Version: v5.2

Agents

Overview

Use the Agents API to list, create, update, retrieve, and delete agents.

With this REST API, you can do the following:

List agents
Create agent
Get agent by ID
Update agent by ID
Delete agent by ID

List agents

Endpoints

GET aisvc/api/v1/agents

Request

Query parameters

Parameter	Type	Description	Required
`_offset`	Number	Number of results to skip	Optional
`_pageSize`	Number	Number of results per page	Optional
`_userType`	String	Filter by the agent's unique `_userType` identifier	Optional
`_type`	String	Filter by the agent type, such as `user_agent` or `system_agent`	Optional
`query`	String	Wildcard search on the name, description, and background of agents	Optional

Request example

None

Response

Codes

Code	Description
`200`	Success
`400`	Bad Request
`404`	Not Found

Response body

{
  "_offset": 0,
  "_pageSize": 1,
  "_total": 50,
  "_list": [
    {
        "_name": "Related Items and File Helper Agent",
        "_background": "It uses the RelatedQueryTool to generate related queries as JSON from the user prompt and feeds them to the SearchRelatedItemsTool to retrieve data from the Item Service. It can also look up file information using the getFiles_IafFileSvc system MCP tool and the GetFileNameById custom MCP tool.",
        "_userType": "related_items_file_helper_agent",
        "_namespaces": [
            "iputGraph_kxYOcW7O"
        ],
        "_config": {
            "_model": "gpt-4o",
            "_provider": "openai",
            "_temperature": 1.2
        },
        "_tools": [
            "RelatedQueryTool",
            "SearchRelatedItemsTool",
            "getFiles_IafFileSvc",
            "GetFileNameById"
        ],
        "_invocationMessage": "Analyzing related items and files…",
        "_id": "6fe848f8-3d9b-48ff-bcf1-643756168904",
        "_irn": "aisvc:agent:6fe848f8-3d9b-48ff-bcf1-643756168904",
        "_metadata": {
            "_createdAt": "1757048208583",
            "_updatedById": "70699091-77de-4ee3-8a3f-034ec8746a3b",
            "_createdById": "70699091-77de-4ee3-8a3f-034ec8746a3b",
            "_updatedAt": "1757048208583"
        }        
    }
  ]
}

Create agent

Endpoints

POST aisvc/api/v1/agents

Request

Request body

Parameter	Type	Description	Required
`_namespaces`	Array of String	One or more namespaces that contain the resource	Required
`_name`	String	The agent's name	Required
`_background`	String	Enter a prompt for prompt engineering.	Required
`_userType`	String	Unique identifier of the agent	Required
`_description`	String	Agent's description	Optional
`_tools`	Array of String	Tools the agent can use. Each entry is either a regular tool's `_userType` or a Twinit MCP tool's `_name` — both system MCP tools (for example, `getFiles_IafFileSvc`) and custom (user) MCP tools (for example, `GetFileNameById`). See Twinit MCP tools (`_tools`) below.	Optional
`_knowledgebases`	Array of String	The identifiers (`_userType`) of knowledge bases the agent uses	Optional
`_externalMcpServers`	Array of Object	External MCP servers the agent can use (by `_userType`)	Optional
`_promptTemplate`	String	The `_userType` of a Prompt Template to assign to this agent. The template serves as the agent's instruction and is parameterized at runtime.	Optional
`_invocationMessage`	String	A short, plain-text status message streamed to the conversation when this agent is invoked during a team run (for example, `Analyzing related items and files…`). Maximum 500 characters (leading/trailing whitespace is trimmed). Must be plain text — HTML tags and template expressions (`{{ }}`, `${ }`, `<% %>`) are not allowed. An empty or whitespace-only value is stored as `null`.	Optional
`_config`	Object	The agent's LLM model configuration. See additional `_config` properties below.	Required
`_config._model`	Object	The agent's LLM model. The set of available models is dynamic — use the LLM Models API to retrieve the supported model names for a provider.	Required
`_config._provider`	Object	The provider of the agent's LLM model. Supported providers are `openai` and `anthropic`.	Required

LLM configuration (`_config`)

Parameter	Type	Description	Required
`_config._provider`	String	The LLM provider (for example, `openai` or `anthropic`)	Required
`_config._model`	String	The LLM model name (for example, `gpt-4o`)	Required
`_config._temperature`	Number	Sampling temperature. Must be within the allowed range for the selected model.
If omitted or `null`, the service uses the model's default temperature.	Optional

The allowed temperature range is model-specific, not provider-wide. Most OpenAI chat models (for example gpt-4o, gpt-4.1, gpt-4-turbo) accept 0.0-2.0, and Anthropic models accept 0.0-1.0.

