
 - **Thinking Events**: Support for thinking/reasoning process events from the model
 - **Workflow Integration**: Support for ADP workflows with tool call events
 - **Custom Variables**: Pass custom parameters to workflows and knowledge base
+- **File Upload**: Upload images and documents to COS for multimodal conversations (**requires `enableUpload: true`**)
 
 ## Environment Variables
 
@@ -121,6 +122,55 @@ observable.subscribe({
 });
 ```
 
+### With File Upload (Images and Documents)
+
+When `enableUpload` is **set to `true`**, you can send images and documents in messages. Files are automatically uploaded to Tencent Cloud COS and processed by ADP.
+
+**Note:** File upload requires Tencent Cloud credentials (`TENCENTCLOUD_SECRETID` and `TENCENTCLOUD_SECRETKEY`).
+
+```typescript
+import { AdpAgent } from "@cloudbase/agent-adapter-adp";
+import { randomUUID } from "crypto";
+import * as fs from "fs";
+
+const agent = new AdpAgent({
+  name: "my-adp-agent",
+  adpConfig: {
+    appKey: "your-app-key",
+    enableUpload: true, // Enable file upload
+    credential: {
+      secretId: "your-secret-id",
+      secretKey: "your-secret-key",
+    },
+  },
+});
+
+const observable = agent.run({
+  runId: randomUUID(),
+  threadId: randomUUID(),
+  messages: [
+    {
+      id: randomUUID(),
+      role: "user",
+      content: [
+        { type: "text", text: "What's in this image?" },
+        {
+          type: "binary",
+          mimeType: "image/png",
+          filename: "screenshot.png",
+          data: fs.readFileSync("./screenshot.png"),
+        },
+      ],
+    },
+  ],
+});
+```
+
+**Supported file types:**
+
+- **Images**: `image/png`, `image/jpeg`, `image/bmp`
+- **Documents**: `application/pdf`, `application/msword`, `application/vnd.openxmlformats-officedocument.wordprocessingml.document`, `application/vnd.ms-powerpoint`, `application/vnd.openxmlformats-officedocument.presentationml.presentation`, `text/plain`
+
 ## API Reference
 
 ### AdpAgent
@@ -146,9 +196,11 @@ interface AdpConfig {
     token?: string; // Session token (optional if TENCENTCLOUD_SESSIONTOKEN env is set)
   };
   historyCount?: number; // Number of history messages to retrieve (reserved)
+  enableUpload?: boolean; // Enable file upload for images and documents (default: false)
   request?: {
     baseUrl?: string; // Base URL for ADP API (default: https://wss.lke.cloud.tencent.com)
     endpoint?: string; // API endpoint (default: /v1/qbot/chat/sse)
+    docParseEndpoint?: string; // Document parse API endpoint (default: /v1/qbot/chat/docParse)
     body?: Partial<AdpChatRequest>; // Additional request body options
   };
 }
@@ -187,6 +239,7 @@ The adapter emits the following AG-UI events:
 - `axios`: HTTP client for API requests
 - `rxjs`: Reactive extensions for JavaScript
 - `tencentcloud-sdk-nodejs-lke`: Tencent Cloud LKE SDK
+- `cos-nodejs-sdk-v5`: Tencent Cloud COS SDK (for file upload)
 
 ## Related Resources
 

package/dist/index.d.mts

@@ -1,5 +1,6 @@
 import { AbstractAgent, AgentConfig, RunAgentInput, EventType } from '@ag-ui/client';
 import { Observable } from 'rxjs';
+import { lke } from 'tencentcloud-sdk-nodejs-lke';
 
 /**
  * 文件信息
@@ -58,8 +59,10 @@ type AdpConfig = {
         baseUrl?: string;
         endpoint?: string;
         body?: Partial<AdpChatRequest>;
+        docParseEndpoint?: string;
     };
     historyCount?: number;
+    enableUpload?: boolean;
     appKey?: string;
     credential?: {
         secretId?: string;
@@ -244,24 +247,51 @@ interface ThoughtProcedure {
 interface Debugging {
     content: string;
 }
+interface DocumentParseRequest {
+    sessionId: string;
+    botAppKey: string;
+    requestId: string;
+    cosBucket: string;
+    fileType: string;
+    fileName: string;
+    cosUrl: string;
+    cosHash: string;
+    eTag: string;
+    size: string;
+}
+interface DocumentParseChunk {
+    type: "parsing";
+    payload: ParsingEvent;
+}
+interface ParsingEvent {
+    session_id: string;
+    trace_id: string;
+    is_final: boolean;
+    doc_id: string;
+    process: number;
+    status: string;
+    timestamp: number;
+    error_message: string;
+}
 
 declare class AdpAgentError extends Error {
     code?: string;
     constructor(message: string, code?: string);
 }
+type CosParams = Awaited<ReturnType<typeof lke.v20231130.Client.prototype.DescribeStorageCredential>>;
 declare class AdpAgent extends AbstractAgent {
     private reqAppClient;
     private reqLkeClient;
     protected adpConfig: AdpConfig;
+    private finalAppKey;
+    private finalCloudCredential;
     constructor(config: AgentConfig & {
         adpConfig: AdpConfig;
     });
-    generateRequestBody({ message, fileInfos, runId, threadId, forwardedProps, }: {
