Skip to content

REX ChatGPT Conversation Data

Schema overview and sample records, prepared by BRIC. Updated November 2026.

This document describes the ChatGPT conversation data collected by a REX browser extension’s Spider module (rex-spider-chatgpt), including a sample record.

A record is one ChatGPT conversation with all of its turns inlined. A conversation is identified by its stable ChatGPT conversation_id; when a participant adds more turns to an existing conversation, the next sync emits a new record under the same identifier reflecting the updated state.

Records are produced by an authenticated API crawl: the spider reads the participant’s conversation list from /backend-api/conversations (including conversations that live inside ChatGPT Projects), then fetches each updated conversation in full. If the participant is not logged in, the crawl ends without collecting anything and reports that no login was found.

Volume: one JSON object per updated ChatGPT conversation. A few to a few dozen records per active day; zero on inactive days.

Granularity: whole conversation, not turn. Turns are inlined as an array; the conversation’s identifier is stable across resyncs. A conversation’s branching and regeneration history is preserved through per-turn parent pointers.

Provenance: every record carries the participant ID, the extension name and version, and a hash of the configuration that produced it in passive-data-metadata, so records remain interpretable after instrumentation changes.

Privacy posture: configurable. The summarize setting chooses between full records and start and end times only (see Summary records). The start, end, and time_anchor settings bound which conversations are collected, by when each was last updated. The REX Content Processing module can redact content* fields (which carry prompt and response text) before they leave the browser.

The spider reads its settings from spider.spiders.chatgpt in the server configuration, on top of any shared settings in spider.spiders.default.

SettingDefaultMeaning
enabledtrueWhether the spider runs.
summarizefalsetrue sends summary records only (below).
start, endnone (no limit)The time window, in milliseconds. A conversation is collected if it was last updated inside the window.
time_anchorruntimeHow start and end are read. runtime: an offset from the time of the crawl, so start: -7776000000 means the last 90 days. install: an offset from when the extension was installed. absolute: a timestamp in milliseconds since 1970.
crawl_delay30000Milliseconds to wait between requests to ChatGPT.
sleep_delay300000The minimum time between crawls, in milliseconds. The host extension decides when crawls run.
halt_on_errortrueWhether a crawl stops at the first error.

With summarize: true, each record holds only name, date, platform, identifier, started (when the conversation was created), ended (when it was last updated), an empty turns array, and is_summary: true. No text, titles, or per-turn times are collected.

Without it, the spider sends full records like the sample below.


Below is the JSON for a single two-turn conversation record. Each turn’s raw upstream metadata* payload is shown in full; the conversation-level metadata, which repeats the whole raw conversation, is abbreviated.