Reasoning-tier models are the exception: the OpenAI o-series (o1, o3, o3-mini, o4-mini) and the gpt-5 family (gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-chat-latest, gpt-5.1, gpt-5.1-mini, gpt-5.2, gpt-5.2-pro, gpt-5.5) support only their default temperature of 1. This mirrors OpenAI's own restriction on those models. Sending any other value — including 0.0 — returns 422:

{
    "source": "ServiceException",
    "message": "The _config._temperature is fixed at 1 for model 'gpt-5' and cannot be changed"
}

Omitting _config._temperature is always safe: the service applies the model's default, so the same agent payload can be reused across models with different temperature rules. This is the recommended approach when an agent's model may change, since the LLM Models API reports model names only and does not return temperature bounds.

Twinit MCP tools (`_tools`)

An agent can use Twinit MCP tools directly by listing the Twinit MCP tool's _name in the _tools array — there is no need to define or reference a Twinit MCP Server (_externalMcpServers) for this. Both kinds of Twinit MCP tools are supported:

Type	`_type` value	Description	Reference by
System MCP tools	`system_mcp_tool`	Built-in, read-only tools for reading platform data.	`_name`, for example `getFiles_IafFileSvc` or `getNamedUserItems_IafItemSvc`
Custom (user) MCP tools	`user_mcp_tool`	Tools you create to run your own Item Service script.	`_name` you gave them, for example `GetFileNameById`

Regular tools (by _userType) and Twinit MCP tools (by _name) can be mixed freely in the same _tools array.

Note: A Twinit MCP tool _name must not collide with an existing tool's _userType. If it does, agent creation fails with 409 Conflict asking you to rename one of them.

MCP servers (`_externalMcpServers`)

Note: This field is stored internally on the agent resource as external_mcp_servers (JSONB).

Parameter	Type	Description	Required
`_externalMcpServers[]. _userType`	String	External MCP server config `_userType` (see External MCP Server Config API).	Required
`_externalMcpServers[]. _filter`	Object	Optional filter for MCP tool visibility.	Optional
`_externalMcpServers[]. _filter._names`	Array of String	Optional list of MCP tool names to allow from this server.	Optional

Request body example

[
    {
        "_name": "Related Items and File Helper Agent",
        "_background": "It uses the RelatedQueryTool to generate related queries as JSON from the user prompt and feeds them to the SearchRelatedItemsTool to retrieve data from the Item Service. It can also look up file information using the getFiles_IafFileSvc system MCP tool and the GetFileNameById custom MCP tool.",
        "_userType": "related_items_file_helper_agent",
        "_namespaces": [
            "iputGraph_kxYOcW7O"
        ],
        "_config": {
            "_model": "gpt-4o",
            "_provider": "openai",
            "_temperature": 1.5
        },
        "_tools": [
            "RelatedQueryTool",
            "SearchRelatedItemsTool",
            "getFiles_IafFileSvc",
            "GetFileNameById"
        ],
        "_externalMcpServers": [
            {
                "_userType": "github_mcp",
                "_filter": {
                    "_names": [
                        "search_repositories",
                        "list_issues"
                    ]
                }
            }
        ],
        "_promptTemplate": "platform_resource_universal_tmpl",
        "_invocationMessage": "Analyzing related items and files…"
    }
]

Response

Codes

Code	Description
`200`	Success
`400`	Bad Request
`404`	Not Found
`422`	Unprocessable Entity

