Files
ai-agent/internal/pkg/i18nx/locales/en-US.yml
T
t 18c9354095 refactor: 将客服后端重构为宿主可嵌入模块
- 注入数据库、运行时配置、统一响应、文件存储和平台 AI 能力,补充业务读写工具与客户快捷操作契约。

- 移除模块内重复的组织、客户、工单、标签、技能、旧工作流、MCP 和迁移实现,将身份权限与业务主体交由宿主管理。

- 使用 libSQL 重构向量存储,并完善图片消息、访客身份、排队调度、企业微信和支持聊天页面。

- 统一 HTTP、DTO 与 WebSocket 的 snake_case 协议,补齐模块初始化、业务动作和公共载荷等回归测试。
2026-08-28 22:23:13 +08:00

434 lines
26 KiB
YAML

error.e0001: "AI Agent not found"
error.e0002: "AI Agent not found."
error.e0003: "AI Agent not found or disabled."
error.e0004: "AI Agent not found or not enabled."
error.e0005: "Enter an AI Agent name."
error.e0006: "This AI Agent name is already in use."
error.e0007: "AI Agent not found or not enabled."
error.e0008: "The AI configuration linked to this AI Agent does not exist."
error.e0009: "AI configuration not found."
error.e0010: "Select an AI configuration."
error.e0011: "The AI configuration is not enabled."
error.e0012: "AI configuration not found."
error.e0014: "Checkpoint not found."
error.e0015: "The checkpoint does not belong to this AI Agent."
error.e0016: "MCP Tool toolCode does not match serverCode."
error.e0017: "MCP Tool toolCode does not match toolName."
error.e0018: "Invalid MCP Tool toolCode format."
error.e0019: "MCP Tool toolCode, serverCode, and toolName are required."
error.e0020: "Only MCP Tools can be configured."
error.e0021: "Invalid MCP Tool configuration."
error.e0022: "The Excel file is empty."
error.e0023: "Failed to parse the Excel file."
error.e0024: "Failed to read the Excel file."
error.e0025: "FAQ not found."
error.e0026: "FAQ knowledge bases do not support documents."
error.e0027: "Graph Tools can only contain Graph tools."
error.e0028: "Invalid Graph Tools configuration format."
error.e0029: "HTML message content is empty."
error.e0030: "Images in HTML messages must use uploaded files."
error.e0031: "Invalid JSON array format."
error.e0032: "MCP endpoint is required."
error.e0033: "MCP server is not enabled."
error.e0034: "MCP server configuration not found."
error.e0035: "MCP is not enabled."
error.e0048: "OSS accessKeyId is not configured."
error.e0049: "OSS accessKeySecret is not configured."
error.e0050: "OSS bucket is not configured."
error.e0051: "OSS endpoint is not configured."
error.e0052: "Invalid Skill ID."
error.e0053: "Skill not found."
error.e0054: "Skill not found or not enabled."
error.e0055: "Enter a Skill name."
error.e0056: "Skill is not enabled."
error.e0057: "Skill is required."
error.e0058: "This Skill already exists."
error.e0059: "Web channel position must be left or right."
error.e0060: "Invalid web channel configuration."
error.e0061: "AI Agent ID is required."
error.e0062: "Channel not found."
error.e0063: "Checkpoint ID is required."
error.e0064: "Conversation ID is required."
error.e0065: "Customer ID is required."
error.e0066: "Document ID or FAQ ID is required."
error.e0067: "Invalid index status."
error.e0068: "openKfID is required."
error.e0069: "This openKfId is already used by another channel."
error.e0070: "Server code is required."
error.e0071: "Skill definition ID is required."
error.e0072: "Ticket is required."
error.e0073: "The MCP server bound to this tool code does not exist or is not enabled."
error.e0074: "Tool code is required."
error.e0075: "Invalid tool code format."
error.e0076: "Tool name is required."
error.e0077: "tool_search only supports calling MCP toolCode."
error.e0078: "User message is required."
error.e0079: "The uploaded file exceeds the size limit."
error.e0080: "Unsupported sender type."
error.e0081: "Unsupported read operation type."
error.e0082: "Unsupported file storage type."
error.e0083: "A tag cannot be moved under itself."
error.e0084: "A directory cannot be moved under itself."
error.e0085: "Schedules cannot be added or changed for past dates."
error.e0086: "Transaction context is required."
