Agents
Agents
@toothfairyai/sdk@latest…Agent Management Module Handles agent CRUD operations and retrieval.
Accessed via client.agents.
Methods
| Method | HTTP | Endpoint |
|---|---|---|
create | POST | POST /agent/create |
get | GET | GET /agent/get/{id} |
update | POST | POST /agent/update |
delete | DELETE | DELETE /agent/delete/{id} |
list | GET | GET /agent/list |
getByMode | — | derived |
search | — | derived |
getRetrievers | — | derived |
getChatters | — | derived |
getCoders | — | derived |
getPlanners | — | derived |
clone | — | derived |
create
Create a new agent
async create(data: AgentCreateData)
Endpoint: POST /agent/create · API service
Request fields
| Field | Type | Required | Description |
|---|---|---|---|
id | string | no | Unique identifier |
workspaceid | string | yes | Unique workspace identifier (UUID v4) |
label | string | yes | Human-readable display name |
description | string | no | Detailed description of purpose and capabilities |
interpolationString | string | yes | The prompt text/template (with interpolation variables) |
customToolingInstructions | string | no | Custom instructions for tool/function usage |
goals | string | yes | Primary objectives the agent should achieve |
pertinencePassage | string | no | Text passage used to improve response relevance |
inhibitionPassage | string | no | Text passage defining prohibited behaviors or content |
defaultAnswer | string | no | Default response when the agent cannot answer |
noKnowledgeDefaultAnswer | string | no | Response shown when no relevant knowledge is found |
subject | string | no | Subject matter expertise area |
qaUrl | string | no | URL for Q&A/knowledge source |
mode | string | yes | Operating mode of the agent: retriever (knowledge retrieval), coder (code execution), chatter (conversational), planner (multi-agent orchestration), computer (browser/desktop automation), or voice (voice interaction) |
Allowed: retriever, coder, chatter, planner, computer, voice |
| temperature | string | yes | Randomness level in responses (0.001-1.0); higher values produce more varied output |
| maxTokens | integer | yes | Maximum number of tokens in the agent's response |
| maxHistory | integer | yes | Maximum number of conversation turns retained in context |
| maxTopics | integer | no | Maximum number of topics considered (1-5) |
| topK | integer | yes | Number of top retrieval results considered when generating a response |
| docTopK | integer | yes | Number of top documents retrieved for context |
| minRetrievalScore | string | no | Minimum score threshold for retrieval results (0.01-0.99) |
| keywordsWeightInRetrieval | integer | no | Weight of keywords in retrieval scoring (0-5) |
| recencyImportance | integer | no | Weight of recency in retrieval scoring (0-5) |
| maxRecencyIncrease | string | no | Maximum recency score increase (0.0-1.0) |
| recencyTopKIncreaseFactor | integer | no | Factor by which recency increases top-K (0-5) |
| allowedTopics | string | no | List of topic IDs the agent is restricted to (max 10) |
| staticDocs | string | no | JSON-encoded static documents available to the hook |
| functionContext | string | no | List of function IDs providing additional context |
| hasTopicsContext | boolean | no | Whether topic context is considered when generating responses |
| topicEnhancer | boolean | no | Whether responses are enhanced with topic information |
| keyWordsForKnowledgeBase | boolean | no | Whether keyword-based knowledge base queries are used |
| summarisation | boolean | no | Whether the agent summarizes long content |
| compressor | boolean | no | Whether context compression is enabled to reduce token usage |
| hasMemory | boolean | no | Whether the agent maintains conversation memory across turns |
| isLongTermMemoryEnabled | boolean | no | Whether long-term memory persistence is enabled |
| hasFunctions | boolean | no | Whether the agent can execute external functions/tools |
| agentFunctions | string | no | List of function IDs associated with the agent |
| agentFnParams | string | no | JSON-encoded parameters for agent functions |
| llmProvider | string | no | LLM provider (e.g. openai, anthropic, tf) |
| llmBaseModel | string | no | Base LLM model identifier (e.g. sorcerer, mystica, gpt-4) |
| functionCallingProvider | string | no | Provider used for function/tool calling |
| functionCallingModel | string | no | Model used for function/tool calling |
| llmSeed | integer | no | Random seed for LLM generation reproducibility |
| hasModeration | boolean | no | Whether content moderation is enabled |
| moderationMessage | string | no | Message shown when content is moderated/rejected |
| customModerations | string | no | Custom moderation rules (JSON) |
| hasNER | boolean | no | Whether named entity recognition is enabled |
| showAgentName | boolean | no | Whether the agent name is shown in responses |
| hideReasoning | boolean | no | Whether the reasoning process is hidden from users |
| plainTextOutput | boolean | no | Whether output is plain text only (no formatting) |
| enableJsonOutput | boolean | no | Whether structured JSON output mode is enabled |
| jsonOutputStructure | string | no | JSON schema defining the structure for JSON output mode |
| predictedPlanJson | string | no | JSON representation of the predicted execution plan |
| extendedOutput | boolean | no | Whether extended output metadata is included |
| tabulate | boolean | no | Whether tabular output formatting is used |
| showReferencesToInternalDocs | boolean | no | Whether references to internal documents are shown |
| showCitations | boolean | no | Whether source citations are shown in responses |
| showTimeForResponse | boolean | no | Whether response time is displayed |
| showDetectedLanguage | boolean | no | Whether the detected language is shown |
| showRoutedModel | boolean | no | Which model was routed to for the response is shown |
| dynamicPlaceholderMessageOnLoading | boolean | no | Whether the loading placeholder message is dynamic |
| generateExtendedReport | boolean | no | Whether an extended report is generated |
| icon | string | no | Icon identifier for the agent |
| largeLogo | string | no | URL or key for the agent's large logo |
| icoUrl | string | no | URL for the agent's favicon (.ico or .png) |
| color | string | no | Hex color code for agent display (light theme) |
| darkColor | string | no | Hex color code for agent display (dark theme) |
| logoBackground | string | no | Hex color code for logo background (light theme) |
| darkLogoBackground | string | no | Hex color code for logo background (dark theme) |
| forcedTheme | string | no | Forced UI theme for this agent |
| placeholderInputMessage | string | no | Placeholder text shown in the input field |
| placeholderMessageOnLoading | string | no | Placeholder message shown while loading |
| messageOnLaunch | string | no | Welcome message shown when the chat starts |
| disclaimer | string | no | Disclaimer text displayed to users |
| quickQuestions | string | no | Semicolon-separated suggested quick questions (max 3) |
| splashTitle | string | no | Title shown on the splash screen |
| showSplashWhenEmpty | boolean | no | Whether the splash screen is shown when the chat is empty |
| preventWidgetUsage | boolean | no | Whether widget usage is prevented |
| allowFeedback | boolean | no | Whether users can provide feedback on responses |
| promptBuffering | boolean | no | Prompt buffering |
| restrictedAccess | boolean | no | Whether access to this agent is restricted |
| restrictedAccessUsers | string | no | List of user IDs with access to this restricted agent |
| enhancedApproverUsers | string | no | List of users who can approve enhanced actions |
| isMultiLanguageEnabled | boolean | no | Whether multi-language support is enabled |
| advancedLanguageDetection | boolean | no | Whether advanced language detection is used |