Response body

{
  "_offset": 0,
  "_pageSize": 1,
  "_total": 1,
  "_list": [
    {
        "_name": "Related Items and File Helper Agent",
        "_background": "It uses the RelatedQueryTool to generate related queries as JSON from the user prompt and feeds them to the SearchRelatedItemsTool to retrieve data from the Item Service. It can also look up file information using the getFiles_IafFileSvc system MCP tool and the GetFileNameById custom MCP tool.",
        "_userType": "related_items_file_helper_agent",
        "_namespaces": [
            "iputGraph_kxYOcW7O"
        ],
        "_config": {
            "_model": "gpt-4o",
            "_provider": "openai",
            "_temperature": 1.5
        },
        "_tools": [
            "RelatedQueryTool",
            "SearchRelatedItemsTool",
            "getFiles_IafFileSvc",
            "GetFileNameById"
        ],
        "_promptTemplate": "platform_resource_universal_tmpl",
        "_invocationMessage": "Analyzing related items and files…",
        "_id": "6fe848f8-3d9b-48ff-bcf1-643756168904",
        "_irn": "aisvc:agent:6fe848f8-3d9b-48ff-bcf1-643756168904",
        "_metadata": {
            "_createdAt": "1757048208583",
            "_updatedById": "70699091-77de-4ee3-8a3f-034ec8746a3b",
            "_createdById": "70699091-77de-4ee3-8a3f-034ec8746a3b",
            "_updatedAt": "1757048208583"
        }        
    }
  ]
}

Get agent by ID

Endpoints

GET aisvc/api/v1/agents/{id}

Response

Codes

Code	Description
`200`	Success
`400`	Bad Request
`404`	Not Found

Response body

    {
        "_name": "Related Items and File Helper Agent",
        "_background": "It uses the RelatedQueryTool to generate related queries as JSON from the user prompt and feeds them to the SearchRelatedItemsTool to retrieve data from the Item Service. It can also look up file information using the getFiles_IafFileSvc system MCP tool and the GetFileNameById custom MCP tool.",
        "_userType": "related_items_file_helper_agent",
        "_namespaces": [
            "iputGraph_kxYOcW7O"
        ],
        "_config": {
            "_model": "gpt-4o",
            "_provider": "openai",
            "_temperature": 1.5
        },
        "_tools": [
            "RelatedQueryTool",
            "SearchRelatedItemsTool",
            "getFiles_IafFileSvc",
            "GetFileNameById"
        ],
        "_invocationMessage": "Analyzing related items and files…",
        "_id": "6fe848f8-3d9b-48ff-bcf1-643756168904",
        "_irn": "aisvc:agent:6fe848f8-3d9b-48ff-bcf1-643756168904",
        "_metadata": {
            "_createdAt": "1757048208583",
            "_updatedById": "70699091-77de-4ee3-8a3f-034ec8746a3b",
            "_createdById": "70699091-77de-4ee3-8a3f-034ec8746a3b",
            "_updatedAt": "1757048208583"
        }        
    }

Update agent by ID

Endpoints

PUT aisvc/api/v1/agents/{id}

Request

Request body

Parameter	Type	Description	Required
`_name`	String	The agent name	Required
`_background`	String	The context for the agent	Required
`_userType`	String	Unique identifier of the agent	Required
`_description`	String	Agent's description	Optional
`_tools`	Array of String	Tools usable by the agent. Each entry is either a regular tool's `_userType` or a Twinit MCP tool's `_name` — both system MCP tools (for example, `getFiles_IafFileSvc`) and custom (user) MCP tools (for example, `GetFileNameById`). See Twinit MCP tools (`_tools`) above.	Optional
`_knowledgebases`	Array of String	The identifiers (`_userType`) of knowledge bases usable by agent	Optional
`_externalMcpServers`	Array of Object	External MCP servers the agent can use (by `_userType`)	Optional
`_promptTemplate`	String	The `_userType` of a Prompt Template to assign to this agent. The template serves as the agent's instruction and is parameterized at runtime.	Optional
`_invocationMessage`	String	A short, plain-text status message streamed to the conversation when this agent is invoked during a team run (for example, `Analyzing related items and files…`). Maximum 500 characters (leading/trailing whitespace is trimmed). Must be plain text — HTML tags and template expressions (`{{ }}`, `${ }`, `<% %>`) are not allowed. An empty or whitespace-only value is stored as `null`.	Optional
`_config`	Object	Configuration for the agent's LLM model	Required

LLM configuration (`_config`)

Parameter	Type	Description	Required
`_config._provider`	String	The LLM provider (for example, `openai` or `anthropic`)	Required
`_config._model`	String	The LLM model name (for example, `gpt-4o`)	Required
`_config._temperature`	Number	Sampling temperature. Must be within the allowed range for the selected model. If omitted or `null`, the service uses the model's default temperature.	Optional

MCP servers (`_externalMcpServers`)

Note: This field is stored internally on the agent resource as external_mcp_servers (JSONB).