error.e0087: "You can only recall messages you sent."
error.e0088: "Only deleted Skills can be restored."
error.e0089: "Only .xlsx files are supported."
error.e0090: "Only image files are supported."
error.e0091: "Only agent messages can be recalled."
error.e0092: "Only one primary contact method can be set."
error.e0093: "WeCom AgentID is not configured."
error.e0094: "WeCom openKfID is required."
error.e0095: "WeCom media ID is required."
error.e0096: "WeCom customer ID is required."
error.e0097: "This WeCom phone number is already used by a system user."
error.e0098: "The WeCom channel is not linked to an AI Agent."
error.e0099: "The AI Agent linked to this WeCom channel does not exist or has been disabled."
error.e0100: "WeCom is not enabled or its configuration is incomplete."
error.e0101: "WeCom message ID is required."
error.e0102: "Invalid WeCom channel configuration."
error.e0103: "WeCom channel configuration is missing openKfId."
error.e0104: "This WeCom user ID is already used as a system username."
error.e0105: "Failed to get the WeCom user ID."
error.e0106: "WeCom user information not found."
error.e0107: "WeCom sign-in callback URL is not configured."
error.e0108: "WeCom sign-in secret is not configured."
error.e0109: "WeCom sign-in is not enabled."
error.e0110: "WeCom sign-in state is invalid."
error.e0111: "WeCom sign-in state is invalid or has expired."
error.e0112: "The system user linked to this WeCom account does not exist."
error.e0113: "WeCom returned an empty image media_id."
error.e0114: "WeCom returned an empty message ID."
error.e0115: "This WeCom email address is already used by a system user."
error.e0116: "Conversation not found."
error.e0117: "The conversation does not belong to this AI Agent."
error.e0118: "The conversation does not belong to this customer."
error.e0119: "This conversation is closed."
error.e0120: "This conversation has not been assigned to an agent, so messages cannot be sent yet."
error.e0121: "Invalid conversation filter."
error.e0122: "Select a provider."
error.e0123: "Invalid fallback policy."
error.e0124: "Company not found."
error.e0125: "Enter a company name."
error.e0126: "This company name is already in use."
error.e0127: "Linked user not found."
error.e0128: "Enter a close reason."
error.e0129: "Unsupported content type."
error.e0130: "Unsupported chunking strategy."
error.e0131: "Failed to create the conversation."
error.e0132: "A single schedule entry cannot span multiple days."
error.e0133: "Invalid request parameters."
error.e0134: "Only active conversations can be transferred."
error.e0135: "Only queued conversations can be assigned."
error.e0136: "Only queued conversations can be auto-assigned."
error.e0137: "Only queued unassigned conversations can be auto-assigned."
error.e0138: "Only FAQs in the current knowledge base can be moved."
error.e0139: "Only documents in the current knowledge base can be moved."
error.e0140: "Only directories in the same knowledge base and same level can be reordered."
error.e0141: "A tag with this name already exists at the same level."
error.e0142: "A directory with this name already exists at the same level."
error.e0143: "Enabled AI configurations cannot be deleted."
error.e0144: "Reply timeout seconds cannot be less than 0."
error.e0145: "Image message is missing assetId."
error.e0146: "Image asset not found."
error.e0147: "Enter a base URL."
error.e0148: "Enter a progress update."
error.e0149: "External user ID is required."
error.e0150: "External identity is not initialized."
error.e0151: "There are conflicting schedules. Resolve the conflicts first."
error.e0152: "A directory with subdirectories cannot be moved to the second level."
error.e0153: "Some ticket tags are invalid."
error.e0154: "Some ticket tags are disabled."
error.e0155: "Customer not found."
error.e0156: "Enter a customer name."
error.e0157: "Support session is required."
error.e0158: "Support session parameters are incomplete."
error.e0159: "Support session secret is not configured."
error.e0160: "The support session has expired."
error.e0161: "Support session verification failed."
error.e0162: "Enter both agent ID and display name."
error.e0163: "This agent ID is already in use."
error.e0164: "Agent profile not found."
error.e0165: "Invalid agent status."
error.e0166: "This agent team is linked to AI Agents and cannot be deleted."
error.e0167: "This agent team has linked agent profiles and cannot be deleted."
error.e0168: "This agent team has schedules and cannot be deleted."
error.e0169: "Agent team not found."
error.e0170: "Enter an agent team name."