| languageDetectionConfidence | string | no | Confidence threshold for language detection (0.5-1.0) |
| allowEmailToAgent | boolean | no | Whether the agent can be reached via email |
| forceNewThreadOnProgrammaticRequest | boolean | no | Whether programmatic requests force a new conversation thread |
| allowedEmails | string | no | Comma-separated list of allowed email addresses |
| phoneNumberAsSender | string | no | Phone number used as sender identity |
| whatsappNumberAsSender | string | no | WhatsApp number used as sender identity |
| emailAsSender | string | no | Email address used as sender identity |
| communicationServices | string | no | List of communication service IDs enabled for the agent |
| channelCallbackDelay | integer | no | Delay (seconds) before channel callback (0-120) |
| analyticsInstructions | string | no | Custom instructions for analytics processing |
| charting | boolean | no | Whether the agent can generate charts (TF models only) |
| allowImagesUpload | boolean | no | Whether users can upload images |
| allowAudiosUpload | boolean | no | Whether users can upload audio files |
| allowDocsUpload | boolean | no | Whether users can upload documents |
| hasImages | boolean | no | Whether the agent can process images |
| allowIntrospection | boolean | no | Whether the agent can introspect its own capabilities |
| promptTopKeywords | integer | no | Number of top keywords extracted from prompts for retrieval (1-10) |
| agenticRAG | boolean | no | Whether agentic retrieval-augmented generation is enabled (retriever mode) |
| type | string | no | Type classification (free-form string identifier) |
| version | string | no | Version identifier for the agent configuration |
| emoji | string | no | Emoji icon for the folder |
| messagesOnLaunch | string | no | List of quick-start messages shown on launch |
| rotateMessagesOnLaunch | boolean | no | Whether launch messages are rotated |
| rotateMessagesOnLaunchInterval | integer | no | Interval for rotating launch messages |
| customGreetingInstructions | string | no | Custom instructions for the greeting message |
| customConclusionInstructions | string | no | Custom instructions for the conclusion message |
| customChartingInstructions | string | no | Custom instructions for chart generation |
| customSummarisationInstructions | string | no | Custom instructions for content summarization |
| customImagesInstructions | string | no | Custom instructions for image handling |
| openByDefault | boolean | no | Whether the agent is open by default in the UI |
| isDefault | boolean | no | Whether this is the default agent for the workspace |
| showDocumentsReferences | boolean | no | Whether document references are displayed |
| stopSequence | string | no | Sequence that stops response generation |
| enhancementPassage | string | no | Text passage used to enhance response quality |
| timeSignificance | boolean | no | Whether time significance is considered in responses |
| seed | integer | no | Random seed for reproducible generation |
| fnReasoningEffort | string | no | Reasoning effort level for function-calling |
| canvasEnabled | boolean | no | Whether canvas (visual workspace) is enabled |
| advancedCompute | boolean | no | Whether advanced compute capabilities are enabled |
| regionalEndpoint | string | no | Regional endpoint override for the LLM |
| agentCategoryType | string | no | Category classification for the agent |
| agentVersion | string | no | Version identifier for the agent configuration |
| llmEndpoint | string | no | Custom LLM endpoint URL |
| llmUrl | string | no | Custom LLM URL |
| llmUrlType | string | no | Type of custom LLM URL |
| llmUrlStatus | string | no | Status of the custom LLM URL connection |
| llmTopK | integer | no | Top-K parameter for the LLM |
| visionProvider | string | no | Provider for vision/image understanding |
| videoGenerationProvider | string | no | Provider for video generation |
| treeOfThoughts | boolean | no | Whether tree-of-thoughts reasoning is used |
| hasMath | boolean | no | Whether mathematical computation capabilities are enabled |
| hasComputer | boolean | no | Whether computer/browser automation is enabled (computer mode) |
| mcps | string | no | List of MCP (Model Context Protocol) server IDs associated with the agent |
| hasContentCreation | boolean | no | Whether content creation capabilities are enabled |
| customCodeExecutionEnvironments | string | no | List of custom code execution environment IDs |
| hasCode | boolean | no | Whether code execution capabilities are enabled |
| showCodeInExecution | boolean | no | Whether code is displayed during execution |
| agenticCodingModel | string | no | Model used for agentic code generation |
| visionModel | string | no | Model used for vision/image understanding |
| allowInternetSearch | boolean | no | Whether internet search is allowed |
| allowDeepInternetSearch | boolean | no | Whether deep internet search is allowed |
| internetSearchModes | string | no | List of internet search modes enabled |
| internetSearchLocation | string | no | Geographic location preference for internet search |
| bannedDomains | string | no | List of domains excluded from internet search |
| maxUrlsForInternetSearch | integer | no | Maximum number of URLs fetched per internet search (1-1000) |
| minDeepSearchPagesPercentage | string | no | Minimum percentage of pages for deep search (0.01-1.0) |
| allowAskQuestion | boolean | no | Whether users can ask clarifying questions |
| autoVoiceMode | boolean | no | Whether voice mode is automatically activated (voice mode) |
| voiceSensitivity | string | no | Voice activity detection sensitivity (voice mode, 0.1-1.0) |
| vadThresholds | string | no | Voice activity detection thresholds (voice mode) |
| voiceBackgroundNoise | boolean | no | Whether background noise filtering is enabled (voice mode) |
| department | string | no | Department the agent belongs to |
| metadata | string | no | Arbitrary metadata key-value pairs (JSON) |
| agentHiringTemplate | string | no | Template used for hiring/onboarding new agents |
| agentLongTermMemory | boolean | no | Whether long-term agent memory is enabled |
| isGlobal | boolean | no | Whether this function is available across all agents |
| ephemeralAgent | boolean | no | Whether this is an ephemeral (temporary) agent |
| parentAgentID | string | no | ID of the parent agent (for spawned sub-agents) |
| parentChatID | string | no | ID of the parent chat (for spawned conversations) |
| minimumSubscriptionType | string | no | Minimum subscription tier required to use this agent |
| clonedAgentID | string | no | ID of the agent this was cloned from |
| clonedAgentIDIcon | string | no | Icon of the agent this was cloned from |
| agentType | string | no | Agent type: Chatbot, BusinessAnalyst, or ContentCreator
Allowed: Chatbot, BusinessAnalyst, ContentCreator |
| createdBy | string | no | ID of the user who created this resource |
| updatedBy | string | no | ID of the user who last updated this resource |
| forceJsonOutput | boolean | no | Whether JSON output is forced regardless of request |
| reRank | boolean | no | Whether retrieval results are re-ranked for relevance (retriever mode) |
| blender | boolean | no | Whether multiple information sources are blended (retriever mode) |
| ragSearchStrategy | string | no | Strategy used for RAG search |
| ragInstructions | string | no | Custom instructions for the retrieval-augmented generation process |
| minChunksBeforeCompleteness | string | no | Minimum fraction of retrieved chunks required before considering a response complete (0.25-1.0) |
| ragCompletenessThreshold | string | no | Threshold for considering retrieval context sufficient to answer (0.25-1.0) |
| maxPlanningSteps | integer | no | Maximum number of planning steps (planner/computer mode, 1-10) |