{
"name": "rex-conversation",
"date": "2026-04-15T14:02:11.000Z",
"platform": "chatgpt",
"identifier": "abc123de-4567-89ab-cdef-0123456789ab",
"started": "2026-04-15T14:02:11Z",
"ended": "2026-04-15T14:03:18Z",
"user_agent": "Browser",
"metadata": { "conversation_id": "abc123de-4567-89ab-cdef-0123456789ab", "mapping": { "...": "ChatGPT's raw conversation, abbreviated here" } },
"turns": [
{
"speaker": "user",
"when": "2026-04-15T14:02:11Z",
"identifier": "aaaaaaa1-1111-2222-3333-444444444444",
"content*": "Is the CTA Red Line running normally today, or are there delays?",
"parent": "client-created-root",
"metadata*": {
"id": "aaaaaaa1-1111-2222-3333-444444444444",
"message": {
"id": "aaaaaaa1-1111-2222-3333-444444444444",
"author": { "role": "user", "name": null, "metadata": {} },
"create_time": 1776261731.0,
"content": {
"content_type": "text",
"parts": ["Is the CTA Red Line running normally today, or are there delays?"]
},
"status": "finished_successfully",
"end_turn": null,
"weight": 1.0,
"metadata": { "serialization_metadata": { "custom_symbol_offsets": [] } },
"recipient": "all",
"channel": null
},
"parent": "client-created-root",
"children": ["bbbbbbb2-2222-3333-4444-555555555555"]
}
},
{
"speaker": "assistant",
"when": "2026-04-15T14:03:18Z",
"identifier": "bbbbbbb2-2222-3333-4444-555555555555",
"content*": "As of right now, the CTA's service alerts page shows the Red Line running normally. Check transitchicago.com/alerts for the most current updates before you travel.",
"parent": "aaaaaaa1-1111-2222-3333-444444444444",
"metadata*": {
"id": "bbbbbbb2-2222-3333-4444-555555555555",
"message": {
"id": "bbbbbbb2-2222-3333-4444-555555555555",
"author": { "role": "assistant", "name": null, "metadata": {} },
"create_time": 1776261798.0,
"content": {
"content_type": "text",
"parts": ["As of right now, the CTA's service alerts page shows the Red Line running normally. Check transitchicago.com/alerts for the most current updates before you travel."]
},
"status": "finished_successfully",
"end_turn": true,
"weight": 1.0,
"metadata": {
"model_slug": "gpt-4o",
"default_model_slug": "gpt-4o",
"parent_id": "aaaaaaa1-1111-2222-3333-444444444444",
"search_result_groups": [
{
"type": "web",
"entries": [
{
"title": "CTA Service Alerts",
"url": "https://www.transitchicago.com/alerts/",
"snippet": "Red Line: normal service. No alerts are in effect.",
"ref_id": { "ref_index": 0 }
}
]
}
]
},
"recipient": "all",
"channel": null
},
"parent": "aaaaaaa1-1111-2222-3333-444444444444",
"children": []
},
"search": {
"platform": "chatgpt",
"query*": "?",
"type": "web",
"results": [
{
"title": "CTA Service Alerts",
"url": "https://www.transitchicago.com/alerts/",
"preview": "Red Line: normal service. No alerts are in effect.",
"index": 0
}
]
},
"citations": [
{
"title": "CTA Service Alerts",
"url": "https://www.transitchicago.com/alerts/",
"source": "transitchicago.com"
}
]
}
],
"passive-data-metadata": {
"source": "participant-001",
"group": "participant-001",
"generator": "rex-conversation: Example Study/1.1.0 Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/140.0.0.0 Safari/537.36",
"generator-id": "rex-conversation",
"timestamp": 1776261731.0,
"timezone": "America/Chicago",
"configuration-hash": "3f9a1c0e7b2d4a6f8e1b5c9d0a2e4f6b8c1d3e5f7a9b0c2d4e6f8a1b3c5d7e9f",
"encrypted_transmission": false
}
}

2. Example parsed view: conversation-level

Section titled “2. Example parsed view: conversation-level”

The table below flattens five sample conversation records into an analysis-ready rectangle. Timestamps are shown in the participant’s local timezone (from passive-data-metadata.timezone); the underlying epoch-millisecond values are preserved in the raw data.

conversation_idstartedendedplatformturnsmodels_usedfirst_prompt_snippetsource
abc123de…89ab2026-04-15 09:02:11 CT2026-04-15 09:03:18 CTchatgpt2gpt-4oIs the CTA Red Line running normally…participant-001
cd44ef01…12cd2026-04-15 09:17:44 CT2026-04-15 09:24:02 CTchatgpt8gpt-4o, o3-miniHelp me draft a grant cover letter for…participant-001
e5ff2233…44ef2026-04-15 10:41:09 CT2026-04-15 10:41:55 CTchatgpt2gpt-4oTranslate this paragraph into Spanish: ”…“participant-001
f6aa4455…66002026-04-15 14:08:30 CT2026-04-15 14:33:12 CTchatgpt22gpt-4o, gpt-4.5I’m debugging a Python script that reads…participant-002
aa77bb88…cc992026-04-15 16:52:01 CT2026-04-15 17:04:47 CTchatgpt6o3-miniSummarize the attached PDF and pull out…participant-002

Columns shown are a curated subset. The full record includes each turn’s content and per-turn metadata (model slug, search results, citations, parent pointers), plus each turn’s raw upstream node; see the field dictionary below.