error.e0171: "This agent team name is already in use."
error.e0172: "Agent team schedule not found."
error.e0173: "Agent team is not enabled."
error.e0174: "Invalid agent team status."
error.e0175: "Invalid password length."
error.e0176: "Failed to read the import file."
error.e0177: "Invalid import mode."
error.e0178: "Ticket not found."
error.e0179: "Enter a ticket description."
error.e0180: "Invalid ticket source."
error.e0181: "Enter a ticket title."
error.e0182: "Invalid ticket status."
error.e0183: "Closed conversations cannot be linked to customers."
error.e0184: "Restore this deleted Skill before changing its status."
error.e0185: "This AI Agent is linked to channels and cannot be deleted."
error.e0186: "Platform message not found."
error.e0189: "This conversation is not currently handled by AI."
error.e0190: "This conversation has already been assigned."
error.e0191: "This conversation has been assigned to another agent."
error.e0192: "This conversation has already been taken over by a human agent."
error.e0193: "This conversation is not assigned to an agent."
error.e0194: "Human support is currently outside service hours."
error.e0195: "Reading files from this storage provider is not supported yet."
error.e0196: "This channel does not support a user JWT secret."
error.e0197: "This conversation cannot be closed in its current status."
error.e0198: "The current sign-in identity is not an internal enterprise member."
error.e0199: "This knowledge base is not an FAQ knowledge base."
error.e0200: "The current system account has been disabled."
error.e0201: "Invalid WeChat Official Account channel configuration."
error.e0202: "WeChat authorization code is required."
error.e0203: "Quick reply not found."
error.e0204: "Company not found."
error.e0205: "Agent team not found."
error.e0206: "This phone number is already in use."
error.e0207: "Enter a Skill description."
error.e0208: "Channel not found."
error.e0209: "The channel does not exist or has been disabled."
error.e0210: "Channel error."
error.e0211: "The channel is not initialized."
error.e0212: "Recipient is required."
error.e0213: "This file cannot be accessed."
error.e0214: "File not found."
error.e0215: "Text content is required."
error.e0216: "Text list is required."
error.e0217: "Text message content is empty."
error.e0218: "Document not found."
error.e0219: "Document knowledge bases cannot use the FAQ chunking strategy."
error.e0220: "Enter a new password."
error.e0221: "You do not have permission to close this conversation."
error.e0222: "You do not have permission to access this conversation."
error.e0223: "You do not have permission to transfer this conversation."
error.e0224: "You do not have permission to link this conversation."
error.e0225: "You do not have permission to perform this action."
error.e0226: "You do not have permission to perform this action."
error.e0227: "Invalid time format."
error.e0228: "Weekday must be between 1 and 7."
error.e0229: "Maximum concurrent conversations cannot be less than 0."
error.e0230: "Invalid service mode."
error.e0231: "No matching WeCom channel was found."
error.e0232: "No schedules were generated."
error.auth.expired: "Your session has expired. Please sign in again."
error.e0234: "No available AI configuration is configured."
error.e0235: "No available embedding model is configured."
error.e0236: "Permission not found."
error.e0237: "The standard question already exists and was skipped."
error.e0238: "Tag not found."
error.e0239: "Enter a tag name."
error.e0240: "Enter both title and content."
error.e0241: "Retrieval log not found."
error.e0242: "Enter a model name."
error.e0243: "Select a model type."
error.e0244: "Message not found."
error.e0245: "Message content is required."
error.e0246: "This message has been recalled."
error.e0247: "Enter a channel name."
error.e0248: "This channel code is already in use."
error.e0249: "Invalid channel status."
error.e0250: "Invalid channel type."
error.e0251: "Parent tag not found."
error.e0252: "Parent directory not found."
error.e0253: "The parent directory does not belong to the current knowledge base."
error.e0254: "Invalid status value."
error.e0255: "User not found."
error.e0256: "The user does not exist or has been disabled."
error.e0257: "Enter a username."
error.e0258: "Enter both username and password."
error.e0259: "This username is already in use."
error.e0260: "The username or password is incorrect."
error.e0261: "User name is required."
error.e0262: "User ID is required."
error.e0263: "User identity is required."
error.e0264: "User identity has expired."
error.e0265: "User identity verification failed."
error.e0266: "User identity verification is not configured."
error.e0267: "Login credential has been invalidated."
error.e0268: "Login credential has expired."