| maxBrowserSteps | integer | no | Maximum number of browser automation steps (computer mode, 1-50) |
| plannerExecutionAttempts | integer | no | Number of plan execution attempts (1-5) |
| planningInstructions | string | no | Custom instructions for the planning process |
| reviewInstructions | string | no | Custom instructions for plan review |
| allowReplanning | boolean | no | Whether re-planning is allowed when a plan fails |
| agentDesktopVM | string | no | Virtual machine identifier for desktop automation (computer mode) |
| agentDesktopPortRange | integer | no | Port range for desktop VM access (computer mode) |
| agentDesktopCredentials | string | no | Credentials for desktop VM access (computer mode, max 10) |
| agentDesktopBrowser | boolean | no | Whether browser automation is enabled on the desktop VM (computer mode) |
| maxTotalToolCalls | integer | no | Maximum total tool calls per execution (1-100) |
| maxConsecutiveSameTool | integer | no | Maximum consecutive calls to the same tool (1-50) |
| maxConsecutiveFailures | integer | no | Maximum consecutive tool failures before stopping (1-20) |
| allowExternalAPI | boolean | no | Whether the hook can make external API calls |
| allowImagesGeneration | boolean | no | Whether image generation is allowed (chatter mode) |
| allowVideosGeneration | boolean | no | Whether video generation is allowed (chatter mode) |
| allowAudiosGeneration | boolean | no | Whether audio generation is allowed (chatter mode) |
| allow3dModelGeneration | boolean | no | Whether 3D model generation is allowed (chatter mode) |
| advancedImageGeneration | boolean | no | Whether advanced image generation is enabled (chatter mode) |
| maxImagesGenerated | integer | no | Maximum number of images generated per request (1-10) |
| baseImageGenerationModel | string | no | Base model used for image generation |
| videoGenerationModel | string | no | Model used for video generation |
| hasEntityExtraction | boolean | no | Whether entity extraction is enabled (chatter mode) |
| chainOfThoughts | boolean | no | Whether chain-of-thoughts reasoning is displayed (chatter mode) |
| agentsPool | string | no | List of agent IDs available for orchestration (planner mode, max 10) |
| plannerRequiresApprovalForPlanExecution | boolean | no | Whether plan execution requires user approval (planner mode) |
| plannerEmailOnApprovalRequest | boolean | no | Whether email is sent when approval is requested |
| plannerEmailOnFailedPlan | boolean | no | Whether email is sent when a plan fails |
| plannerEmailOnCompletedPlan | boolean | no | Whether email is sent when a plan completes |
| plannerAutoAgentSpawn | boolean | no | Whether the planner can automatically spawn sub-agents |
| plannerDeepThinking | boolean | no | Whether deep thinking mode is enabled for the planner |
| plannerRetainsSpawnedAgents | boolean | no | Whether spawned agents are retained after plan completion |
| plannerPromptsAgentsProgrammatically | boolean | no | Whether the planner prompts agents via API |
| plannerProceedsWhenImprovementsRequired | boolean | no | Whether the planner proceeds even when improvements are suggested |
| plannerApproverEmails | string | no | List of email addresses that can approve plans |
| adverserialProvider | string | no | Provider for the adversarial review model |
| adverserialModel | string | no | Model used for adversarial review of plans |
| virtualDesktopInstructions | string | no | Custom instructions for virtual desktop interaction (computer mode) |
| voiceName | string | no | Voice name used for text-to-speech (voice mode) |
| sttModel | string | no | Speech-to-text model (voice mode) |
| llmVoiceModel | string | no | LLM model used for voice interactions (voice mode) |
| ttsModel | string | no | Text-to-speech model (voice mode) |
| defaultVoiceLanguage | string | no | Default language for voice interactions (voice mode) |
| voiceInstructions | string | no | Custom instructions for voice interactions (voice mode) |
| voiceFileKey | string | no | S3 key for the voice audio file (voice mode) |
| voiceMinSilenceDuration | string | no | Minimum silence duration to detect end of speech (voice mode, 0.1-5.0s) |
| voiceMinEndpointingDelay | string | no | Minimum endpointing delay for speech detection (voice mode, 0.1-5.0s) |
| voiceMinInterruptionDuration | string | no | Minimum interruption duration to pause speech (voice mode, 0.1-5.0s) |
| enableVoiceIntermissions | boolean | no | Whether voice intermissions are enabled (voice mode) |
| sipPhoneNumber | string | no | SIP phone number for voice calls (voice mode, max 20 chars) |
| sipDispatchRuleId | string | no | SIP dispatch rule identifier (voice mode) |
| enableInboundSip | boolean | no | Whether inbound SIP calls are enabled (voice mode) |
| enableOutboundSip | boolean | no | Whether outbound SIP calls are enabled (voice mode) |
| reasoningBudget | integer | no | Token budget allocated for reasoning (1-36000) |
| reasoningMode | string | no | Reasoning mode: auto, dynamic, always, or never |
| reasoningEffort | string | no | Level of reasoning effort: none, low, medium, or high
Allowed: none, low, medium, high |
| contextRelevancyRatio | string | no | Ratio for context relevancy scoring (0.01-1.0) |
| useInterleavedReasoning | boolean | no | Whether interleaved reasoning is used |
| interleavedPreset | string | no | Preset configuration for interleaved reasoning |
| dynamicModelSelectionInstructions | string | no | Custom instructions for dynamic model selection |
| allowVideosUpload | boolean | no | Whether users can upload videos |
Response fields
| Field | Type | Description |
|---|---|---|
id | string | Unique identifier for the agent |
type | string | Type classification of the agent (free-form string) |
label | string | Human-readable name of the agent |
description | string | Detailed description of the agent's purpose and capabilities |
interpolationString | string | System prompt template for the agent |
emoji | string | Emoji character representing the agent |
color | string | Hex color code for agent display (light theme) |
darkColor | string | Hex color code for agent display (dark theme) |
icon | string | Icon identifier for the agent |
largeLogo | string | URL to large logo image |
icoUrl | string | URL to favicon/ico file |
logoBackground | string | Background color for logo area (light theme) |
darkLogoBackground | string | Background color for logo area (dark theme) |
messageOnLaunch | string | Welcome message displayed on chat start |
messagesOnLaunch | array<string> | List of welcome messages to rotate through |
rotateMessagesOnLaunch | boolean | Whether to rotate welcome messages |
rotateMessagesOnLaunchInterval | integer | Interval in seconds between message rotations |
placeholderMessageOnLoading | string | Placeholder text shown while loading |
dynamicPlaceholderMessageOnLoading | boolean | Whether to dynamically generate loading messages |
customGreetingInstructions | string | Custom instructions for greeting generation |
customConclusionInstructions | string | Custom instructions for conclusion generation |
customChartingInstructions | string | Custom instructions for chart generation |
customSummarisationInstructions | string | Custom instructions for summarization |
customImagesInstructions | string | Custom instructions for image processing |
customToolingInstructions | string | Custom instructions for tool/function usage |
placeholderInputMessage | string | Placeholder text in input field |
openByDefault | boolean | Whether agent is open by default in UI |
agenticCodingModel | string | Model used for agentic coding tasks |
disclaimer | string | Disclaimer text displayed to users |
showDocumentsReferences | boolean | Whether to show document references in responses |
isDefault | boolean | Whether this agent is the default for the workspace |
