Send message to thread

Access control

requires_org
Restricted tokens cannot call this endpoint

POST/v1/ai/threads/{thread_id}/messages

Authorization

AuthorizationBearer token · headerrequired

Path parameters

thread_idstringrequired

Header parameters

X-Roboto-Org-Idstring

X-Roboto-User-Idstring

Request body

requiredapplication/json

client_contextClientViewingContext | null

default: null

Show properties

Any of:

ClientViewingContext

dataset_idsstring[]

file_idsstring[]

collection_idsstring[]

device_idsstring[]

view_idsstring[]

table_stateobject | null

default: null

Show properties

Any of:

object

object

null

null

display_time_anchor_nsinteger | null

default: null

Show properties

Any of:

integer

integer

null

null

display_time_anchor_labelstring | null

default: null

Show properties

Any of:

string

string

null

null

visualizer_stateobject | null

default: null

Show properties

Any of:

object

object

null

null

misc_contextobject | null

default: null

Show properties

Any of:

object

object

null

null

null

null

messageAgentMessage | null

default: null

Show properties

Any of:

AgentMessage

roleAgentRolerequired

Enumeration of possible roles in an agent thread.

Defines the different participants that can send messages in a thread.

Allowed:userassistantroboto

Show properties

Array of

AgentTextContent | AgentToolUseContent | AgentToolResultContent | AgentErrorContent | AgentDeletedContent | AgentCompressionFillerContent | AgentClientContextEntry

Any of:

AgentTextContent

textstringrequired

AgentToolUseContent

content_typestring

default: "tool_use"

tool_namestringrequired

tool_use_idstringrequired

inputobject | null

default: null

Show properties

Any of:

object

object

null

null

raw_requestobject | null

default: null

Show properties

Any of:

object

object

null

null

AgentToolResultContent

content_typestring

default: "tool_result"

tool_namestringrequired

tool_use_idstringrequired

runtime_msintegerrequired

statusstringrequired

payloadstring | object | any[] | null

default: null

Show properties

Any of:

string

string

object

object

any[]

Array of any

any

null

null

raw_responseobject | null

default: null

Show properties

Any of:

object

object

null

null

AgentErrorContent

content_typestring

default: "error"

error_messagestringrequired

error_codestring | null

default: null

Show properties

Any of:

string

string

null

null

AgentDeletedContent

content_typestring

default: "deleted"

AgentCompressionFillerContent

content_typestring

default: "compression_filler"

AgentClientContextEntry

content_typestring

default: "client_context"

contextClientViewingContextrequired

What the Roboto client (e.g. the Web UI) is currently viewing when the user composed a message.

Passed to the agent as implicit context for resolving deictic references — "this dataset", "those files", "the visualizer state I'm looking at" — that the user would otherwise have to spell out. This type is purely informational; it is not enforced and never gates tool authorization.

Distinct from:

:class:AnalysisScope, which is a hard analysis window honored by individual tools on the server side.
:class:~roboto.ai.goals.AgentGoal, which declares typed outcomes the agent runner must drive the turn to satisfy.

The corresponding wire-format field is client_context (with a one-release context alias for migration).

Show properties

dataset_idsstring[]

file_idsstring[]

collection_idsstring[]

device_idsstring[]

view_idsstring[]

table_stateobject | null

default: null

Show properties

Any of:

object

object

null

null

display_time_anchor_nsinteger | null

default: null

Show properties

Any of:

integer

integer

null

null

display_time_anchor_labelstring | null

default: null

Show properties

Any of:

string

string

null

null

visualizer_stateobject | null

default: null

Show properties

Any of:

object

object

null

null

misc_contextobject | null

default: null

Show properties

Any of:

object

object

null

null

statusAgentMessageStatus

Enumeration of possible message generation states.

Tracks the lifecycle of message generation from initiation to completion.

Allowed:not_startedgeneratingcompletedfailedcancelled

createdstring<date-time>

null

null

client_toolsClientToolSpec[] | null

default: null

Show properties

Any of:

ClientToolSpec[]

Array of ClientToolSpec

namestringrequired

descriptionstringrequired

input_schemaobjectrequired

null

null

analysis_scopeAnalysisScope | null

default: null

Show properties

Any of:

AnalysisScope

start_timeinteger | null

default: null

Show properties

Any of:

integer

integer

null

null

end_timeinteger | null

default: null

Show properties

Any of:

integer

integer

null

null

null

null

goalsDatasetSummaryAgentGoal | DatasetTriageGoal | CreateEventsGoal[] | null

default: null

Show properties

Any of:

DatasetSummaryAgentGoal | DatasetTriageGoal | CreateEventsGoal[]

Array of DatasetSummaryAgentGoal | DatasetTriageGoal | CreateEventsGoal

One of:

DatasetSummaryAgentGoal

goal_typestring

default: "dataset_summary"

dataset_idstringrequired

summary_format_spec_promptstring | null

default: null

Show properties

Any of:

string

string

null

null

DatasetTriageGoal

goal_typestring

default: "dataset_triage"

dataset_idstringrequired

label_vocabularyobjectrequired

CreateEventsGoal

goal_typestring

default: "create_events"

dataset_idstringrequired

event_vocabularyobjectrequired

tag_vocabularyobject

collection_idstring | null

default: null

Show properties

Any of:

string

string

null

null

event_focus_promptstring | null

default: null

Show properties

Any of:

string

string

null

null

null

null

invoke_skillsInvokeSkillSpec[]

Show properties

Array of InvokeSkillSpec

skill_idstringrequired

versioninteger | null

default: null

Show properties

Any of:

integer

integer

null

null

Responses

200

datanullrequired

400

Thrown when the conversation context (messages, system prompt, tool results) exceeds the model's context window limit.

