[codex-analytics] rework thread_source for thread analytics (#20949)

## Summary
- make `thread_source` an explicit optional thread-level field on
`thread/start`, `thread/fork`, and returned thread payloads
- persist `thread_source` in rollout/session metadata so resumed live
threads retain the original value
- replace the old best-effort `session_source` -> `thread_source`
mapping with an explicit caller-supplied analytics classification

## Why
Before this change, analytics `thread_source` was populated by a
best-effort mapping from `session_source`. `session_source` describes
the runtime/client surface, not the actual thread-level origin, so that
projection was not accurate enough to distinguish cases such as `user`,
`subagent`, `memory_consolidation`, and future thread origins reliably.

Making `thread_source` explicit keeps one thread-level analytics field
while letting callers provide the real classification directly instead
of recovering it indirectly from `session_source`.

## Impact
For new analytics events, `thread_source` now reflects the explicit
thread-level classification supplied by the caller rather than an
inferred value derived from `session_source`. Existing protocol fields
remain optional; callers that omit `threadSource` now produce `null`
instead of a best-effort inferred value.

## Validation
- `just write-app-server-schema`
- `cargo test -p codex-analytics -p codex-core -p
codex-app-server-protocol --no-run`
- `cargo test -p codex-app-server-protocol
generated_ts_optional_nullable_fields_only_in_params`
- `cargo test -p codex-analytics
thread_initialized_event_serializes_expected_shape`
- `cargo test -p codex-core
resume_stopped_thread_from_rollout_preserves_thread_source`
This commit is contained in:
rhan-oai
2026-05-06 02:12:31 +00:00
committed by GitHub
parent 94db03d5af
commit b3d4f1a9f0
98 changed files with 896 additions and 90 deletions
@@ -3558,6 +3558,17 @@
},
"threadId": {
"type": "string"
},
"threadSource": {
"anyOf": [
{
"$ref": "#/definitions/ThreadSource"
},
{
"type": "null"
}
],
"description": "Optional client-supplied analytics source classification for this forked thread."
}
},
"required": [
@@ -4032,6 +4043,14 @@
],
"type": "string"
},
"ThreadSource": {
"enum": [
"user",
"subagent",
"memory_consolidation"
],
"type": "string"
},
"ThreadSourceKind": {
"enum": [
"cli",
@@ -4165,6 +4184,17 @@
"type": "null"
}
]
},
"threadSource": {
"anyOf": [
{
"$ref": "#/definitions/ThreadSource"
},
{
"type": "null"
}
],
"description": "Optional client-supplied analytics source classification for this thread."
}
},
"type": "object"
@@ -3088,6 +3088,17 @@
],
"description": "Current runtime status for the thread."
},
"threadSource": {
"anyOf": [
{
"$ref": "#/definitions/ThreadSource"
},
{
"type": "null"
}
],
"description": "Optional analytics source classification for this thread."
},
"turns": {
"description": "Only populated on `thread/resume`, `thread/rollback`, `thread/fork`, and `thread/read` (when `includeTurns` is true) responses. For all other responses and notifications returning a Thread, the turns field will be an empty list.",
"items": {
@@ -4094,6 +4105,14 @@
],
"type": "object"
},
"ThreadSource": {
"enum": [
"user",
"subagent",
"memory_consolidation"
],
"type": "string"
},
"ThreadStartedNotification": {
"properties": {
"thread": {
@@ -15232,6 +15232,17 @@
],
"description": "Current runtime status for the thread."
},
"threadSource": {
"anyOf": [
{
"$ref": "#/definitions/v2/ThreadSource"
},
{
"type": "null"
}
],
"description": "Optional analytics source classification for this thread."
},
"turns": {
"description": "Only populated on `thread/resume`, `thread/rollback`, `thread/fork`, and `thread/read` (when `includeTurns` is true) responses. For all other responses and notifications returning a Thread, the turns field will be an empty list.",
