diff --git a/it0_app/lib/features/agent_call/presentation/pages/agent_call_page.dart b/it0_app/lib/features/agent_call/presentation/pages/agent_call_page.dart index 9f850bf..fdb60a1 100644 --- a/it0_app/lib/features/agent_call/presentation/pages/agent_call_page.dart +++ b/it0_app/lib/features/agent_call/presentation/pages/agent_call_page.dart @@ -8,6 +8,7 @@ import 'package:it0_app/l10n/app_localizations.dart'; import 'package:livekit_client/livekit_client.dart'; import 'package:image_picker/image_picker.dart'; import 'package:file_picker/file_picker.dart'; +import 'package:url_launcher/url_launcher.dart'; import '../../../../core/config/api_endpoints.dart'; import '../../../../core/config/app_config.dart'; import '../../../../core/network/dio_client.dart'; @@ -190,6 +191,15 @@ class _AgentCallPageState extends ConsumerState _scrollToBottom(); } } catch (_) {} + } else if (event.topic == 'oauth_prompt') { + try { + final payload = jsonDecode(utf8.decode(event.data)); + final url = payload['url'] as String? ?? ''; + final instanceName = payload['instanceName'] as String? ?? '小龙虾'; + if (url.isNotEmpty && mounted) { + _showOAuthBottomSheet(url, instanceName); + } + } catch (_) {} } }); @@ -297,6 +307,78 @@ class _AgentCallPageState extends ConsumerState _endCall(); } + /// Show DingTalk OAuth authorization card pushed by iAgent. + void _showOAuthBottomSheet(String url, String instanceName) { + showModalBottomSheet( + context: context, + backgroundColor: const Color(0xFF1A1D2E), + shape: const RoundedRectangleBorder( + borderRadius: BorderRadius.vertical(top: Radius.circular(20)), + ), + builder: (ctx) => Padding( + padding: const EdgeInsets.fromLTRB(24, 20, 24, 36), + child: Column( + mainAxisSize: MainAxisSize.min, + children: [ + Container( + width: 40, height: 4, + decoration: BoxDecoration( + color: Colors.white24, + borderRadius: BorderRadius.circular(2), + ), + ), + const SizedBox(height: 20), + const Text('🦞', style: TextStyle(fontSize: 48)), + const SizedBox(height: 12), + Text( + '授权「$instanceName」接入钉钉', + style: const TextStyle( + color: Colors.white, + fontSize: 18, + fontWeight: FontWeight.bold, + ), + textAlign: TextAlign.center, + ), + const SizedBox(height: 8), + const Text( + '点击下方按钮，在钉钉中一键完成授权绑定', + style: TextStyle(color: Colors.white54, fontSize: 14), + textAlign: TextAlign.center, + ), + const SizedBox(height: 24), + SizedBox( + width: double.infinity, + height: 52, + child: ElevatedButton( + style: ElevatedButton.styleFrom( + backgroundColor: const Color(0xFF1677FF), + shape: RoundedRectangleBorder( + borderRadius: BorderRadius.circular(12), + ), + ), + onPressed: () async { + Navigator.of(ctx).pop(); + final uri = Uri.tryParse(url); + if (uri != null) { + await launchUrl(uri, mode: LaunchMode.externalApplication); + } + }, + child: const Text( + '立即授权', + style: TextStyle( + color: Colors.white, + fontSize: 16, + fontWeight: FontWeight.w600, + ), + ), + ), + ), + ], + ), + ), + ); + } + /// Toggle microphone mute. void _toggleMute() { _isMuted = !_isMuted; diff --git a/it0_app/lib/features/chat/data/models/stream_event_model.dart b/it0_app/lib/features/chat/data/models/stream_event_model.dart index 247ff0a..bfd47c0 100644 --- a/it0_app/lib/features/chat/data/models/stream_event_model.dart +++ b/it0_app/lib/features/chat/data/models/stream_event_model.dart @@ -88,6 +88,13 @@ class StreamEventModel { case 'cancelled': return CancelledEvent(); + case 'oauth_prompt': + return OAuthPromptEvent( + data['url'] as String? ?? '', + data['instanceId'] as String? ?? '', + data['instanceName'] as String? ?? '小龙虾', + ); + default: // Fall back to text event for unknown types return TextEvent( diff --git a/it0_app/lib/features/chat/domain/entities/chat_message.dart b/it0_app/lib/features/chat/domain/entities/chat_message.dart index 9fbb00e..153fb77 100644 --- a/it0_app/lib/features/chat/domain/entities/chat_message.dart +++ b/it0_app/lib/features/chat/domain/entities/chat_message.dart @@ -1,6 +1,6 @@ enum MessageRole { user, assistant, system } -enum MessageType { text, toolUse, toolResult, approval, thinking, standingOrderDraft, interrupted } +enum MessageType { text, toolUse, toolResult, approval, thinking, standingOrderDraft, interrupted, oauthPrompt } enum ToolStatus { executing, completed, error, blocked, awaitingApproval } diff --git a/it0_app/lib/features/chat/domain/entities/stream_event.dart b/it0_app/lib/features/chat/domain/entities/stream_event.dart index a744d91..d73be73 100644 --- a/it0_app/lib/features/chat/domain/entities/stream_event.dart +++ b/it0_app/lib/features/chat/domain/entities/stream_event.dart @@ -67,3 +67,12 @@ class TaskInfoEvent extends StreamEvent { class CancelledEvent extends StreamEvent { CancelledEvent(); } + +/// Emitted when the agent wants to trigger DingTalk OAuth for an agent instance. +/// The UI should show an authorization card so the user can tap "立即授权". +class OAuthPromptEvent extends StreamEvent { + final String url; + final String instanceId; + final String instanceName; + OAuthPromptEvent(this.url, this.instanceId, this.instanceName); +} diff --git a/it0_app/lib/features/chat/presentation/pages/chat_page.dart b/it0_app/lib/features/chat/presentation/pages/chat_page.dart index 00aeac6..aed12af 100644 --- a/it0_app/lib/features/chat/presentation/pages/chat_page.dart +++ b/it0_app/lib/features/chat/presentation/pages/chat_page.dart @@ -3,6 +3,7 @@ import 'dart:io'; import 'package:flutter/material.dart'; import 'package:flutter_riverpod/flutter_riverpod.dart'; import 'package:it0_app/l10n/app_localizations.dart'; +import 'package:url_launcher/url_launcher.dart'; import 'package:image_picker/image_picker.dart'; import 'package:file_picker/file_picker.dart'; import '../../../../core/theme/app_colors.dart'; @@ -483,6 +484,18 @@ class _ChatPageState extends ConsumerState { icon: Icons.cancel_outlined, ); + case MessageType.oauthPrompt: + final url = message.metadata?['url'] as String? ?? ''; + final instanceName = message.metadata?['instanceName'] as String? ?? '小龙虾'; + return TimelineEventNode( + status: NodeStatus.warning, + label: '钉钉授权', + isFirst: isFirst, + isLast: isLast, + icon: Icons.link, + content: _OAuthPromptCard(url: url, instanceName: instanceName), + ); + case MessageType.text: default: return TimelineEventNode( @@ -779,6 +792,50 @@ class _ChatPageState extends ConsumerState { // Standing order content (embedded in timeline node) // --------------------------------------------------------------------------- +// --------------------------------------------------------------------------- +// OAuth prompt card — shown in timeline when agent triggers DingTalk binding +// --------------------------------------------------------------------------- + +class _OAuthPromptCard extends StatelessWidget { + final String url; + final String instanceName; + + const _OAuthPromptCard({required this.url, required this.instanceName}); + + @override + Widget build(BuildContext context) { + return Column( + crossAxisAlignment: CrossAxisAlignment.start, + children: [ + Text( + '点击下方按钮，在钉钉中为「$instanceName」完成一键授权绑定。', + style: const TextStyle(color: AppColors.textSecondary, fontSize: 13), + ), + const SizedBox(height: 10), + SizedBox( + width: double.infinity, + child: ElevatedButton.icon( + icon: const Text('🦞', style: TextStyle(fontSize: 16)), + label: const Text('立即授权'), + style: ElevatedButton.styleFrom( + backgroundColor: const Color(0xFF1677FF), + foregroundColor: Colors.white, + shape: RoundedRectangleBorder(borderRadius: BorderRadius.circular(10)), + padding: const EdgeInsets.symmetric(vertical: 12), + ), + onPressed: () async { + final uri = Uri.tryParse(url); + if (uri != null) { + await launchUrl(uri, mode: LaunchMode.externalApplication); + } + }, + ), + ), + ], + ); + } +} + // --------------------------------------------------------------------------- // Collapsible