hasMemory | boolean | Whether the agent maintains conversation memory |
hasImages | boolean | Whether the agent can process images |
promptTopKeywords | integer | Number of top keywords to extract from prompts |
keyWordsForKnowledgeBase | boolean | Whether to use keywords for knowledge base queries |
hasTopicsContext | boolean | Whether the agent considers topic context |
hasFunctions | boolean | Whether the agent can execute functions |
advancedLanguageDetection | boolean | Whether to use advanced language detection |
allowedTopics | object | List of topic IDs the agent is restricted to |
staticDocs | object | List of document IDs always included in context |
defaultAnswer | string | Default response when agent cannot provide an answer |
noKnowledgeDefaultAnswer | string | Response when no relevant knowledge is found |
quickQuestions | string | Semicolon-separated quick question suggestions |
recencyImportance | number | Importance weight for recency in retrieval |
maxRecencyIncrease | number | Maximum recency boost factor |
recencyTopKIncreaseFactor | integer | Factor to increase topK based on recency |
stopSequence | string | Sequence that stops text generation |
examples | array<object> | Example conversations for agent training |
enhancementPassage | string | Text to enhance agent responses |
inhibitionPassage | string | Text to prevent certain agent behaviors |
pertinencePassage | string | Text to improve response relevance |
goals | string | Primary objectives of the agent |
qaUrl | string | URL for quality assurance endpoint |
topK | integer | Number of top results to consider for retrieval |
mode | string | Operating mode of the agent |
Allowed: speed, accuracy, custom, retriever, coder, mathematician, chatter, planner, computer, voice |
| showCodeInExecution | boolean | Whether to show code during execution |
| hideReasoning | boolean | Whether to hide reasoning process from users |
| charting | boolean | Whether the agent can create charts |
| summarisation | boolean | Whether the agent can summarize content |
| compressor | boolean | Whether to use content compression |
| docTopK | integer | Number of top documents to retrieve |
| minRetrievalScore | number | Minimum score threshold for retrieval results |
| timeSignificance | number | Time significance factor for retrieval |
| hasModeration | boolean | Whether content moderation is enabled |
| customModerations | object | Custom moderation rules (JSON object) |
| moderationMessage | string | Message shown when content is moderated |
| languageDetectionConfidence | number | Confidence threshold for language detection |
| maxHistory | integer | Maximum conversation history to maintain |
| maxTokens | integer | Maximum tokens in agent response |
| topicEnhancer | boolean | Whether to enhance responses with topic information |
| maxTopics | integer | Maximum number of topics to consider |
| blender | boolean | Whether to blend multiple information sources |
| temperature | number | Randomness level in responses (0.001-1.0) |
| seed | integer | Random seed for reproducible generation |
| version | integer | Agent configuration version |
| subject | string | Subject matter expertise area |
| workspaceID | string | Unique workspace identifier (UUID v4) |
| createdBy | string | User ID who created the agent |
| updatedBy | string | User ID who last updated the agent |
| agentFunctions | array<string> | List of function IDs associated with the agent |
| isGlobal | boolean | Whether the agent is available globally |
| promptBuffering | boolean | Whether to use prompt buffering |
| functionContext | object | Context data for function execution (JSON object) |
| plainTextOutput | boolean | Whether to output plain text only |
| chainOfThoughts | boolean | Whether to show reasoning process |
| treeOfThoughts | boolean | Whether to use tree-of-thoughts reasoning |
| extendedOutput | boolean | Whether to include extended output metadata |
| agentType | string | Agent type classification
Allowed: Chatbot, BusinessAnalyst, ContentCreator, Default |
| agentsPool | array<string> | List of agent IDs for orchestration (planner mode) |
| mcps | array<string> | List of MCP server IDs associated with the agent |
| maxPlanningSteps | integer | Maximum planning steps (planner/computer mode) |
| maxBrowserSteps | integer | Maximum browser automation steps (computer mode) |
| virtualDesktopInstructions | string | Instructions for virtual desktop operations |
| planningInstructions | string | Instructions for planning process |
| plannerExecutionAttempts | integer | Number of execution attempts for planner |
| plannerRequiresApprovalForPlanExecution | boolean | Whether approval is required before plan execution |
| plannerEmailOnApprovalRequest | boolean | Send email when approval is requested |
| plannerEmailOnFailedPlan | boolean | Send email when plan fails |
| plannerEmailOnCompletedPlan | boolean | Send email when plan completes |
| plannerAutoAgentSpawn | boolean | Whether to automatically spawn agents |
| plannerRetainsSpawnedAgents | boolean | Whether to retain spawned agents after completion |
| plannerPromptsAgentsProgrammatically | boolean | Whether to programmatically prompt spawned agents |
| plannerDeepThinking | boolean | Enable deep thinking mode for planner |
| allowReplanning | boolean | Whether to allow replanning during execution |
| plannerProceedsWhenImprovementsRequired | boolean | Continue when improvements are suggested |
| plannerApproverEmails | array<string> | List of email addresses for plan approvals |
| reviewInstructions | string | Instructions for reviewing agent outputs |
| showReferencesToInternalDocs | boolean | Whether to show references to internal documents |
| showCitations | boolean | Whether to show source citations |
| forceJsonOutput | boolean | Whether to force JSON output format |
| agenticRAG | boolean | Whether agentic RAG is enabled |
| preventWidgetUsage | boolean | Whether to prevent widget usage |
| allowFeedback | boolean | Whether to allow user feedback |
| generateExtendedReport | boolean | Whether to generate extended reports |
| showTimeForResponse | boolean | Whether to show response time |
| showDetectedLanguage | boolean | Whether to show detected language |
| showRoutedModel | boolean | Whether to show which model was routed to |
| isMultiLanguageEnabled | boolean | Whether multi-language support is enabled |
| hasMath | boolean | Whether math capabilities are enabled |
| hasCode | boolean | Whether code execution is enabled |
| hasComputer | boolean | Whether computer/browser automation is enabled |
| hasNER | boolean | Whether named entity recognition is enabled |
| restrictedAccess | boolean | Whether access is restricted to specific users |
| restrictedAccessUsers | array<string> | List of user IDs with access |
| splashTitle | string | Title displayed on splash screen |
| showSplashWhenEmpty | boolean | Whether to show splash screen when chat is empty |
| llmEndpoint | string | Custom LLM endpoint URL |
| llmUrl | string | Custom LLM URL |
| llmUrlStatus | string | Status of the LLM URL
Allowed: ready, notReady, dismissed, unknown, swapping |
| llmUrlType | string | Type of LLM deployment
Allowed: serverless, provisioned, elastic |
| llmBaseModel | string | Base model identifier for LLM |
| llmProvider | string | LLM provider (e.g., 'openai', 'anthropic') |
| llmTopK | number | Top-K sampling parameter for LLM |
| llmSeed | number | Seed for reproducible LLM outputs |
| forcedTheme | string | Force a specific theme for this agent |
| adverserialProvider | string | Provider for adversarial content detection |
| adverserialModel | string | Model for adversarial content detection |
| functionCallingProvider | string | Provider for function calling capability |
| functionCallingModel | string | Model for function calling |
| visionProvider | string | Provider for vision/image processing |
