A valid request URL is required to generate request examples{
"error": {
"name": "<string>",
"statusCode": 123,
"data": "<unknown>",
"message": "<string>"
},
"status": "error"
}Post apiv1projects aiagents threads stream
A valid request URL is required to generate request examples{
"error": {
"name": "<string>",
"statusCode": 123,
"data": "<unknown>",
"message": "<string>"
},
"status": "error"
}Body
Tool names hinted by the user when they composed the message (via suggestion chips that carry a tool id). agentV2 appends a soft hint to the user message before sending it to the LLM. Transient ā never persisted.
Skips the SQL human-approval gate for this stream. Used by the review remediation workspace so Continue PR turns run frictionlessly. Defaults to false ā normal chat still asks the user to approve SQL.
Per-thread toggle that decides whether the agent gets access to the
runSql / listWarehouseTables / describeWarehouseTable tools for this
stream. Frontend tracks the toggle in its slice; passed in on every
stream call. Falls back to false when omitted (e.g. older clients,
API callers) so the safer "semantic layer only" mode is the default.
Response
Success
Was this page helpful?