code block for tool results – collapsed by default, tap to expand // --------------------------------------------------------------------------- diff --git a/it0_app/lib/features/chat/presentation/providers/chat_providers.dart b/it0_app/lib/features/chat/presentation/providers/chat_providers.dart index 347e985..d1985f2 100644 --- a/it0_app/lib/features/chat/presentation/providers/chat_providers.dart +++ b/it0_app/lib/features/chat/presentation/providers/chat_providers.dart @@ -348,6 +348,18 @@ class ChatNotifier extends StateNotifier { if (state.agentStatus != AgentStatus.idle) { state = state.copyWith(agentStatus: AgentStatus.idle, clearTaskId: true); } + + case OAuthPromptEvent(:final url, :final instanceId, :final instanceName): + // Add an authorization card to the timeline so the user can tap "立即授权" + final msg = ChatMessage( + id: DateTime.now().microsecondsSinceEpoch.toString(), + role: MessageRole.assistant, + content: '授权「$instanceName」接入钉钉', + timestamp: DateTime.now(), + type: MessageType.oauthPrompt, + metadata: {'url': url, 'instanceId': instanceId, 'instanceName': instanceName}, + ); + state = state.copyWith(messages: [...state.messages, msg]); } } diff --git a/packages/services/agent-service/src/domain/ports/outbound/agent-engine.port.ts b/packages/services/agent-service/src/domain/ports/outbound/agent-engine.port.ts index 0772c57..210149b 100644 --- a/packages/services/agent-service/src/domain/ports/outbound/agent-engine.port.ts +++ b/packages/services/agent-service/src/domain/ports/outbound/agent-engine.port.ts @@ -47,4 +47,5 @@ export type EngineStreamEvent = } | { type: 'error'; message: string; code: string } | { type: 'cancelled'; message: string; code: string } - | { type: 'task_info'; taskId: string }; + | { type: 'task_info'; taskId: string } + | { type: 'oauth_prompt'; url: string; instanceId: string; instanceName: string }; diff --git a/packages/services/agent-service/src/domain/services/allowed-tools-resolver.service.ts b/packages/services/agent-service/src/domain/services/allowed-tools-resolver.service.ts index 7e530a2..773b307 100644 --- a/packages/services/agent-service/src/domain/services/allowed-tools-resolver.service.ts +++ b/packages/services/agent-service/src/domain/services/allowed-tools-resolver.service.ts @@ -16,11 +16,12 @@ import { TenantAgentConfig } from '../entities/tenant-agent-config.entity'; const ALL_SDK_TOOLS = [ 'Bash', 'Read', 'Write', 'Edit', 'Glob', 'Grep', 'WebFetch', 'WebSearch', 'NotebookEdit', 'Task', + 'initiate_dingtalk_binding', ]; const ROLE_TOOL_MAP: Record = { admin: [...ALL_SDK_TOOLS], - operator: ['Bash', 'Read', 'Write', 'Edit', 'Glob', 'Grep'], + operator: ['Bash', 'Read', 'Write', 'Edit', 'Glob', 'Grep', 'initiate_dingtalk_binding'], viewer: ['Read', 'Glob', 'Grep'], }; diff --git a/packages/services/agent-service/src/infrastructure/engines/claude-api/claude-api-engine.ts b/packages/services/agent-service/src/infrastructure/engines/claude-api/claude-api-engine.ts index c8d285e..f2adcc2 100644 --- a/packages/services/agent-service/src/infrastructure/engines/claude-api/claude-api-engine.ts +++ b/packages/services/agent-service/src/infrastructure/engines/claude-api/claude-api-engine.ts @@ -203,6 +203,11 @@ export class ClaudeApiEngine implements AgentEnginePort { output: result.output, isError: result.isError, }; + + // Emit any UI side-effect events (e.g. oauth_prompt) + if (result.uiEvent) { + yield result.uiEvent as any; + } } // Add tool results as user message to continue the conversation @@ -303,13 +308,28 @@ export class ClaudeApiEngine implements AgentEnginePort { ): Array<{ name: string; description: string; input_schema: Record }> { if (!allowedTools || allowedTools.length === 0) return []; - return allowedTools.map((toolName) => ({ - name: toolName, - description: `Tool: ${toolName}`, - input_schema: { - type: 'object' as