| visionModel | string | Model for vision/image processing |
| videoGenerationProvider | string | Provider for video generation |
| videoGenerationModel | string | Model for video generation |
| showAgentName | boolean | Whether to show agent name in responses |
| allowImagesUpload | boolean | Whether image uploads are allowed |
| allowVideosUpload | boolean | Whether video uploads are allowed |
| allowAudiosUpload | boolean | Whether audio uploads are allowed |
| allowDocsUpload | boolean | Whether document uploads are allowed |
| allowImagesGeneration | boolean | Whether image generation is allowed |
| baseImageGenerationModel | string | Base model for image generation |
| maxImagesGenerated | integer | Maximum number of images to generate per request |
| advancedImageGeneration | boolean | Whether advanced image generation features are enabled |
| allowVideosGeneration | boolean | Whether video generation is allowed |
| allowAudiosGeneration | boolean | Whether audio generation is allowed |
| allowIntrospection | boolean | Whether agent introspection is enabled |
| voiceFileKey | string | S3 key for custom voice reference file |
| allowInternetSearch | boolean | Whether internet search is allowed |
| bannedDomains | array<string> | List of banned domains for internet search |
| maxUrlsForInternetSearch | integer | Maximum URLs to crawl per search |
| allowDeepInternetSearch | boolean | Whether deep internet search is allowed |
| internetSearchModes | array<string> | Allowed internet search modes |
| internetSearchLocation | string | Location for internet search results |
| autoVoiceMode | boolean | Whether to automatically enable voice mode |
| voiceSensitivity | string | Voice sensitivity level |
| keywordsWeightInRetrieval | number | Weight for keywords in retrieval scoring |
| customCodeExecutionEnvironments | array<string> | List of custom code execution environment IDs |
| phoneNumberAsSender | string | Phone number used as sender for SMS |
| whatsappNumberAsSender | string | WhatsApp number used as sender |
| emailAsSender | string | Email address used as sender |
| communicationServices | array<string> | List of communication service IDs |
| channelCallbackDelay | integer | Delay in seconds for channel callbacks |
| ephemeralAgent | boolean | Whether this is an ephemeral/temporary agent |
| parentAgentID | string | ID of parent agent (for spawned agents) |
| parentChatID | string | ID of parent chat (for spawned agents) |
| minimumSubscriptionType | string | Minimum subscription required to use this agent
Allowed: base, pro, business, enterprise |
| clonedAgentID | string | ID of agent this was cloned from |
| clonedAgentIDIcon | string | Icon of the original cloned agent |
| hasContentCreation | boolean | Whether content creation features are enabled |
| hasEntityExtraction | boolean | Whether entity extraction is enabled |
| department | string | Department this agent belongs to
Allowed: HUMAN_RESOURCES, FINANCE_AND_ACCOUNTING, SALES, MARKETING, OPERATIONS, INFORMATION_TECHNOLOGY, CUSTOMER_SERVICE, RESEARCH_AND_DEVELOPMENT, LEGAL_AND_COMPLIANCE, SUPPLY_CHAIN_MANAGEMENT, PROJECT_MANAGEMENT, GENERAL_PURPOSE |
| metadata | object | Additional metadata (JSON object) |
| allowEmailToAgent | boolean | Whether email-to-agent is enabled |
| allowedEmails | string | Comma-separated list of allowed email addresses |
| agentHiringTemplate | object | Template for hiring this agent (JSON object) |
| agentDesktopVM | string | Virtual machine ID for agent desktop |
| agentDesktopPortRange | string | Port range for agent desktop |
| agentDesktopCredentials | object | Credentials for agent desktop (JSON object) |
| agentDesktopBrowser | boolean | Whether to use browser in agent desktop |
| allow3dModelGeneration | boolean | Whether 3D model generation is allowed |
| agentLongTermMemory | string | Configuration for long-term memory |
| isLongTermMemoryEnabled | boolean | Whether long-term memory is enabled |
| allowExternalAPI | boolean | Whether external API calls are allowed |
| forceNewThreadOnProgrammaticRequest | boolean | Force new thread on programmatic requests |
| dynamicModelSelectionInstructions | string | Instructions for dynamic model selection |
| contextRelevancyRatio | number | Ratio for context relevancy scoring |
| reasoningBudget | integer | Token budget for reasoning |
| reasoningMode | string | Reasoning mode: auto, dynamic, always, or never
Allowed: auto, dynamic, always, never |
| reasoningEffort | string | Level of reasoning effort
Allowed: none, low, medium, high |
| fnReasoningEffort | string | Reasoning effort for function calls
Allowed: none, low, medium, high |
| agentFnParams | object | Function parameters configuration (JSON object) |
| canvasEnabled | boolean | Whether canvas/whiteboard is enabled |
| advancedCompute | boolean | Whether advanced compute features are enabled |
| reRank | boolean | Whether to re-rank retrieval results |
| minDeepSearchPagesPercentage | number | Minimum percentage of pages for deep search |
| voiceName | string | Voice name for TTS |
| vadThresholds | number | Voice Activity Detection threshold |
| analyticsInstructions | string | Instructions for analytics/reporting |
| ragInstructions | string | Instructions for RAG operations |
| allowAskQuestion | boolean | Whether agent can ask clarifying questions |
| ragSearchStrategy | string | Search strategy for RAG
Allowed: parallel, targeted_first, vector_first |
| minChunksBeforeCompleteness | number | Minimum chunks before checking completeness |
| ragCompletenessThreshold | number | Threshold for RAG completeness |
| voiceInstructions | string | Instructions for voice interactions |
| sttModel | string | Speech-to-text model identifier |
| llmVoiceModel | string | LLM model for voice interactions |
| ttsModel | string | Text-to-speech model identifier |
| defaultVoiceLanguage | string | Default language for voice interactions |
| voiceMinSilenceDuration | number | Seconds of silence before considering turn complete |
| voiceMinEndpointingDelay | number | Extra delay before committing turn |
| voiceMinInterruptionDuration | number | How long user must speak to interrupt |
| enableVoiceIntermissions | boolean | Whether to enable voice intermissions |
| voiceBackgroundNoise | string | Background noise setting for voice |
| sipPhoneNumber | string | SIP phone number for voice calls |
| sipDispatchRuleId | string | SIP dispatch rule ID |
| enableInboundSip | boolean | Whether inbound SIP calls are enabled |
| enableOutboundSip | boolean | Whether outbound SIP calls are enabled |
| enableJsonOutput | boolean | Whether to enable structured JSON output mode |
| jsonOutputStructure | object | JSON schema defining the structure for JSON output mode |
| predictedPlanJson | object | Predicted plan structure (JSON object) |
| useInterleavedReasoning | boolean | Whether to use interleaved reasoning mode for the agent |
| interleavedPreset | string | The preset configuration for interleaved reasoning |
| maxTotalToolCalls | integer | Maximum total number of tool calls allowed per conversation turn |
| maxConsecutiveSameTool | integer | Maximum consecutive calls to the same tool before stopping |
| maxConsecutiveFailures | integer | Maximum consecutive tool call failures before stopping |
| regionalEndpoint | boolean | Regional endpoint override for the LLM |
| agentVersion | string | Version identifier for the agent configuration |
| agentCategoryType | string | Category classification for the agent |
| createdAt | string | Timestamp when this resource was created |
| updatedAt | string | Timestamp when this resource was last updated |
Example
const result = await client.agents.create(…);
get
Get an agent by ID
async get(agentId: string)
Endpoint: GET /agent/get/{id} · API service
Response
Returns the Agent object — fields documented in the create section above.