Parameter	Type	Description	Required
`_externalMcpServers[]. _userType`	String	External MCP server config `_userType` (see External MCP Server Config API).	Required
`_externalMcpServers[]. _filter`	Object	Optional filter for MCP tool visibility.	Optional
`_externalMcpServers[]. _filter._names`	Array of String	Optional list of MCP tool names to allow from this server.	Optional

Request body example

{
    "_name": "Related Items and File Helper Agent",
    "_background": "It uses the RelatedQueryTool to generate related queries as JSON from the user prompt and feeds them to the SearchRelatedItemsTool to retrieve data from the Item Service. It can also look up file information using the getFiles_IafFileSvc system MCP tool and the GetFileNameById custom MCP tool.",
    "_userType": "related_items_file_helper_agent",
    "_namespaces": [
        "iputGraph_kxYOcW7O"
    ],
    "_config": {
        "_model": "gpt-4o",
        "_provider": "openai",
        "_temperature": 1.5
    },
    "_tools": [
        "RelatedQueryTool",
        "SearchRelatedItemsTool",
        "getFiles_IafFileSvc",
        "GetFileNameById"
    ],
    "_externalMcpServers": [
        {
            "_userType": "github_mcp",
            "_filter": {
                "_names": [
                    "search_repositories",
                    "list_issues"
                ]
            }
        }
    ],
    "_promptTemplate": "platform_resource_universal_tmpl",
    "_invocationMessage": "Analyzing related items and files…"
}

Response

Codes

Code	Description
`200`	Success
`400`	Bad Request
`404`	Not Found
`422`	Unprocessable Entity

Response body

    {
        "_name": "Related Items and File Helper Agent",
        "_background": "It uses the RelatedQueryTool to generate related queries as JSON from the user prompt and feeds them to the SearchRelatedItemsTool to retrieve data from the Item Service. It can also look up file information using the getFiles_IafFileSvc system MCP tool and the GetFileNameById custom MCP tool.",
        "_userType": "related_items_file_helper_agent",
        "_namespaces": [
            "iputGraph_kxYOcW7O"
        ],
        "_config": {
            "_model": "gpt-4o",
            "_provider": "openai",
            "_temperature": 1.5
        },
        "_tools": [
            "RelatedQueryTool",
            "SearchRelatedItemsTool",
            "getFiles_IafFileSvc",
            "GetFileNameById"
        ],
        "_promptTemplate": "platform_resource_universal_tmpl",
        "_invocationMessage": "Analyzing related items and files…",
        "_id": "6fe848f8-3d9b-48ff-bcf1-643756168904",
        "_irn": "aisvc:agent:6fe848f8-3d9b-48ff-bcf1-643756168904",
        "_metadata": {
            "_createdAt": "1757048208583",
            "_updatedById": "70699091-77de-4ee3-8a3f-034ec8746a3b",
            "_createdById": "70699091-77de-4ee3-8a3f-034ec8746a3b",
            "_updatedAt": "1757048208583"
        }        
    }

Delete agent by ID

Endpoints

DELETE aisvc/api/v1/agents/{id}

Request

Request body

None

Response

Codes

Code	Description
`200`	Success
`400`	Bad Request
`404`	Not Found

Response body

// empty response body

<!-- Hidden per PLN-2761: custom agents run in the AI Service process space and are no longer documented. Use custom MCP tools instead.