+    generateRequestBody({ message, fileInfos, input, }: {
         message: string;
         fileInfos: FileInfo[];
-        runId: string;
-        threadId: string;
-        forwardedProps: Record<string, string>;
+        input: RunAgentInput;
     }): AdpChatRequest;
     run(input: RunAgentInput): Observable<{
         type: EventType;
@@ -269,6 +299,10 @@ declare class AdpAgent extends AbstractAgent {
         rawEvent?: any;
     }>;
     private _run;
+    private convertAGUIMessagesToAdpMessages;
+    private extractDocuments;
+    private getCosParams;
+    private uploadToCos;
 }
 
-export { AdpAgent, AdpAgentError, type AdpChatRequest, type AdpChunk, type AdpConfig, type CurrentNode, CurrentNodeStatus, type Debugging, type ErrorInfo, type FileInfo, type Knowledge, type QuoteInfo, type Reference, type ReferenceEvent, type ReplyEvent, ReplyMethod, type StatisticInfo, type TaskFlow, type ThoughtEvent, type ThoughtProcedure, type TokenStatEvent, type TokenStatProcedure, type WorkFlow };
+export { AdpAgent, AdpAgentError, type AdpChatRequest, type AdpChunk, type AdpConfig, type CosParams, type CurrentNode, CurrentNodeStatus, type Debugging, type DocumentParseChunk, type DocumentParseRequest, type ErrorInfo, type FileInfo, type Knowledge, type ParsingEvent, type QuoteInfo, type Reference, type ReferenceEvent, type ReplyEvent, ReplyMethod, type StatisticInfo, type TaskFlow, type ThoughtEvent, type ThoughtProcedure, type TokenStatEvent, type TokenStatProcedure, type WorkFlow };

package/dist/index.d.ts

@@ -1,5 +1,6 @@
 import { AbstractAgent, AgentConfig, RunAgentInput, EventType } from '@ag-ui/client';
 import { Observable } from 'rxjs';
+import { lke } from 'tencentcloud-sdk-nodejs-lke';
 
 /**
  * 文件信息
@@ -58,8 +59,10 @@ type AdpConfig = {
         baseUrl?: string;
         endpoint?: string;
         body?: Partial<AdpChatRequest>;
+        docParseEndpoint?: string;
     };
     historyCount?: number;
+    enableUpload?: boolean;
     appKey?: string;
     credential?: {
         secretId?: string;
@@ -244,24 +247,51 @@ interface ThoughtProcedure {
 interface Debugging {
     content: string;
 }
+interface DocumentParseRequest {
+    sessionId: string;
+    botAppKey: string;
+    requestId: string;
+    cosBucket: string;
+    fileType: string;
+    fileName: string;
+    cosUrl: string;
+    cosHash: string;
+    eTag: string;
+    size: string;
+}
+interface DocumentParseChunk {
+    type: "parsing";
+    payload: ParsingEvent;
+}
+interface ParsingEvent {
+    session_id: string;
+    trace_id: string;
+    is_final: boolean;
+    doc_id: string;
+    process: number;
+    status: string;
+    timestamp: number;
+    error_message: string;
+}
 
 declare class AdpAgentError extends Error {
     code?: string;
     constructor(message: string, code?: string);
 }
+type CosParams = Awaited<ReturnType<typeof lke.v20231130.Client.prototype.DescribeStorageCredential>>;
 declare class AdpAgent extends AbstractAgent {
     private reqAppClient;
     private reqLkeClient;
     protected adpConfig: AdpConfig;
+    private finalAppKey;
+    private finalCloudCredential;
     constructor(config: AgentConfig & {
         adpConfig: AdpConfig;
     });
-    generateRequestBody({ message, fileInfos, runId, threadId, forwardedProps, }: {
+    generateRequestBody({ message, fileInfos, input, }: {
         message: string;
         fileInfos: FileInfo[];
-        runId: string;
-        threadId: string;
-        forwardedProps: Record<string, string>;
+        input: RunAgentInput;
     }): AdpChatRequest;
     run(input: RunAgentInput): Observable<{
         type: EventType;
@@ -269,6 +299,10 @@ declare class AdpAgent extends AbstractAgent {
         rawEvent?: any;
     }>;
     private _run;
+    private convertAGUIMessagesToAdpMessages;
+    private extractDocuments;
+    private getCosParams;
+    private uploadToCos;
 }
 
-export { AdpAgent, AdpAgentError, type AdpChatRequest, type AdpChunk, type AdpConfig, type CurrentNode, CurrentNodeStatus, type Debugging, type ErrorInfo, type FileInfo, type Knowledge, type QuoteInfo, type Reference, type ReferenceEvent, type ReplyEvent, ReplyMethod, type StatisticInfo, type TaskFlow, type ThoughtEvent, type ThoughtProcedure, type TokenStatEvent, type TokenStatProcedure, type WorkFlow };
+export { AdpAgent, AdpAgentError, type AdpChatRequest, type AdpChunk, type AdpConfig, type CosParams, type CurrentNode, CurrentNodeStatus, type Debugging, type DocumentParseChunk, type DocumentParseRequest, type ErrorInfo, type FileInfo, type Knowledge, type ParsingEvent, type QuoteInfo, type Reference, type ReferenceEvent, type ReplyEvent, ReplyMethod, type StatisticInfo, type TaskFlow, type ThoughtEvent, type ThoughtProcedure, type TokenStatEvent, type TokenStatProcedure, type WorkFlow };