Example
const result = await client.agents.get('agent-id');
update
Update an existing agent
async update(agentId: string, data: AgentUpdateData)
Endpoint: POST /agent/update · API service
Request fields
| Field | Type | Required | Description |
|---|---|---|---|
id | string | yes | Unique identifier |
workspaceid | string | no | Unique workspace identifier (UUID v4) |
label | string | no | Human-readable display name |
description | string | no | Detailed description of purpose and capabilities |
interpolationString | string | no | The prompt text/template (with interpolation variables) |
customToolingInstructions | string | no | Custom instructions for tool/function usage |
goals | string | no | Primary objectives the agent should achieve |
pertinencePassage | string | no | Text passage used to improve response relevance |
inhibitionPassage | string | no | Text passage defining prohibited behaviors or content |
defaultAnswer | string | no | Default response when the agent cannot answer |
noKnowledgeDefaultAnswer | string | no | Response shown when no relevant knowledge is found |
subject | string | no | Subject matter expertise area |
qaUrl | string | no | URL for Q&A/knowledge source |
mode | string | no | Operating mode of the agent: retriever (knowledge retrieval), coder (code execution), chatter (conversational), planner (multi-agent orchestration), computer (browser/desktop automation), or voice (voice interaction) |
Allowed: retriever, coder, chatter, planner, computer, voice |
| temperature | string | no | Randomness level in responses (0.001-1.0); higher values produce more varied output |
| maxTokens | integer | no | Maximum number of tokens in the agent's response |
| maxHistory | integer | no | Maximum number of conversation turns retained in context |
| maxTopics | integer | no | Maximum number of topics considered (1-5) |
| topK | integer | no | Number of top retrieval results considered when generating a response |
| docTopK | integer | no | Number of top documents retrieved for context |
| minRetrievalScore | string | no | Minimum score threshold for retrieval results (0.01-0.99) |
| keywordsWeightInRetrieval | integer | no | Weight of keywords in retrieval scoring (0-5) |
| recencyImportance | integer | no | Weight of recency in retrieval scoring (0-5) |
| maxRecencyIncrease | string | no | Maximum recency score increase (0.0-1.0) |
| recencyTopKIncreaseFactor | integer | no | Factor by which recency increases top-K (0-5) |
| allowedTopics | string | no | List of topic IDs the agent is restricted to (max 10) |
| staticDocs | string | no | JSON-encoded static documents available to the hook |
| functionContext | string | no | List of function IDs providing additional context |
| hasTopicsContext | boolean | no | Whether topic context is considered when generating responses |
| topicEnhancer | boolean | no | Whether responses are enhanced with topic information |
| keyWordsForKnowledgeBase | boolean | no | Whether keyword-based knowledge base queries are used |
| summarisation | boolean | no | Whether the agent summarizes long content |
| compressor | boolean | no | Whether context compression is enabled to reduce token usage |
| hasMemory | boolean | no | Whether the agent maintains conversation memory across turns |
| isLongTermMemoryEnabled | boolean | no | Whether long-term memory persistence is enabled |
| hasFunctions | boolean | no | Whether the agent can execute external functions/tools |
| agentFunctions | string | no | List of function IDs associated with the agent |
| agentFnParams | string | no | JSON-encoded parameters for agent functions |
| llmProvider | string | no | LLM provider (e.g. openai, anthropic, tf) |
| llmBaseModel | string | no | Base LLM model identifier (e.g. sorcerer, mystica, gpt-4) |
| functionCallingProvider | string | no | Provider used for function/tool calling |
| functionCallingModel | string | no | Model used for function/tool calling |
| llmSeed | integer | no | Random seed for LLM generation reproducibility |
| hasModeration | boolean | no | Whether content moderation is enabled |
| moderationMessage | string | no | Message shown when content is moderated/rejected |
| customModerations | string | no | Custom moderation rules (JSON) |
| hasNER | boolean | no | Whether named entity recognition is enabled |
| showAgentName | boolean | no | Whether the agent name is shown in responses |
| hideReasoning | boolean | no | Whether the reasoning process is hidden from users |
| plainTextOutput | boolean | no | Whether output is plain text only (no formatting) |
| enableJsonOutput | boolean | no | Whether structured JSON output mode is enabled |
| jsonOutputStructure | string | no | JSON schema defining the structure for JSON output mode |
| predictedPlanJson | string | no | JSON representation of the predicted execution plan |
| extendedOutput | boolean | no | Whether extended output metadata is included |
| tabulate | boolean | no | Whether tabular output formatting is used |
| showReferencesToInternalDocs | boolean | no | Whether references to internal documents are shown |
| showCitations | boolean | no | Whether source citations are shown in responses |
| showTimeForResponse | boolean | no | Whether response time is displayed |
| showDetectedLanguage | boolean | no | Whether the detected language is shown |
| showRoutedModel | boolean | no | Which model was routed to for the response is shown |
| dynamicPlaceholderMessageOnLoading | boolean | no | Whether the loading placeholder message is dynamic |
| generateExtendedReport | boolean | no | Whether an extended report is generated |
| icon | string | no | Icon identifier for the agent |
| largeLogo | string | no | URL or key for the agent's large logo |
| icoUrl | string | no | URL for the agent's favicon (.ico or .png) |
| color | string | no | Hex color code for agent display (light theme) |
| darkColor | string | no | Hex color code for agent display (dark theme) |
| logoBackground | string | no | Hex color code for logo background (light theme) |
| darkLogoBackground | string | no | Hex color code for logo background (dark theme) |
| forcedTheme | string | no | Forced UI theme for this agent |
| placeholderInputMessage | string | no | Placeholder text shown in the input field |
| placeholderMessageOnLoading | string | no | Placeholder message shown while loading |
| messageOnLaunch | string | no | Welcome message shown when the chat starts |
| disclaimer | string | no | Disclaimer text displayed to users |
| quickQuestions | string | no | Semicolon-separated suggested quick questions (max 3) |
| splashTitle | string | no | Title shown on the splash screen |
| showSplashWhenEmpty | boolean | no | Whether the splash screen is shown when the chat is empty |
| preventWidgetUsage | boolean | no | Whether widget usage is prevented |
| allowFeedback | boolean | no | Whether users can provide feedback on responses |
| promptBuffering | boolean | no | Prompt buffering |
| restrictedAccess | boolean | no | Whether access to this agent is restricted |
| restrictedAccessUsers | string | no | List of user IDs with access to this restricted agent |
| enhancedApproverUsers | string | no | List of users who can approve enhanced actions |
| isMultiLanguageEnabled | boolean | no | Whether multi-language support is enabled |
| advancedLanguageDetection | boolean | no | Whether advanced language detection is used |
| languageDetectionConfidence | string | no | Confidence threshold for language detection (0.5-1.0) |
| allowEmailToAgent | boolean | no | Whether the agent can be reached via email |
| forceNewThreadOnProgrammaticRequest | boolean | no | Whether programmatic requests force a new conversation thread |