error.e0269: "Invalid login credential."
error.e0270: "Too many failed sign-in attempts. Please try again later."
error.e0271: "The sign-in ticket is invalid or has expired."
error.e0272: "Sign-in result is required."
error.e0273: "Directory not found."
error.e0274: "Directories cannot be moved to another knowledge base."
error.e0275: "Directory name is required."
error.e0276: "Target agent not found."
error.e0277: "The target agent must be different from the current assignee."
error.e0278: "Select a target agent."
error.e0279: "The target tool is not authorized for the current conversation."
error.e0280: "Invalid similar-question format."
error.e0281: "This knowledge base contains FAQs and cannot be deleted."
error.e0282: "This knowledge base contains documents and cannot be deleted."
error.e0283: "Knowledge base not found."
error.e0284: "Knowledge base is required."
error.e0285: "Knowledge base is not enabled."
error.e0286: "This knowledge base directory is unavailable."
error.e0287: "Knowledge base directory not found."
error.e0288: "This directory does not belong to the current knowledge base."
error.e0289: "Knowledge base directories support at most two levels."
error.e0290: "Unsupported knowledge base type."
error.e0291: "Disabled roles cannot be assigned."
error.e0292: "Enter an answer."
error.e0293: "Built-in system roles cannot be deleted."
error.e0294: "Team lead user not found."
error.e0295: "End date must be later than or equal to start date."
error.e0296: "End time must be later than start time."
error.e0297: "The standard question column is missing."
error.e0298: "The answer column is missing."
error.e0299: "Contact method not found."
error.e0300: "Contact method is required."
error.e0301: "Invalid contact method type."
error.e0302: "View not found."
error.e0303: "Enter a view name."
error.e0304: "The view filter format is invalid."
error.e0305: "Role not found."
error.e0306: "Enter both role name and role code."
error.e0307: "This role is assigned to users and cannot be deleted."
error.e0308: "This role code is already in use."
error.e0309: "This agent team already has a schedule in the selected time period."
error.e0310: "This tag has child tags and cannot be deleted."
error.e0311: "This tag is linked to conversations and cannot be deleted."
error.e0312: "This tag is linked to tickets and cannot be deleted."
error.e0313: "This channel does not support public support configuration."
error.e0314: "This user already has an agent profile."
error.e0315: "This directory contains FAQs and cannot be deleted."
error.e0316: "This directory contains subdirectories and cannot be deleted."
error.e0317: "This directory contains documents and cannot be deleted."
error.e0318: "This contact method already exists."
error.e0319: "Use the delete endpoint to mark a Skill as deleted."
error.e0320: "Select at least one knowledge base."
error.e0321: "Select an AI Agent."
error.e0322: "Choose an image to upload."
error.e0323: "Choose a file to upload."
error.e0324: "Choose an attachment to upload."
error.e0325: "Select a user to link."
error.e0326: "Select an agent team."
error.e0327: "Choose a file to import."
error.e0328: "Select an agent team."
error.e0329: "Select a weekday."
error.e0330: "Select FAQs to delete."
error.e0331: "Select documents to delete."
error.e0332: "Select FAQs to move."
error.e0333: "Select documents to move."
error.e0334: "Assignee not found."
error.path.invalid: "Invalid path parameter."
error.e0336: "Invalid human handoff mode."
error.e0337: "Notification not found."
error.e0338: "This email address is already in use."
error.e0339: "Enter a configuration name."
error.e0340: "Enter a question."
error.e0341: "The question cannot exceed 500 characters."
error.e0342: "Attachment not found."
error.e0343: "The attachment has not finished uploading."
error.e0344: "Invalid attachment message payload format."
error.e0345: "Attachment message is missing assetId."
error.e0346: "Attachment message is missing payload."
error.e0347: "Default team queue mode requires at least one agent team."
error.notFound: "Not found"
error.knowledgeBase.referencedByAgent: "This knowledge base is referenced by AI Agent \"%s\". Remove the binding first."
error.knowledgeBase.referencedByAgents: "This knowledge base is referenced by %d AI Agents. Remove the bindings first."
error.agentTeamSchedule.batchLimit: "You can generate at most %d schedule entries at a time."
error.agentTeamSchedule.conflictRange: "This agent team already has a schedule from %s to %s."
error.knowledgeFAQImport.duplicateQuestionInFile: "The standard question is duplicated in the same file. It first appeared on row %d."