The token estimate and the model's context limit are not carried on the exception, so a caller cannot read usage numbers off it.

errorobject

Show properties

error_codenumber

messagestring

stack_tracestring | null

401

Thrown when authentication fails

errorobject

Show properties

error_codenumber

messagestring

stack_tracestring | null

403

Thrown if an operation would exceed a user or org level limit.

errorobject

Show properties

error_codenumber

messagestring

stack_tracestring | null

404

Thrown if a user is attempting to perform an action unrecognized by the Roboto platform.

errorobject

Show properties

error_codenumber

messagestring

stack_tracestring | null

409

Thrown if there is a conflict between a resource you're creating and another existing resource

errorobject

Show properties

error_codenumber

messagestring

stack_tracestring | null

410

Thrown if a resource is missing or expired.

errorobject

Show properties

error_codenumber

messagestring

stack_tracestring | null

500

An error the platform reported that this SDK release cannot resolve to a specific exception class.

Reported for an element of a :py:class:~roboto.http.BatchResponse whose error names a code this release defines no class for, or that arrived without a code, without a message, or as text that is not an error envelope at all. It carries whatever code and message the platform sent, so a caller handling the failure still learns what went wrong; when no message could be read, the message is the error's raw text.

The error envelope carries no status code, so http_status_code reports the 500 inherited from :py:class:RobotoDomainException rather than the status the failure actually had.

errorobject

Show properties

error_codenumber

messagestring

stack_tracestring | null

501

Thrown by shimmed out APIs which have not yet been implemented

errorobject

Show properties

error_codenumber

messagestring

stack_tracestring | null

503

Thrown when a service is unavailable, such as when it's under heavy load and can't accept new requests. This is expected to be transient and ought to be retried.

errorobject

Show properties

error_codenumber

messagestring

stack_tracestring | null

504

Thrown when the service times out while processing a request. This is exepcted to be transient and ought to be retried.

errorobject

Show properties

error_codenumber

messagestring

stack_tracestring | null

507

Thrown when the server cannot complete the request because the response payload exceeds a storage or transport capacity limit (e.g., Lambda response size). This is NOT expected to be transient and should NOT be retried.

errorobject

Show properties

error_codenumber

messagestring

stack_tracestring | null

Try it

Server

Base URLCustom base URLOverrides the selected server when set.

Authorization

Bearer tokenRemember on this deviceInclude my values in samples

Parameters

X-Roboto-Org-IdheaderX-Roboto-User-Idheaderthread_idpath*

Bodyapplication/json

Request body

Request

curl -X POST 'https://api.roboto.ai/v1/ai/threads/string/messages' \
  -H 'Authorization: Bearer YOUR_TOKEN' \
  -H 'Content-Type: application/json' \
  -d '{
  "client_context": null,
  "message": null,
  "client_tools": null,
  "analysis_scope": null,
  "goals": null,
  "invoke_skills": [
    {
      "skill_id": "string",
      "version": null
    }
  ]
}'

const response = await fetch("https://api.roboto.ai/v1/ai/threads/string/messages", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_TOKEN",
    "Content-Type": "application/json"
  },
  body: "{\n  \"client_context\": null,\n  \"message\": null,\n  \"client_tools\": null,\n  \"analysis_scope\": null,\n  \"goals\": null,\n  \"invoke_skills\": [\n    {\n      \"skill_id\": \"string\",\n      \"version\": null\n    }\n  ]\n}"
});

import requests

response = requests.post(
    "https://api.roboto.ai/v1/ai/threads/string/messages",
    headers={
        "Authorization": "Bearer YOUR_TOKEN",
        "Content-Type": "application/json"
    },
    data="{\n  \"client_context\": null,\n  \"message\": null,\n  \"client_tools\": null,\n  \"analysis_scope\": null,\n  \"goals\": null,\n  \"invoke_skills\": [\n    {\n      \"skill_id\": \"string\",\n      \"version\": null\n    }\n  ]\n}",
)

Response

{
  "data": null
}

{
  "error": {
    "error_code": 0,
    "message": "string",
    "stack_trace": "string"
  }
}

{
  "error": {
    "error_code": 0,
    "message": "string",
    "stack_trace": "string"
  }
}

{
  "error": {
    "error_code": 0,
    "message": "string",
    "stack_trace": "string"
  }
}

{
  "error": {
    "error_code": 0,
    "message": "string",
    "stack_trace": "string"
  }
}

{
  "error": {
    "error_code": 0,
    "message": "string",
    "stack_trace": "string"
  }
}

{
  "error": {
    "error_code": 0,
    "message": "string",
    "stack_trace": "string"
  }
}

{
  "error": {
    "error_code": 0,
    "message": "string",
    "stack_trace": "string"
  }
}

{
  "error": {
    "error_code": 0,
    "message": "string",
    "stack_trace": "string"
  }
}

{
  "error": {
    "error_code": 0,
    "message": "string",
    "stack_trace": "string"
  }
}

{
  "error": {
    "error_code": 0,
    "message": "string",
    "stack_trace": "string"
  }
}

{
  "error": {
    "error_code": 0,
    "message": "string",
    "stack_trace": "string"
  }
}