Payload schema
requestOffsetinteger
The settled request: the offset of its llm-request-requested event.
durationMsintegeroptional
Wall-clock duration of the settling attempt.
resultobject
How the request settled.
status: "succeeded"object
status"succeeded"
textstring
The assistant's text — ALSO carried by the atomically-appended assistant context item; kept here so the settled event alone tells the whole story.
usageobjectoptional
Normalized provider-reported token usage.
inputTokensinteger
Total input tokens, including cached ones.
outputTokensinteger
Total output tokens, including reasoning ones.
cachedInputTokensintegeroptional
Prompt-cache hits, where the model reports them.
reasoningOutputTokensintegeroptional
Reasoning/thinking tokens, where the model reports them.
rawResponseanyoptional
Provider response verbatim.
status: "failed"object
status"failed"
errorMessagestring
What the transport reported.
rawResponseanyoptional
Provider response verbatim.
status: "cancelled"object
status"cancelled"
reason"interrupted-by-user-input" | "expired"
Why the request was cancelled.
partialTextstringoptional
Whatever streamed before the abort — preserved for the conversation.
Raw JSON schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"requestOffset": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991,
"description": "The settled request: the offset of its llm-request-requested event."
},
"durationMs": {
"description": "Wall-clock duration of the settling attempt.",
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
},
"result": {
"oneOf": [
{
"type": "object",
"properties": {
"status": {
"type": "string",
"const": "succeeded"
},
"text": {
"type": "string",
"description": "The assistant's text — ALSO carried by the atomically-appended assistant context item; kept here so the settled event alone tells the whole story."
},
"usage": {
"description": "Normalized provider-reported token usage.",
"type": "object",
"properties": {
"inputTokens": {
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991,
"description": "Total input tokens, including cached ones."
},
"outputTokens": {
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991,
"description": "Total output tokens, including reasoning ones."
},
"cachedInputTokens": {
"description": "Prompt-cache hits, where the model reports them.",
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
},
"reasoningOutputTokens": {
"description": "Reasoning/thinking tokens, where the model reports them.",
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
}
},
"required": [
"inputTokens",
"outputTokens"
]
},
"rawResponse": {
"description": "Provider response verbatim."
}
},
"required": [
"status",
"text"
]
},
{
"type": "object",
"properties": {
"status": {
"type": "string",
"const": "failed"
},
"errorMessage": {
"type": "string",
"description": "What the transport reported."
},
"rawResponse": {
"description": "Provider response verbatim."
}
},
"required": [
"status",
"errorMessage"
]
},
{
"type": "object",
"properties": {
"status": {
"type": "string",
"const": "cancelled"
},
"reason": {
"type": "string",
"enum": [
"interrupted-by-user-input",
"expired"
],
"description": "Why the request was cancelled."
},
"partialText": {
"description": "Whatever streamed before the abort — preserved for the conversation.",
"type": "string"
}
},
"required": [
"status",
"reason"
]
}
],
"description": "How the request settled."
}
},
"required": [
"requestOffset",
"result"
]
}