const, - properties: {}, + const TOOL_SCHEMAS: Record; required?: string[] }> = { + initiate_dingtalk_binding: { + description: 'Generate a DingTalk OAuth authorization URL for an agent instance and push an authorization card to the user\'s screen. Call this after creating the instance.', + properties: { + instanceId: { type: 'string', description: 'The ID of the newly created agent instance' }, + instanceName: { type: 'string', description: 'The display name of the agent instance' }, + }, + required: ['instanceId', 'instanceName'], }, - })); + }; + + return allowedTools.map((toolName) => { + const schema = TOOL_SCHEMAS[toolName]; + return { + name: toolName, + description: schema?.description ?? `Tool: ${toolName}`, + input_schema: { + type: 'object' as const, + properties: schema?.properties ?? {}, + ...(schema?.required ? { required: schema.required } : {}), + }, + }; + }); } } diff --git a/packages/services/agent-service/src/infrastructure/engines/claude-api/tool-executor.ts b/packages/services/agent-service/src/infrastructure/engines/claude-api/tool-executor.ts index 1d0324c..f944d9e 100644 --- a/packages/services/agent-service/src/infrastructure/engines/claude-api/tool-executor.ts +++ b/packages/services/agent-service/src/infrastructure/engines/claude-api/tool-executor.ts @@ -12,6 +12,8 @@ const exec = promisify(child_process.exec); export interface ToolExecutionResult { output: string; isError: boolean; + /** Optional side-effect event to emit to the client UI (e.g. oauth_prompt). */ + uiEvent?: Record; } @Injectable() @@ -36,6 +38,8 @@ export class ToolExecutor { return this.executeGlob(input.pattern, input.path); case 'Grep': return this.executeGrep(input.pattern, input.path, input.include); + case 'initiate_dingtalk_binding': + return this.executeInitiateDingTalkBinding(input.instanceId as string, input.instanceName as string); default: return { output: `Unknown tool: ${toolName}`, isError: true }; } @@ -121,6 +125,35 @@ export class ToolExecutor { return { output: matches.join('\n') || '(no matches)', isError: false }; } + private async executeInitiateDingTalkBinding( + instanceId: string, + instanceName: string, + ): Promise { + if (!instanceId) { + return { output: 'instanceId is required', isError: true }; + } + try { + const url = `http://localhost:3002/api/v1/agent/channels/dingtalk/oauth/init?instanceId=${encodeURIComponent(instanceId)}`; + const resp = await fetch(url, { signal: AbortSignal.timeout(10_000) }); + if (!resp.ok) { + return { output: `Failed to generate OAuth URL: HTTP ${resp.status}`, isError: true }; + } + const data = await resp.json() as { oauthUrl: string }; + return { + output: 'DingTalk OAuth authorization URL generated. The app will show a one-tap authorization card to the user.', + isError: false, + uiEvent: { + type: 'oauth_prompt', + url: data.oauthUrl, + instanceId, + instanceName: instanceName || instanceId, + }, + }; + } catch (err: any) { + return { output: `Failed to generate OAuth URL: ${err.message}`, isError: true }; + } + } + private async executeGrep( pattern: string, searchPath?: string, diff --git a/packages/services/agent-service/src/infrastructure/engines/claude-code-cli/system-prompt-builder.ts b/packages/services/agent-service/src/infrastructure/engines/claude-code-cli/system-prompt-builder.ts index df0ab8a..e53f8a2 100644 --- a/packages/services/agent-service/src/infrastructure/engines/claude-code-cli/system-prompt-builder.ts +++ b/packages/services/agent-service/src/infrastructure/engines/claude-code-cli/system-prompt-builder.ts @@ -11,6 +11,9 @@ export interface SystemPromptContext { skills?: string[]; riskBoundary?: string; additionalInstructions?: string; + /** Voice session ID — when set, uses the internal wget-based OAuth trigger endpoint + * instead of the initiate_dingtalk_binding tool, so both engines work. */ + sessionId?: string; } /** @@ -29,6 +32,23 @@ export class