| allowedEmails | string | no | Comma-separated list of allowed email addresses |
| phoneNumberAsSender | string | no | Phone number used as sender identity |
| whatsappNumberAsSender | string | no | WhatsApp number used as sender identity |
| emailAsSender | string | no | Email address used as sender identity |
| communicationServices | string | no | List of communication service IDs enabled for the agent |
| channelCallbackDelay | integer | no | Delay (seconds) before channel callback (0-120) |
| analyticsInstructions | string | no | Custom instructions for analytics processing |
| charting | boolean | no | Whether the agent can generate charts (TF models only) |
| allowImagesUpload | boolean | no | Whether users can upload images |
| allowAudiosUpload | boolean | no | Whether users can upload audio files |
| allowDocsUpload | boolean | no | Whether users can upload documents |
| hasImages | boolean | no | Whether the agent can process images |
| allowIntrospection | boolean | no | Whether the agent can introspect its own capabilities |
| promptTopKeywords | integer | no | Number of top keywords extracted from prompts for retrieval (1-10) |
| agenticRAG | boolean | no | Whether agentic retrieval-augmented generation is enabled (retriever mode) |
| type | string | no | Type classification (free-form string identifier) |
| version | string | no | Version identifier for the agent configuration |
| emoji | string | no | Emoji icon for the folder |
| messagesOnLaunch | string | no | List of quick-start messages shown on launch |
| rotateMessagesOnLaunch | boolean | no | Whether launch messages are rotated |
| rotateMessagesOnLaunchInterval | integer | no | Interval for rotating launch messages |
| customGreetingInstructions | string | no | Custom instructions for the greeting message |
| customConclusionInstructions | string | no | Custom instructions for the conclusion message |
| customChartingInstructions | string | no | Custom instructions for chart generation |
| customSummarisationInstructions | string | no | Custom instructions for content summarization |
| customImagesInstructions | string | no | Custom instructions for image handling |
| openByDefault | boolean | no | Whether the agent is open by default in the UI |
| isDefault | boolean | no | Whether this is the default agent for the workspace |
| showDocumentsReferences | boolean | no | Whether document references are displayed |
| stopSequence | string | no | Sequence that stops response generation |
| enhancementPassage | string | no | Text passage used to enhance response quality |
| timeSignificance | boolean | no | Whether time significance is considered in responses |
| seed | integer | no | Random seed for reproducible generation |
| fnReasoningEffort | string | no | Reasoning effort level for function-calling |
| canvasEnabled | boolean | no | Whether canvas (visual workspace) is enabled |
| advancedCompute | boolean | no | Whether advanced compute capabilities are enabled |
| regionalEndpoint | string | no | Regional endpoint override for the LLM |
| agentCategoryType | string | no | Category classification for the agent |
| agentVersion | string | no | Version identifier for the agent configuration |
| llmEndpoint | string | no | Custom LLM endpoint URL |
| llmUrl | string | no | Custom LLM URL |
| llmUrlType | string | no | Type of custom LLM URL |
| llmUrlStatus | string | no | Status of the custom LLM URL connection |
| llmTopK | integer | no | Top-K parameter for the LLM |
| visionProvider | string | no | Provider for vision/image understanding |
| videoGenerationProvider | string | no | Provider for video generation |
| treeOfThoughts | boolean | no | Whether tree-of-thoughts reasoning is used |
| hasMath | boolean | no | Whether mathematical computation capabilities are enabled |
| hasComputer | boolean | no | Whether computer/browser automation is enabled (computer mode) |
| mcps | string | no | List of MCP (Model Context Protocol) server IDs associated with the agent |
| hasContentCreation | boolean | no | Whether content creation capabilities are enabled |
| customCodeExecutionEnvironments | string | no | List of custom code execution environment IDs |
| hasCode | boolean | no | Whether code execution capabilities are enabled |
| showCodeInExecution | boolean | no | Whether code is displayed during execution |
| agenticCodingModel | string | no | Model used for agentic code generation |
| visionModel | string | no | Model used for vision/image understanding |
| allowInternetSearch | boolean | no | Whether internet search is allowed |
| allowDeepInternetSearch | boolean | no | Whether deep internet search is allowed |
| internetSearchModes | string | no | List of internet search modes enabled |
| internetSearchLocation | string | no | Geographic location preference for internet search |
| bannedDomains | string | no | List of domains excluded from internet search |
| maxUrlsForInternetSearch | integer | no | Maximum number of URLs fetched per internet search (1-1000) |
| minDeepSearchPagesPercentage | string | no | Minimum percentage of pages for deep search (0.01-1.0) |
| allowAskQuestion | boolean | no | Whether users can ask clarifying questions |
| autoVoiceMode | boolean | no | Whether voice mode is automatically activated (voice mode) |
| voiceSensitivity | string | no | Voice activity detection sensitivity (voice mode, 0.1-1.0) |
| vadThresholds | string | no | Voice activity detection thresholds (voice mode) |
| voiceBackgroundNoise | boolean | no | Whether background noise filtering is enabled (voice mode) |
| department | string | no | Department the agent belongs to |
| metadata | string | no | Arbitrary metadata key-value pairs (JSON) |
| agentHiringTemplate | string | no | Template used for hiring/onboarding new agents |
| agentLongTermMemory | boolean | no | Whether long-term agent memory is enabled |
| isGlobal | boolean | no | Whether this function is available across all agents |
| ephemeralAgent | boolean | no | Whether this is an ephemeral (temporary) agent |
| parentAgentID | string | no | ID of the parent agent (for spawned sub-agents) |
| parentChatID | string | no | ID of the parent chat (for spawned conversations) |
| minimumSubscriptionType | string | no | Minimum subscription tier required to use this agent |
| clonedAgentID | string | no | ID of the agent this was cloned from |
| clonedAgentIDIcon | string | no | Icon of the agent this was cloned from |
| agentType | string | no | Agent type: Chatbot, BusinessAnalyst, or ContentCreator
Allowed: Chatbot, BusinessAnalyst, ContentCreator |
| createdBy | string | no | ID of the user who created this resource |
| updatedBy | string | no | ID of the user who last updated this resource |
| forceJsonOutput | boolean | no | Whether JSON output is forced regardless of request |
| reRank | boolean | no | Whether retrieval results are re-ranked for relevance (retriever mode) |
| blender | boolean | no | Whether multiple information sources are blended (retriever mode) |
| ragSearchStrategy | string | no | Strategy used for RAG search |
| ragInstructions | string | no | Custom instructions for the retrieval-augmented generation process |
| minChunksBeforeCompleteness | string | no | Minimum fraction of retrieved chunks required before considering a response complete (0.25-1.0) |
| ragCompletenessThreshold | string | no | Threshold for considering retrieval context sufficient to answer (0.25-1.0) |
| maxPlanningSteps | integer | no | Maximum number of planning steps (planner/computer mode, 1-10) |
| maxBrowserSteps | integer | no | Maximum number of browser automation steps (computer mode, 1-50) |