The same records expanded to one row per turn (showing the first two conversations from the table above).

conversation_idturn_identifierwhenspeakermodelcontent_snippethas_searchhas_citationssource
abc123de…89abaaaaaaa1…44442026-04-15 09:02:11 CTusernoneIs the CTA Red Line running normally…nonoparticipant-001
abc123de…89abbbbbbbb2…55552026-04-15 09:03:18 CTassistantgpt-4oAs of right now, the CTA’s service alerts…yesyesparticipant-001
cd44ef01…12cd1111aaaa…22222026-04-15 09:17:44 CTusernoneHelp me draft a grant cover letter for…nonoparticipant-001
cd44ef01…12cd2222bbbb…33332026-04-15 09:18:02 CTassistantgpt-4oHere’s a draft cover letter. I’ve structured…nonoparticipant-001

The model column is derived from each assistant turn’s metadata*.message.metadata.model_slug. User turns have no model and are shown as none.


Reference for the fields most commonly used in analysis.

FieldTypeMeaning
namestringAlways rex-conversation. Identifies the record type for downstream routing.
dateISO timestampConversation start time. Mirrors started and the passive-data-metadata.timestamp.
platformstringAlways chatgpt for records produced by this spider.
identifierstringChatGPT’s stable conversation_id. Resyncs of the same conversation share this value.
startedISO timestampThe conversation’s create time.
endedISO timestampThe latest turn’s create time. In a summary record, the conversation’s last update time.
turnsarrayOrdered turns in the conversation; empty in a summary record. See turn-level fields below.
user_agentstringBrowser if the conversation was started in a web browser, otherwise App (Mobile or Desktop).
metadataobjectChatGPT’s raw conversation payload, including the full mapping tree, which contains the conversation’s title and text. Currently present in every full record; planned to become debug-only.
is_summarybooleantrue on summary records; absent on full records.
passive-data-metadataobjectCapture context: source (participant ID), group, generator (record type, extension name and version, and browser user agent), generator-id, timestamp (seconds since 1970), timezone, configuration-hash, and encrypted_transmission.
FieldTypeMeaning
speakerstringuser, assistant, system, or tool, passed through from the upstream author.role.
whenISO timestampThe turn’s create time.
identifierstringChatGPT’s message ID for this turn.
content*stringTurn text. For multi-part messages, parts are joined with newlines. Subject to redaction via REX Content Processing.
parentstringIdentifier of the parent turn, or client-created-root for the synthetic root. Use these pointers to reconstruct the conversation tree (branches and regenerations).
metadata*objectRaw upstream node from the conversation’s mapping. Includes message.metadata.model_slug, search_result_groups, message.status, and children.
searchobjectPresent when the assistant’s turn triggered a web search. Carries platform, type, and a results array.
citationsarrayPresent when the assistant’s turn cited sources. Each citation has title, url, and source.

ChatGPT stores a conversation as a tree, not a flat list, so that branches (regenerations, edits to earlier turns) can coexist. The turns array is a pre-order traversal of that tree, so turns from abandoned branches appear alongside the “active” branch, and parent pointers are needed to distinguish them. For most analyses, start from the latest turn (by when) that has no children in its metadata*, then walk parent pointers back to the root. That gives you the branch the participant saw last.

Fields whose names end in * (content*, metadata*, query*) carry content that may include participant prompts, model responses, or upstream payloads that embed them. The REX Content Processing module can be configured to redact these fields before transmission. Fields without the * suffix (identifiers, timestamps, model slugs, URLs in citations) are not subject to that redaction pass.