Upload Agent Source Code

Endpoints

PUT aisvc/api/v1/agents/{id}/sourcecodes

Request

Request body

{
    "_content":"import { Agent } from '@dtplatform/agent-core';\nimport { IafItemSvc } from '@dtplatform/platform-api';\n\ninterface ChillerRequest {\n    chillerId: string;\n    capacityKw: number;\n    metric: string; // e.g. \"chiller_load_kw\"\n    thresholdPct: number; // e.g. 0.9 for 90%\n    lookbackDays?: number;\n}\n\ntype Reading = {\n  _id: string;\n  _ts: string; // timestamp in UTC\n  chiller_load_kw: number;\n  chiller_load_pct: number;\n};\n\ntype Data = {\n  _list: Reading[];\n};\n\nexport default class ChillerForecastAgent extends Agent {\n    requestContext: any = {}\n    constructor(options: any, requestContext: any) {\n        super(options);\n        this.requestContext = requestContext;\n    }\n\n    async processRequest(\n        type: string,\n        state?: any,\n        prompt?: string,\n        tools?: any[],\n        userId?: string,\n        sessionId?: string,\n        chatHistory?: [],\n        additionalParams?: Record<string, string>,\n    ): Promise<any> {\n\n        // ------------------------------\n        // 1. Interpret prompt (simple parsing via LLM)\n        // ------------------------------\n        const llmRes: any = await this.simpleCall(`Extract structured JSON from the following prompt. \n            Fields: chillerId and lookbackDays (optional).\n            Prompt: ${prompt}`);\n\n        //console.log(llmRes, \">>llmRes\")\n        console.log(llmRes?.content, \">>llmRes?.content\")\n\n        let chillerReq: ChillerRequest;\n\n        try {\n            let rawContent: string = llmRes?.content || \"\";\n\n            // Remove Markdown code fences if they exist\n            rawContent = rawContent.replace(/```json|```/gi, \"\").trim();\n\n            // Try to extract JSON block if extra text is present\n            const jsonMatch = rawContent.match(/\{[\s\S]*\}/);\n            if (jsonMatch) {\n                rawContent = jsonMatch[0];\n            }\n\n            chillerReq = JSON.parse(rawContent);\n\n        } catch (err) {\n            console.error(\"Failed to parse chiller request:\", err);\n            return {\n                messages: [\n                    {\n                        role: \"assistant\",\n                        content: JSON.stringify({ error: \"Invalid LLM JSON response\", raw: llmRes })\n                    }\n                ]\n            };\n        }\n\n        const lookback = chillerReq.lookbackDays ?? 90;\n        const startDate = new Date();\n        startDate.setDate(startDate.getDate() - lookback);\n\n        const aggs = [\n            {\n                $match: {\n                    \"_tsMetadata._sourceId\": { \"$regex\": `.*${chillerReq.chillerId}.*` } ,\n                    \"_ts\": { $gte: startDate.toISOString() }\n                }\n            },\n            { $sort: { ts: 1 } },\n            { $limit: 10 }\n\n        ];\n\n        console.log('Aggs::', JSON.stringify(aggs))\n        \n        let res = await IafItemSvc.aggregateReadings('68c50a58993fee0ea750db6f', aggs, this.requestContext, {});\n        let finalRes = this.predictChiller90(res);\n        console.log(finalRes, 'finalRes')\n        return {\n            messages: [\n                {\n                    role: \"assistant\",\n                    content: `Chiller will cross 90% load around:\", ${finalRes}`\n                }\n            ]\n        };\n    }\n\n\n    predictChiller90(data: Data): Date | null {\n        // Step 1: clean duplicates by unique timestamp\n        const readings: Reading[] = Object.values(\n            data._list.reduce<Record<string, Reading>>((acc, item) => {\n            acc[item._ts] = item; // overwrite duplicates\n            return acc;\n            }, {})\n        );\n\n        if (readings.length < 2) return null; // not enough data to predict\n\n        // Step 2: sort by timestamp\n        readings.sort((a, b) => new Date(a._ts).getTime() - new Date(b._ts).getTime());\n\n        // Step 3: convert timestamps to epoch ms\n        const points = readings.map(r => ({\n            ts: new Date(r._ts).getTime(),\n            load: r.chiller_load_pct\n        }));\n\n        // Step 4: calculate slope & intercept (linear regression)\n        const n = points.length;\n        const sumX = points.reduce((s, p) => s + p.ts, 0);\n        const sumY = points.reduce((s, p) => s + p.load, 0);\n        const sumXY = points.reduce((s, p) => s + p.ts * p.load, 0);\n        const sumX2 = points.reduce((s, p) => s + p.ts * p.ts, 0);\n\n        const denominator = n * sumX2 - sumX * sumX;\n        if (denominator === 0) return null; // avoid division by zero\n\n        const slope = (n * sumXY - sumX * sumY) / denominator;\n        const intercept = (sumY - slope * sumX) / n;\n\n        // Step 5: solve for timestamp when load = 0.9\n        const targetLoad = 0.9;\n        const targetTs = (targetLoad - intercept) / slope;\n\n        if (isNaN(targetTs) || !isFinite(targetTs)) return null;\n\n        return new Date(targetTs);\n    }\n\n}\n"
}