| plannerExecutionAttempts | integer | no | Number of plan execution attempts (1-5) |
| planningInstructions | string | no | Custom instructions for the planning process |
| reviewInstructions | string | no | Custom instructions for plan review |
| allowReplanning | boolean | no | Whether re-planning is allowed when a plan fails |
| agentDesktopVM | string | no | Virtual machine identifier for desktop automation (computer mode) |
| agentDesktopPortRange | integer | no | Port range for desktop VM access (computer mode) |
| agentDesktopCredentials | string | no | Credentials for desktop VM access (computer mode, max 10) |
| agentDesktopBrowser | boolean | no | Whether browser automation is enabled on the desktop VM (computer mode) |
| maxTotalToolCalls | integer | no | Maximum total tool calls per execution (1-100) |
| maxConsecutiveSameTool | integer | no | Maximum consecutive calls to the same tool (1-50) |
| maxConsecutiveFailures | integer | no | Maximum consecutive tool failures before stopping (1-20) |
| allowExternalAPI | boolean | no | Whether the hook can make external API calls |
| allowImagesGeneration | boolean | no | Whether image generation is allowed (chatter mode) |
| allowVideosGeneration | boolean | no | Whether video generation is allowed (chatter mode) |
| allowAudiosGeneration | boolean | no | Whether audio generation is allowed (chatter mode) |
| allow3dModelGeneration | boolean | no | Whether 3D model generation is allowed (chatter mode) |
| advancedImageGeneration | boolean | no | Whether advanced image generation is enabled (chatter mode) |
| maxImagesGenerated | integer | no | Maximum number of images generated per request (1-10) |
| baseImageGenerationModel | string | no | Base model used for image generation |
| videoGenerationModel | string | no | Model used for video generation |
| hasEntityExtraction | boolean | no | Whether entity extraction is enabled (chatter mode) |
| chainOfThoughts | boolean | no | Whether chain-of-thoughts reasoning is displayed (chatter mode) |
| agentsPool | string | no | List of agent IDs available for orchestration (planner mode, max 10) |
| plannerRequiresApprovalForPlanExecution | boolean | no | Whether plan execution requires user approval (planner mode) |
| plannerEmailOnApprovalRequest | boolean | no | Whether email is sent when approval is requested |
| plannerEmailOnFailedPlan | boolean | no | Whether email is sent when a plan fails |
| plannerEmailOnCompletedPlan | boolean | no | Whether email is sent when a plan completes |
| plannerAutoAgentSpawn | boolean | no | Whether the planner can automatically spawn sub-agents |
| plannerDeepThinking | boolean | no | Whether deep thinking mode is enabled for the planner |
| plannerRetainsSpawnedAgents | boolean | no | Whether spawned agents are retained after plan completion |
| plannerPromptsAgentsProgrammatically | boolean | no | Whether the planner prompts agents via API |
| plannerProceedsWhenImprovementsRequired | boolean | no | Whether the planner proceeds even when improvements are suggested |
| plannerApproverEmails | string | no | List of email addresses that can approve plans |
| adverserialProvider | string | no | Provider for the adversarial review model |
| adverserialModel | string | no | Model used for adversarial review of plans |
| virtualDesktopInstructions | string | no | Custom instructions for virtual desktop interaction (computer mode) |
| voiceName | string | no | Voice name used for text-to-speech (voice mode) |
| sttModel | string | no | Speech-to-text model (voice mode) |
| llmVoiceModel | string | no | LLM model used for voice interactions (voice mode) |
| ttsModel | string | no | Text-to-speech model (voice mode) |
| defaultVoiceLanguage | string | no | Default language for voice interactions (voice mode) |
| voiceInstructions | string | no | Custom instructions for voice interactions (voice mode) |
| voiceFileKey | string | no | S3 key for the voice audio file (voice mode) |
| voiceMinSilenceDuration | string | no | Minimum silence duration to detect end of speech (voice mode, 0.1-5.0s) |
| voiceMinEndpointingDelay | string | no | Minimum endpointing delay for speech detection (voice mode, 0.1-5.0s) |
| voiceMinInterruptionDuration | string | no | Minimum interruption duration to pause speech (voice mode, 0.1-5.0s) |
| enableVoiceIntermissions | boolean | no | Whether voice intermissions are enabled (voice mode) |
| sipPhoneNumber | string | no | SIP phone number for voice calls (voice mode, max 20 chars) |
| sipDispatchRuleId | string | no | SIP dispatch rule identifier (voice mode) |
| enableInboundSip | boolean | no | Whether inbound SIP calls are enabled (voice mode) |
| enableOutboundSip | boolean | no | Whether outbound SIP calls are enabled (voice mode) |
| reasoningBudget | integer | no | Token budget allocated for reasoning (1-36000) |
| reasoningMode | string | no | Reasoning mode: auto, dynamic, always, or never |
| reasoningEffort | string | no | Level of reasoning effort: none, low, medium, or high
Allowed: none, low, medium, high |
| contextRelevancyRatio | string | no | Ratio for context relevancy scoring (0.01-1.0) |
| useInterleavedReasoning | boolean | no | Whether interleaved reasoning is used |
| interleavedPreset | string | no | Preset configuration for interleaved reasoning |
| dynamicModelSelectionInstructions | string | no | Custom instructions for dynamic model selection |
| allowVideosUpload | boolean | no | Whether users can upload videos |
Response
Returns the Agent object — fields documented in the create section above.
Example
const result = await client.agents.update('agent-id', …);
delete
Delete an agent
async delete(agentId: string): Promise<
Endpoint: DELETE /agent/delete/{id} · API service
Response fields
| Field | Type | Description |
|---|---|---|
success | boolean | Operation success status |
data | object | Response data |
message | string | Optional success message |
Example
const result = await client.agents.delete('agent-id');
list
List agents in the workspace
async list(limit?: number, offset?: number)
Endpoint: GET /agent/list · API service
Example
const result = await client.agents.list();
getByMode
Get agents by mode
async getByMode(mode: AgentMode, limit?: number)
Derived method — delegates to another SDK call and performs no direct HTTP request.
Example
const result = await client.agents.getByMode(…);
search
Search agents by label
async search(searchTerm: string)
Derived method — delegates to another SDK call and performs no direct HTTP request.
Example
const result = await client.agents.search('…');
getRetrievers
Get all retriever agents
async getRetrievers(limit?: number)
Derived method — delegates to another SDK call and performs no direct HTTP request.
Example
const result = await client.agents.getRetrievers();
getChatters
Get all chatter agents
async getChatters(limit?: number)
Derived method — delegates to another SDK call and performs no direct HTTP request.
Example
const result = await client.agents.getChatters();
getCoders
Get all coder agents
async getCoders(limit?: number)
Derived method — delegates to another SDK call and performs no direct HTTP request.
Example
const result = await client.agents.getCoders();
getPlanners
Get all planner agents
async getPlanners(limit?: number)
Derived method — delegates to another SDK call and performs no direct HTTP request.
Example
const result = await client.agents.getPlanners();
clone
Clone an existing agent with modifications
async clone(agentId: string, overrides: Partial<AgentCreateData> = {})
Derived method — delegates to another SDK call and performs no direct HTTP request.
Example
const result = await client.agents.clone('agent-id');