error.mcp.listToolsFailed: "Failed to list MCP tools: %v"
error.mcp.callToolFailed: "Failed to call MCP tool: %v"
error.mcp.connectServerFailed: "Failed to connect to MCP Server: %v"
error.wxwork.unsupportedOutboundMessageType: "Unsupported WeCom outbound message type: %s"
error.wxwork.currentUnsupportedOutboundMessageType: "The current WeCom outbound message type is not supported yet: %s"
error.param.required: "Parameter %s is required."
error.wxwork.userIDMissing: "Failed to get the WeCom user ID."
error.wxwork.userIDTaken: "The WeCom user ID is already used as a system username."
error.wxwork.mobileTaken: "The WeCom mobile number is already used by a system user."
error.wxwork.emailTaken: "The WeCom email address is already used by a system user."
error.wxwork.configIncomplete: "WeCom is not enabled or its configuration is incomplete."
error.conversation.createFailed: "Failed to create conversation."
error.conversation.tagNotFound: "Tag not found."
error.aiConfig.noneEnabled: "No available AI configuration is configured."
error.embeddingModel.noneEnabled: "No available Embedding model is configured."
error.agentTeamSchedule.startAtInvalid: "Invalid start time format."
error.agentTeamSchedule.startAtInvalidWithFormat: "Invalid start time format. Use yyyy-MM-dd HH:mm:ss or RFC3339."
error.agentTeamSchedule.endAtInvalid: "Invalid end time format."
error.agentTeamSchedule.endAtInvalidWithFormat: "Invalid end time format. Use yyyy-MM-dd HH:mm:ss or RFC3339."
error.agentTeamSchedule.startDateInvalid: "Invalid start date format."
error.agentTeamSchedule.startDateInvalidWithFormat: "Invalid start date format. Use yyyy-MM-dd."
error.agentTeamSchedule.endDateInvalid: "Invalid end date format."
error.agentTeamSchedule.endDateInvalidWithFormat: "Invalid end date format. Use yyyy-MM-dd."
error.agentTeamSchedule.startTimeInvalid: "Invalid start time format."
error.agentTeamSchedule.startTimeInvalidWithFormat: "Invalid start time format. Use HH:mm or HH:mm:ss."
error.agentTeamSchedule.endTimeInvalid: "Invalid end time format."
error.agentTeamSchedule.endTimeInvalidWithFormat: "Invalid end time format. Use HH:mm or HH:mm:ss."
tool.builtin.toolSearch.title: "Search and Run Dynamic Tools"
tool.builtin.toolSearch.description: "Searches the MCP tools currently available to the agent and runs the selected tool after its toolCode is confirmed. Best for long-tail tools; it should not replace fixed built-in workflow tools."
tool.builtin.toolSearch.appendix: |-
When you need long-tail MCP capabilities, prefer the tool_search tool and follow these rules:
1. Call tool_search first to find the dynamic tool you need, then continue with the selected real tool.
2. Do not assume all long-tail tools are visible at the start; only tools selected by tool_search are exposed to subsequent model calls.
3. If a fixed built-in tool can already complete the task, prefer the fixed tool and do not overuse tool_search.
tool.builtin.skill.title: "Load Skill Instructions"
tool.builtin.skill.description: "Loads specialized skill instructions for the current agent when extra task-specific guidance is needed."
tool.graph.triageServiceRequest.title: "Route Service Request"
tool.graph.triageServiceRequest.description: "Analyzes the current conversation to decide whether to keep answering or hand off to a human."
tool.graph.triageServiceRequest.appendix: |-
When you need to decide between continuing the answer or handing off to a human, call triage_service_request first.
1. If recommendedAction=continue_answering, continue clarifying or answering.
2. If recommendedAction=handoff_to_human, confirm the reason is sufficient before calling handoff_to_human.
tool.graph.analyzeConversation.title: "Analyze Conversation Risk and Summary"
tool.graph.analyzeConversation.description: "Summarizes the current conversation, identifies risk signals, and recommends whether to keep answering or hand off to a human."
tool.graph.analyzeConversation.appendix: |-
When the conversation may involve escalation, refunds, compensation, clear negative sentiment, or human handoff, call analyze_conversation first.