Response

Codes

Code	Description
`200`	Success
`400`	Bad Request
`404`	Not Found

Get Agent Source Code

Endpoints

GET aisvc/api/v1/agents/{id}/sourcecodes

Response

Codes

Code	Description
`200`	Success
`400`	Bad Request
`404`	Not Found

Response body

    [
    {
        "_content": "import { Agent } from '@dtplatform/agent-core';\nimport { IafItemSvc } from '@dtplatform/platform-api';\n\ninterface ChillerRequest {\n    chillerId: string;\n    capacityKw: number;\n    metric: string; // e.g. \"chiller_load_kw\"\n    thresholdPct: number; // e.g. 0.9 for 90%\n    lookbackDays?: number;\n}\n\ntype Reading = {\n  _id: string;\n  _ts: string; // timestamp in UTC\n  chiller_load_kw: number;\n  chiller_load_pct: number;\n};\n\ntype Data = {\n  _list: Reading[];\n};\n\nexport default class ChillerForecastAgent extends Agent {\n    requestContext: any = {}\n    constructor(options: any, requestContext: any) {\n        super(options);\n        this.requestContext = requestContext;\n    }\n\n    async processRequest(\n        type: string,\n        state?: any,\n        prompt?: string,\n        tools?: any[],\n        userId?: string,\n        sessionId?: string,\n        chatHistory?: [],\n        additionalParams?: Record<string, string>,\n    ): Promise<any> {\n      \n\n        // ------------------------------\n        // 1. Interpret prompt (simple parsing via LLM)\n        // ------------------------------\n        const llmRes: any = await this.simpleCall(`Extract structured JSON from the following prompt. \n            Fields: chillerId and lookbackDays (optional).\n            Prompt: ${prompt}`);\n\n        //console.log(llmRes, \">>llmRes\")\n        console.log(llmRes?.content, \">>llmRes?.content\")\n\n        let chillerReq: ChillerRequest;\n\n        try {\n            let rawContent: string = llmRes?.content || \"\";\n\n            // Remove Markdown code fences if they exist\n            rawContent = rawContent.replace(/```json|```/gi, \"\").trim();\n\n            // Try to extract JSON block if extra text is present\n            const jsonMatch = rawContent.match(/\\{[\\s\\S]*\\}/);\n            if (jsonMatch) {\n                rawContent = jsonMatch[0];\n            }\n\n            chillerReq = JSON.parse(rawContent);\n\n        } catch (err) {\n            console.error(\"Failed to parse chiller request:\", err);\n            return {\n                messages: [\n                    {\n                        role: \"assistant\",\n                        content: JSON.stringify({ error: \"Invalid LLM JSON response\", raw: llmRes })\n                    }\n                ]\n            };\n        }\n\n        // ------------------------------\n        // 2. Query Related Items\n        // ------------------------------\n        const telItems = await IafItemSvc.getRelatedItems(\n            '68c50a58993fee0ea750db6f',\n            { query: { \"_sourceId\": { \"$regex\": `.*${chillerReq.chillerId}.*` } } },\n            this.requestContext\n        );\n\n        const lookback = chillerReq.lookbackDays ?? 90;\n        const startDate = new Date();\n        startDate.setDate(startDate.getDate() - lookback);\n\n        const aggs = [\n            {\n                $match: {\n                    \"_tsMetadata._sourceId\": { \"$regex\": `.*${chillerReq.chillerId}.*` } ,\n                    \"_ts\": { $gte: startDate.toISOString() }\n                }\n            },\n            { $sort: { ts: 1 } },\n            { $limit: 10 }\n\n        ];\n\n        console.log('Aggs::', JSON.stringify(aggs))\n        \n        let res = await IafItemSvc.aggregateReadings('68c50a58993fee0ea750db6f', aggs, this.requestContext, {});\n        let finalRes = this.predictChiller90(res);\n        console.log(finalRes, 'finalRes')\n        return {\n            messages: [\n                {\n                    role: \"assistant\",\n                    content: `Chiller will cross 90% load around:\", ${finalRes}`\n                }\n            ]\n        };\n    }\n\n\n    predictChiller90(data: Data): Date | null {\n        // Step 1: clean duplicates by unique timestamp\n        const readings: Reading[] = Object.values(\n            data._list.reduce<Record<string, Reading>>((acc, item) => {\n            acc[item._ts] = item; // overwrite duplicates\n            return acc;\n            }, {})\n        );\n\n        if (readings.length < 2) return null; // not enough data to predict\n\n        // Step 2: sort by timestamp\n        readings.sort((a, b) => new Date(a._ts).getTime() - new Date(b._ts).getTime());\n\n        // Step 3: convert timestamps to epoch ms\n        const points = readings.map(r => ({\n            ts: new Date(r._ts).getTime(),\n            load: r.chiller_load_pct\n        }));\n\n        // Step 4: calculate slope & intercept (linear regression)\n        const n = points.length;\n        const sumX = points.reduce((s, p) => s + p.ts, 0);\n        const sumY = points.reduce((s, p) => s + p.load, 0);\n        const sumXY = points.reduce((s, p) => s + p.ts * p.load, 0);\n        const sumX2 = points.reduce((s, p) => s + p.ts * p.ts, 0);\n\n        const denominator = n * sumX2 - sumX * sumX;\n        if (denominator === 0) return null; // avoid division by zero\n\n        const slope = (n * sumXY - sumX * sumY) / denominator;\n        const intercept = (sumY - slope * sumX) / n;\n\n        // Step 5: solve for timestamp when load = 0.9\n        const targetLoad = 0.9;\n        const targetTs = (targetLoad - intercept) / slope;\n\n        if (isNaN(targetTs) || !isFinite(targetTs)) return null;\n\n        return new Date(targetTs);\n    }\n\n}\n"
    }
]