SystemPromptBuilder { */ build(context: SystemPromptContext): string { const parts: string[] = []; + // Build the DingTalk OAuth trigger instruction once, reused in the prompt below. + // Voice sessions (sessionId present): use Bash/wget to call the internal endpoint — + // works for BOTH claude_api and claude_agent_sdk engines. + // Text sessions (no sessionId): use the initiate_dingtalk_binding tool (claude_api only). + const dingtalkOauthStep = context.sessionId + ? ` Step 3 — Trigger DingTalk OAuth (Bash/wget — works for all engines):\n` + + ` wget -q -O- --post-data='{"instanceId":"","instanceName":""}' \\\n` + + ` --header="Content-Type: application/json" \\\n` + + ` http://localhost:3002/api/v1/agent/sessions/${context.sessionId}/dingtalk/oauth-trigger\n` + + ` This automatically pushes an OAuth authorization card to the user's screen.\n` + + ` Say: "请查看屏幕上弹出的授权卡片，点击「立即授权」按钮，在钉钉里完成一键授权就好了。"\n` + + ` Do NOT read out the URL — the card handles it automatically.` + : ` Step 3 — Trigger DingTalk OAuth (initiate_dingtalk_binding tool):\n` + + ` Call: initiate_dingtalk_binding(instanceId="", instanceName="")\n` + + ` This automatically pushes an OAuth authorization card to the user's screen.\n` + + ` Say: "请查看屏幕上弹出的授权卡片，点击「立即授权」按钮，在钉钉里完成一键授权就好了。"\n` + + ` Do NOT read out the URL — the card handles it automatically.`; // Base instruction parts.push( @@ -45,25 +65,22 @@ export class SystemPromptBuilder { '1. Ask for a name if not given\n' + '2. Use the Current User ID from this prompt as userId\n' + '3. Call the create API with Bash and report the result (id, status, containerName)\n\n' + - '## DingTalk Channel Binding (钉钉接入 — 语音/对话绑定)\n' + - 'iAgent has a centralized DingTalk bot. Users bind their OpenClaw instance to it using a one-time code.\n' + - 'When a user asks to bind DingTalk (e.g. "帮我绑定钉钉", "bind DingTalk", "连接钉钉"), follow these steps:\n\n' + - ' Step 1 — Find the user\'s active instance:\n' + - ' wget -q -O- http://localhost:3002/api/v1/agent/instances/user/\n' + - ' Pick the first instance with status "running". If none running, pick the first one.\n' + - ' If the user has no instances, tell them to create one first.\n\n' + - ' Step 2 — Generate a binding code for the instance:\n' + - ' wget -q -O- --post-data="" http://localhost:3002/api/v1/agent/channels/dingtalk/bind/\n' + - ' This returns JSON: { "code": "A3F9C2", "expiresAt": "..." }\n\n' + - ' Step 3 — Tell the user clearly (voice-friendly):\n' + - ' Speak the code letter-by-letter with pauses: "验证码是 A-3-F-9-C-2"\n' + - ' Instructions: "请在钉钉中找到 iAgent 机器人，向它发送这6位验证码。发送后绑定会自动完成，有效期15分钟。"\n' + - ' If speaking via voice: spell each character slowly for the user to type easily.\n\n' + - ' Check binding status (optional, if user asks):\n' + + '## 招募小龙虾 + 钉钉绑定 (全语音/文字引导)\n' + + 'When a user says "帮我招募一只小龙虾" / "创建小龙虾" / "recruit agent" / "bind DingTalk":\n\n' + + ' Step 1 — Ask for a name if not provided:\n' + + ' "你想给这只小龙虾取个什么名字？"\n\n' + + ' Step 2 — Create the instance (Bash tool):\n' + + ' wget -q -O- --post-data=\'{"name":"","userId":"","usePool":true}\' --header="Content-Type: application/json" http://localhost:3002/api/v1/agent/instances\n' + + ' Parse JSON to get "id" (instanceId) and "name".\n' + + ' Say: "好的，小龙虾「」已经创建好了！"\n\n' + + `${dingtalkOauthStep}\n\n` + + ' Step 4 — Confirm (after user says they authorized):\n' + ' wget -q -O- http://localhost:3002/api/v1/agent/channels/dingtalk/status/\n' + - ' Returns { "bound": true/false }\n\n' + - ' Unbind DingTalk:\n' + - ' wget -q -O- --post-data="" http://localhost:3002/api/v1/agent/channels/dingtalk/unbind/', + ' If { "bound": true }: "太好了！小龙虾「」已成功绑定钉钉，现在可以在钉钉里和它对话了！"\n' + + ' If still false: "授权还没完成，请确认是否点击了钉钉里的授权按钮。"