1. This tool returns a structured summary, risk signals, and next-step recommendation.
2. If the tool recommends handoff_to_human, confirm the handoff conditions before calling handoff_to_human.
3. If the tool recommends continue_answering, continue clarifying and answering instead of escalating too early.
tool.graph.handoffConversation.title: "Handoff to Human With Confirmation"
tool.graph.handoffConversation.description: "Guides human handoff with reason preparation, customer confirmation, actual transfer, and final result delivery."
tool.graph.handoffConversation.appendix: |-
You can call handoff_to_human after confirming that human help is needed, but follow these rules:
1. Only call this tool when the user explicitly asks for a human agent or you have determined that the issue must be handled by a human.
2. Before calling it, summarize the handoff reason clearly. If the reason is vague, ask a follow-up question first.
3. Once you decide to hand off, you must call handoff_to_human. Do not simply say in text that you have connected the user to a human.
4. This Graph Tool asks the user for confirmation first. The handoff happens only after the user confirms; if the user cancels, the flow ends.
5. If the issue can still be solved in the current conversation, continue helping instead of escalating too early.
6. If the tool returns terminal=true and shouldRetry=false, the handoff flow has ended. Do not call it repeatedly.
conversation.handoff.waiting: "You are now in the human support queue. You can keep leaving messages, and the agent will see them when connected."
conversation.handoff.offHours: "Human support is currently outside service hours. You can keep describing the issue and I will do my best to help. You can also request a human agent again when service hours resume."
notification.conversationTransferred.title: "Conversation transferred"
notification.conversationAutoAssigned.title: "Conversation auto-assigned"
notification.conversationAssigned.title: "Conversation assigned"
notification.conversationAssigned.line: "Conversation #%s has been assigned to you."
notification.conversationAssigned.reason: "Assignment reason: %s"
notification.conversationTransferred.reason: "Transfer reason: %s"
notification.assignee: "Assignee: %s"
notification.conversationAssigned.wxwork.id: "Conversation ID: #%d"
notification.conversationAssigned.wxwork.summary: "Summary: %s"
notification.conversationAssigned.wxwork.channel: "Channel: %s"
notification.conversationAssigned.wxwork.status: "Status: %s"
notification.time: "Time: %s"
graph.confirmOrCancel: "Please reply with \"Confirm\" or \"Cancel\"."
graph.needExplicitConfirmation: "I need your explicit confirmation. Please reply with \"Confirm\" or \"Cancel\"."
graph.confirmationExpired: "This confirmation has expired. Please start again."
graph.cancelHandoff: "Human handoff has been cancelled."
graph.defaultHandoffReason: "The user needs human support."
graph.handoffConfirmPrompt: |-
I am ready to connect you to a human support agent.
Reason: %s
Please reply with "Confirm" or "Cancel".
conversation.interrupt.defaultPrompt: "Please provide more information and try again."
tool.graph.handoffConversation.info: "Graph Tool. Handles handoff reason preparation, user confirmation, actual human handoff, and result return. Use only when the user explicitly asks for a human agent or you have confirmed that human handling is required. Do not repeat the call when the result has terminal=true and shouldRetry=false."
tool.graph.handoffConversation.param.reason: "Handoff reason. Briefly explain why a human is needed, such as explicit user request, manual verification, or after-sales handling."
tool.graph.triageServiceRequest.info: "Graph Tool. Analyzes the current conversation to decide whether to continue answering or hand off to a human."
tool.graph.triageServiceRequest.param.goal: "Analysis goal, such as whether to escalate or hand off to a human."
tool.graph.triageServiceRequest.param.observedIssue: "Main issue or dispute observed in the conversation."
tool.graph.triageServiceRequest.param.needHumanHandoff: "Whether to focus on evaluating human handoff."
tool.graph.triageServiceRequest.param.additionalContext: "Additional context, such as risk signals or constraints already identified."
tool.graph.analyzeConversation.info: "Graph Tool. Summarizes the current conversation, identifies complaint/payment/sentiment risk signals, and recommends whether to continue answering or hand off to a human."
tool.graph.analyzeConversation.param.goal: "Analysis goal, such as whether to hand off to a human or perform risk review."
tool.graph.analyzeConversation.param.observedIssue: "Main issue or request observed in the conversation."
tool.graph.analyzeConversation.param.needQualityCheck: "Whether to focus on risk or quality review."
tool.graph.analyzeConversation.param.additionalContext: "Additional context, such as disputes, complaint points, or business constraints already identified."