-->

Overview​

List agents​

Endpoints​

Request​

Query parameters​

Request example​

Response​

Codes​

Response body​

Create agent​

Endpoints​

Request​

Request body​

LLM configuration (_config)​

Twinit MCP tools (_tools)​

MCP servers (_externalMcpServers)​

Request body example​

Response​

Codes​

Response body​

Get agent by ID​

Endpoints​

Response​

Codes​

Response body​

Update agent by ID​

Endpoints​

Request​

Request body​

LLM configuration (_config)​

MCP servers (_externalMcpServers)​

Request body example​

Response​

Codes​

Response body​

Delete agent by ID​

Endpoints​

Request​

Request body​

Response​

Codes​

Response body​

Upload Agent Source Code​

Endpoints​

Request​

Request body​

Response​

Codes​

Get Agent Source Code​

Endpoints​

Response​

Codes​

Response body​

Overview

List agents

Endpoints

Request

Query parameters

Request example

Response

Codes

Response body

Create agent

Endpoints

Request

Request body

LLM configuration (`_config`)

Twinit MCP tools (`_tools`)

MCP servers (`_externalMcpServers`)

Request body example

Response

Codes

Response body

Get agent by ID

Endpoints

Response

Codes

Response body

Update agent by ID

Endpoints

Request

Request body

LLM configuration (`_config`)

MCP servers (`_externalMcpServers`)

Request body example

Response

Codes

Response body

Delete agent by ID

Endpoints

Request

Request body

Response

Codes

Response body

Upload Agent Source Code

Endpoints

Request

Request body

Response

Codes

Get Agent Source Code

Endpoints

Response

Codes

Response body