\n\n' + + ' Check/unbind:\n' + + ' Status: wget -q -O- http://localhost:3002/api/v1/agent/channels/dingtalk/status/\n' + + ' Unbind: wget -q -O- --post-data="" http://localhost:3002/api/v1/agent/channels/dingtalk/unbind/', ); // Tenant + user context diff --git a/packages/services/agent-service/src/interfaces/rest/controllers/voice-session.controller.ts b/packages/services/agent-service/src/interfaces/rest/controllers/voice-session.controller.ts index a50148b..b28da05 100644 --- a/packages/services/agent-service/src/interfaces/rest/controllers/voice-session.controller.ts +++ b/packages/services/agent-service/src/interfaces/rest/controllers/voice-session.controller.ts @@ -20,6 +20,9 @@ import { TenantId } from '@it0/common'; import { VoiceSessionManager } from '../../../domain/services/voice-session-manager.service'; import { SessionRepository } from '../../../infrastructure/repositories/session.repository'; import { SystemPromptBuilder } from '../../../infrastructure/engines/claude-code-cli/system-prompt-builder'; +import { AgentStreamGateway } from '../../ws/agent-stream.gateway'; +import { DingTalkRouterService } from '../../../infrastructure/dingtalk/dingtalk-router.service'; +import { AgentInstanceRepository } from '../../../infrastructure/repositories/agent-instance.repository'; import { AgentEngineType } from '../../../domain/value-objects/agent-engine-type.vo'; import { AgentSession } from '../../../domain/entities/agent-session.entity'; import * as crypto from 'crypto'; @@ -32,6 +35,9 @@ export class VoiceSessionController { private readonly voiceSessionManager: VoiceSessionManager, private readonly sessionRepository: SessionRepository, private readonly systemPromptBuilder: SystemPromptBuilder, + private readonly gateway: AgentStreamGateway, + private readonly dingTalkRouter: DingTalkRouterService, + private readonly instanceRepo: AgentInstanceRepository, ) {} /** @@ -57,6 +63,10 @@ export class VoiceSessionController { } } + // Determine sessionId early — needed for embedding in the system prompt + // so Claude can call the DingTalk OAuth trigger endpoint with the correct session. + const sessionId = session?.id ?? crypto.randomUUID(); + // Extract user identity from JWT for context-aware system prompt const jwtUser = (req as any).user; const userId: string | undefined = jwtUser?.sub ?? jwtUser?.userId; @@ -68,12 +78,13 @@ export class VoiceSessionController { tenantId, userId, userEmail, + sessionId, }); if (!session) { // Create a fresh session pre-marked as voice mode session = new AgentSession(); - session.id = crypto.randomUUID(); + session.id = sessionId; session.tenantId = tenantId; session.engineType = AgentEngineType.CLAUDE_AGENT_SDK; session.status = 'active'; @@ -162,4 +173,58 @@ export class VoiceSessionController { this.logger.log(`Voice session terminated: ${sessionId}`); return { sessionId, terminated: true }; } + + /** + * Internal DingTalk OAuth trigger — called by Claude via Bash/wget. + * + * Works for BOTH claude_api and claude_agent_sdk engines because Claude + * calls it with `wget` (a Bash tool call), not a custom tool. + * + * Flow: + * Claude (Bash) → POST /sessions/:sessionId/dingtalk/oauth-trigger + * → generateOAuthUrl() → emit oauth_prompt via WS gateway + * → voice-agent picks up → publish_data to Flutter → bottom sheet opens + * + * This endpoint is intentionally unauthenticated (no JWT guard) because + * it is called from localhost inside the container by Claude's Bash tool. + * The sessionId acts as a capability token — only the agent running the + * session knows it. + */ + @Post(':sessionId/dingtalk/oauth-trigger') + async triggerDingTalkOAuth( + @Param('sessionId') sessionId: string, + @Body() body: { instanceId: string; instanceName?: string }, + ) { + if (!body.instanceId) { + throw new BadRequestException('instanceId is required'); + } + + if (!this.dingTalkRouter.isEnabled()) { + return { triggered: false, reason: 'DingTalk integration not configured' }; + } + + const inst = await this.instanceRepo.findById(body.instanceId); + if (!inst) { + throw new NotFoundException(`Instance ${body.instanceId} not