mirror of
https://github.com/openai/codex.git
synced 2026-11-15 21:50:46 +00:00
Zahan Malkani
5943d7acdf
## What changed - Record voice transcripts as `frame` items with a `voice_transcript` channel for eligible threads, while retaining legacy transcript support and the existing app-server live and mixed timeline representation. - Assign first-observed timestamps that never move backward, retain them through completion, and restore the clock floor from history and compaction checkpoints. - Flush realtime records before completion notifications, including file and initial directory durability barriers for local rollouts. - Generate a distinct default session ID for each new call, use the call ID when attaching to an existing call, and derive opening record IDs from session IDs. - Add protocol types for turn-input acceptance and session-end input receipts, excluding those receipts from live notifications and mixed timelines. Update generated schemas and SDK types. ## Testing Add coverage for frame serialization and required voice payloads, clock rollback and checkpoint restoration, durability barrier failures and retries, per-call session IDs, and persisted transcript availability immediately after completion. GitOrigin-RevId: 3f6632b517d563861aee085b723475b8945c391c
335 lines
8.4 KiB
JSON
Generated
335 lines
8.4 KiB
JSON
Generated
{
|
|
"$schema": "http://json-schema.org/draft-07/schema#",
|
|
"definitions": {
|
|
"ThreadRealtimeBemItemPresentation": {
|
|
"description": "EXPERIMENTAL - how an existing agent item appears in a realtime conversation.",
|
|
"oneOf": [
|
|
{
|
|
"properties": {
|
|
"type": {
|
|
"enum": [
|
|
"wholeItem"
|
|
],
|
|
"title": "WholeItemThreadRealtimeBemItemPresentationType",
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"type"
|
|
],
|
|
"title": "WholeItemThreadRealtimeBemItemPresentation",
|
|
"type": "object"
|
|
},
|
|
{
|
|
"properties": {
|
|
"type": {
|
|
"enum": [
|
|
"inlineMarkdown"
|
|
],
|
|
"title": "InlineMarkdownThreadRealtimeBemItemPresentationType",
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"type"
|
|
],
|
|
"title": "InlineMarkdownThreadRealtimeBemItemPresentation",
|
|
"type": "object"
|
|
},
|
|
{
|
|
"properties": {
|
|
"index": {
|
|
"format": "uint32",
|
|
"minimum": 0.0,
|
|
"type": "integer"
|
|
},
|
|
"type": {
|
|
"enum": [
|
|
"inlineVisualization"
|
|
],
|
|
"title": "InlineVisualizationThreadRealtimeBemItemPresentationType",
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"index",
|
|
"type"
|
|
],
|
|
"title": "InlineVisualizationThreadRealtimeBemItemPresentation",
|
|
"type": "object"
|
|
}
|
|
]
|
|
},
|
|
"ThreadRealtimeFrameChannels": {
|
|
"description": "A frame holds one or more payloads, at most one per channel. They share one ID, observation time, and seal. V1 requires its only channel, `voice_transcript`.",
|
|
"properties": {
|
|
"voice_transcript": {
|
|
"$ref": "#/definitions/ThreadRealtimeVoiceTranscript"
|
|
}
|
|
},
|
|
"required": [
|
|
"voice_transcript"
|
|
],
|
|
"type": "object"
|
|
},
|
|
"ThreadRealtimeHandoffMode": {
|
|
"enum": [
|
|
"start",
|
|
"steer"
|
|
],
|
|
"type": "string"
|
|
},
|
|
"ThreadRealtimeItem": {
|
|
"description": "EXPERIMENTAL - a thread-scoped realtime item in the canonical timeline.",
|
|
"oneOf": [
|
|
{
|
|
"properties": {
|
|
"type": {
|
|
"enum": [
|
|
"realtimeSessionStarted"
|
|
],
|
|
"title": "RealtimeSessionStartedThreadRealtimeItemType",
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"type"
|
|
],
|
|
"title": "RealtimeSessionStartedThreadRealtimeItem",
|
|
"type": "object"
|
|
},
|
|
{
|
|
"properties": {
|
|
"channels": {
|
|
"$ref": "#/definitions/ThreadRealtimeFrameChannels"
|
|
},
|
|
"type": {
|
|
"enum": [
|
|
"frame"
|
|
],
|
|
"title": "FrameThreadRealtimeItemType",
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"channels",
|
|
"type"
|
|
],
|
|
"title": "FrameThreadRealtimeItem",
|
|
