Agent

AI Model Configuration

Source: packages/spec/src/ai/agent.zod.ts

TypeScript Usage

import { AIKnowledge, AIModelConfig, AITool, Agent, StructuredOutputConfig, StructuredOutputFormat, TransformPipelineStep } from '@objectstack/spec/ai';
import type { AIKnowledge, AIModelConfig, AITool, Agent, StructuredOutputConfig, StructuredOutputFormat, TransformPipelineStep } from '@objectstack/spec/ai';

// Validate data
const result = AIKnowledge.parse(data);

AIKnowledge

Properties

Property	Type	Required	Description
topics	`string[]`	✅	Topics/Tags to recruit knowledge from
indexes	`string[]`	✅	Vector Store Indexes

AIModelConfig

Properties

Property	Type	Required	Description
provider	`Enum<'openai' \| 'azure_openai' \| 'anthropic' \| 'local'>`	✅
model	`string`	✅	Model name (e.g. gpt-4, claude-3-opus)
temperature	`number`	✅
maxTokens	`number`	optional
topP	`number`	optional

AITool

Properties

Property	Type	Required	Description
type	`Enum<'action' \| 'flow' \| 'query' \| 'vector_search'>`	✅
name	`string`	✅	Reference name (Action Name, Flow Name)
description	`string`	optional	Override description for the LLM

Properties

Property	Type	Required	Description
name	`string`	✅	Agent unique identifier
label	`string`	✅	Agent display name
avatar	`string`	optional
role	`string`	✅	The persona/role (e.g. "Senior Support Engineer")
instructions	`string`	✅	System Prompt / Prime Directives
model	`Object`	optional
lifecycle	`Object`	optional	State machine defining the agent conversation follow and constraints
tools	`Object[]`	optional	Available tools
knowledge	`Object`	optional	RAG access
active	`boolean`	✅
access	`string[]`	optional	Who can chat with this agent
tenantId	`string`	optional	Tenant/Organization ID
visibility	`Enum<'global' \| 'organization' \| 'private'>`	✅
planning	`Object`	optional	Autonomous reasoning and planning configuration
memory	`Object`	optional	Agent memory management
guardrails	`Object`	optional	Safety guardrails for the agent
structuredOutput	`Object`	optional	Structured output format and validation configuration

StructuredOutputConfig

Structured output configuration for agent responses

Properties

Property	Type	Required	Description
format	`Enum<'json_object' \| 'json_schema' \| 'regex' \| 'grammar' \| 'xml'>`	✅	Expected output format
schema	`Record<string, any>`	optional	JSON Schema definition for output
strict	`boolean`	✅	Enforce exact schema compliance
retryOnValidationFailure	`boolean`	✅	Retry generation when output fails validation
maxRetries	`integer`	✅	Maximum retries on validation failure
fallbackFormat	`Enum<'json_object' \| 'json_schema' \| 'regex' \| 'grammar' \| 'xml'>`	optional	Fallback format if primary format fails
transformPipeline	`Enum<'trim' \| 'parse_json' \| 'validate' \| 'coerce_types'>[]`	optional	Post-processing steps applied to output

StructuredOutputFormat

Output format for structured agent responses

Allowed Values

json_object
json_schema
regex
grammar
xml

TransformPipelineStep

Post-processing step for structured output

Allowed Values

trim
parse_json
validate
coerce_types

Agent

On this page