found`); + } + + const instanceName = body.instanceName || inst.name || body.instanceId; + const { oauthUrl } = this.dingTalkRouter.generateOAuthUrl(body.instanceId); + + // Emit the oauth_prompt event to the session's WebSocket stream. + // voice-agent subscribes to this stream and forwards it to Flutter via + // LiveKit publish_data (topic="oauth_prompt"), which triggers the bottom sheet. + this.gateway.emitStreamEvent(sessionId, { + type: 'oauth_prompt', + url: oauthUrl, + instanceId: body.instanceId, + instanceName, + }); + + this.logger.log( + `[VoiceSession ${sessionId}] DingTalk OAuth triggered for instance=${body.instanceId}`, + ); + + return { triggered: true, instanceId: body.instanceId, instanceName }; + } } diff --git a/packages/services/voice-agent/src/agent.py b/packages/services/voice-agent/src/agent.py index 9581aac..60bcfe6 100644 --- a/packages/services/voice-agent/src/agent.py +++ b/packages/services/voice-agent/src/agent.py @@ -339,6 +339,7 @@ async def entrypoint(ctx: JobContext) -> None: agent_service_url=settings.agent_service_url, auth_header=auth_header, engine_type=engine_type, + room=ctx.room, ) # Create and start AgentSession with the full pipeline diff --git a/packages/services/voice-agent/src/plugins/agent_llm.py b/packages/services/voice-agent/src/plugins/agent_llm.py index e011460..9adcff5 100644 --- a/packages/services/voice-agent/src/plugins/agent_llm.py +++ b/packages/services/voice-agent/src/plugins/agent_llm.py @@ -56,12 +56,14 @@ class AgentServiceLLM(llm.LLM): agent_service_url: str = "http://agent-service:3002", auth_header: str = "", engine_type: str = "claude_agent_sdk", + room=None, ): super().__init__() self._agent_service_url = agent_service_url self._auth_header = auth_header self._engine_type = engine_type self._agent_session_id: str | None = None + self._room = room # LiveKit Room — used to publish oauth_prompt events to Flutter # Voice session mode: long-lived agent process tied to the call duration. # True once start_voice_session() completes successfully. @@ -231,6 +233,8 @@ class AgentServiceLLM(llm.LLM): if evt_type == "text": collected_text += evt_data.get("content", "") + elif evt_type == "oauth_prompt": + await self._publish_oauth_prompt(evt_data) elif evt_type in ("completed", "error"): break @@ -325,6 +329,8 @@ class AgentServiceLLM(llm.LLM): if evt_type == "text": collected_text += evt_data.get("content", "") + elif evt_type == "oauth_prompt": + await self._publish_oauth_prompt(evt_data) elif evt_type == "completed": return collected_text elif evt_type == "error": @@ -332,6 +338,22 @@ class AgentServiceLLM(llm.LLM): return collected_text + async def _publish_oauth_prompt(self, evt_data: dict) -> None: + """Publish an oauth_prompt event to Flutter via LiveKit data channel.""" + if not self._room or not self._room.local_participant: + logger.warning("Cannot publish oauth_prompt: room or local_participant not available") + return + try: + payload = json.dumps(evt_data).encode("utf-8") + await self._room.local_participant.publish_data( + payload, + reliable=True, + topic="oauth_prompt", + ) + logger.info("Published oauth_prompt to Flutter: instanceId=%s", evt_data.get("instanceId")) + except Exception as exc: + logger.warning("Failed to publish oauth_prompt: %s", exc) + async def terminate_voice_session(self) -> None: """ Terminate the long-lived voice agent session. @@ -614,6 +636,11 @@ class AgentServiceLLMStream(llm.LLMStream): ) ) + elif evt_type == "oauth_prompt": + asyncio.create_task( + self._llm_instance._publish_oauth_prompt(evt_data) + ) + elif evt_type == "completed": logger.info("Voice inject stream completed") return @@ -775,6 +802,11 @@ class AgentServiceLLMStream(llm.LLMStream): ) ) + elif evt_type == "oauth_prompt": + asyncio.create_task( + self._llm_instance._publish_oauth_prompt(evt_data) + ) + elif evt_type == "completed": logger.info("Agent stream completed") return