"type": "object"
|
|
},
|
|
{
|
|
"properties": {
|
|
"role": {
|
|
"$ref": "#/definitions/ThreadRealtimeTranscriptRole"
|
|
},
|
|
"text": {
|
|
"type": "string"
|
|
},
|
|
"type": {
|
|
"enum": [
|
|
"transcriptSegment"
|
|
],
|
|
"title": "TranscriptSegmentThreadRealtimeItemType",
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"role",
|
|
"text",
|
|
"type"
|
|
],
|
|
"title": "TranscriptSegmentThreadRealtimeItem",
|
|
"type": "object"
|
|
},
|
|
{
|
|
"properties": {
|
|
"item_id": {
|
|
"type": "string"
|
|
},
|
|
"presentation": {
|
|
"$ref": "#/definitions/ThreadRealtimeBemItemPresentation"
|
|
},
|
|
"turn_id": {
|
|
"type": "string"
|
|
},
|
|
"type": {
|
|
"enum": [
|
|
"bemItemPromoted"
|
|
],
|
|
"title": "BemItemPromotedThreadRealtimeItemType",
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"item_id",
|
|
"presentation",
|
|
"turn_id",
|
|
"type"
|
|
],
|
|
"title": "BemItemPromotedThreadRealtimeItem",
|
|
"type": "object"
|
|
},
|
|
{
|
|
"properties": {
|
|
"outcome": {
|
|
"$ref": "#/definitions/ThreadRealtimeSessionOutcome"
|
|
},
|
|
"type": {
|
|
"enum": [
|
|
"realtimeSessionClosed"
|
|
],
|
|
"title": "RealtimeSessionClosedThreadRealtimeItemType",
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"outcome",
|
|
"type"
|
|
],
|
|
"title": "RealtimeSessionClosedThreadRealtimeItem",
|
|
"type": "object"
|
|
},
|
|
{
|
|
"properties": {
|
|
"handoff_id": {
|
|
"type": "string"
|
|
},
|
|
"input": {
|
|
"type": "string"
|
|
},
|
|
"input_item_id": {
|
|
"type": "string"
|
|
},
|
|
"mode": {
|
|
"$ref": "#/definitions/ThreadRealtimeHandoffMode"
|
|
},
|
|
"source_event_ids": {
|
|
"items": {
|
|
"type": "string"
|
|
},
|
|
"type": "array"
|
|
},
|
|
"turn_id": {
|
|
"type": "string"
|
|
},
|
|
"type": {
|
|
"enum": [
|
|
"turnInputAccepted"
|
|
],
|
|
"title": "TurnInputAcceptedThreadRealtimeItemType",
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"handoff_id",
|
|
"input",
|
|
"input_item_id",
|
|
"mode",
|
|
"source_event_ids",
|
|
"turn_id",
|
|
"type"
|
|
],
|
|
"title": "TurnInputAcceptedThreadRealtimeItem",
|
|
"type": "object"
|
|
},
|
|
{
|
|
"properties": {
|
|
"input": {
|
|
"type": "string"
|
|
},
|
|
"input_item_id": {
|
|
"type": "string"
|
|
},
|
|
"source_event_ids": {
|
|
"items": {
|
|
"type": "string"
|
|
},
|
|
"type": "array"
|
|
},
|
|
"type": {
|
|
"enum": [
|
|
"sessionEndInputSaved"
|
|
],
|
|
"title": "SessionEndInputSavedThreadRealtimeItemType",
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"input",
|
|
"input_item_id",
|
|
"source_event_ids",
|
|
"type"
|
|
],
|
|
"title": "SessionEndInputSavedThreadRealtimeItem",
|
|
"type": "object"
|
|
}
|
|
],
|
|
"properties": {
|
|
"id": {
|
|
"type": "string"
|
|
},
|
|
"observedAtMs": {
|
|
"description": "Canonical observation time in Unix milliseconds for eligible voice calls.",
|
|
"format": "int64",
|
|
"type": [
|
|
"integer",
|
|
"null"
|
|
]
|
|
},
|
|
"realtimeSessionId": {
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"id",
|
|
"realtimeSessionId"
|
|
],
|
|
"type": "object"
|
|
},
|
|
"ThreadRealtimeSessionOutcome": {
|
|
"enum": [
|
|
"ended",
|
|
"failed"
|
|
],
|
|
"type": "string"
|
|
},
|
|
"ThreadRealtimeTranscriptRole": {
|
|
"enum": [
|
|
"user",
|
|
"assistant"
|
|
],
|
|
"type": "string"
|
|
},
|
|
"ThreadRealtimeVoiceTranscript": {
|
|
"properties": {
|
|
"role": {
|
|
"$ref": "#/definitions/ThreadRealtimeTranscriptRole"
|
|
},
|
|
"text": {
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"role",
|
|
"text"
|
|
],
|
|
"type": "object"
|
|
}
|
|
},
|
|
"description": "EXPERIMENTAL - a realtime timeline item started before its content streams.",
|
|
"properties": {
|
|
"item": {
|
|
"$ref": "#/definitions/ThreadRealtimeItem"
|
|
},
|
|
"threadId": {
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"item",
|
|
"threadId"
|
|
],
|
|
"title": "ThreadRealtimeItemStartedNotification",
|
|
"type": "object"
|
|
} |