"items": {
@@ -15446,6 +15457,17 @@
},
"threadId": {
"type": "string"
},
"threadSource": {
"anyOf": [
{
"$ref": "#/definitions/v2/ThreadSource"
},
{
"type": "null"
}
],
"description": "Optional client-supplied analytics source classification for this forked thread."
}
},
"required": [
@@ -17126,6 +17148,14 @@
],
"type": "string"
},
"ThreadSource": {
"enum": [
"user",
"subagent",
"memory_consolidation"
],
"type": "string"
},
"ThreadSourceKind": {
"enum": [
"cli",
@@ -17260,6 +17290,17 @@
"type": "null"
}
]
},
"threadSource": {
"anyOf": [
{
"$ref": "#/definitions/v2/ThreadSource"
},
{
"type": "null"
}
],
"description": "Optional client-supplied analytics source classification for this thread."
}
},
"title": "ThreadStartParams",
@@ -13118,6 +13118,17 @@
],
"description": "Current runtime status for the thread."
},
"threadSource": {
"anyOf": [
{
"$ref": "#/definitions/ThreadSource"
},
{
"type": "null"
}
],
"description": "Optional analytics source classification for this thread."
},
"turns": {
"description": "Only populated on `thread/resume`, `thread/rollback`, `thread/fork`, and `thread/read` (when `includeTurns` is true) responses. For all other responses and notifications returning a Thread, the turns field will be an empty list.",
"items": {
@@ -13332,6 +13343,17 @@
},
"threadId": {
"type": "string"
},
"threadSource": {
"anyOf": [
{
"$ref": "#/definitions/ThreadSource"
},
{
"type": "null"
}
],
"description": "Optional client-supplied analytics source classification for this forked thread."
}
},
"required": [
@@ -15012,6 +15034,14 @@
],
"type": "string"
},
"ThreadSource": {
"enum": [
"user",
"subagent",
"memory_consolidation"
],
"type": "string"
},
"ThreadSourceKind": {
"enum": [
"cli",
@@ -15146,6 +15176,17 @@
"type": "null"
}
]
},
"threadSource": {
"anyOf": [
{
"$ref": "#/definitions/ThreadSource"
},
{
"type": "null"
}
],
"description": "Optional client-supplied analytics source classification for this thread."
}
},
"title": "ThreadStartParams",
@@ -137,6 +137,14 @@
"flex"
],
"type": "string"
},
"ThreadSource": {
"enum": [
"user",
"subagent",
"memory_consolidation"
],
"type": "string"
}
},
"description": "There are two ways to fork a thread: 1. By thread_id: load the thread from disk by thread_id and fork it into a new thread. 2. By path: load the thread from disk by path and fork it into a new thread.\n\nIf using path, the thread_id param will be ignored.\n\nPrefer using thread_id whenever possible.",
@@ -232,6 +240,17 @@
},
"threadId": {
"type": "string"
},
"threadSource": {
"anyOf": [
{
"$ref": "#/definitions/ThreadSource"
},
{
"type": "null"
}
],
"description": "Optional client-supplied analytics source classification for this forked thread."
}
},
"required": [
@@ -1419,6 +1419,17 @@
],
"description": "Current runtime status for the thread."
},
"threadSource": {
"anyOf": [
{
"$ref": "#/definitions/ThreadSource"
},
{
"type": "null"
}
],
"description": "Optional analytics source classification for this thread."
},
"turns": {
"description": "Only populated on `thread/resume`, `thread/rollback`, `thread/fork`, and `thread/read` (when `includeTurns` is true) responses. For all other responses and notifications returning a Thread, the turns field will be an empty list.",
"items": {
@@ -2117,6 +2128,14 @@
}
]
},
"ThreadSource": {
"enum": [
"user",
"subagent",
"memory_consolidation"
],
"type": "string"
},
"ThreadStatus": {
"oneOf": [
{
@@ -869,6 +869,17 @@
],
"description": "Current runtime status for the thread."
},
"threadSource": {
"anyOf": [
{
"$ref": "#/definitions/ThreadSource"
},
{
"type": "null"
}
],
"description": "Optional analytics source classification for this thread."
},
"turns": {
"description": "Only populated on `thread/resume`, `thread/rollback`, `thread/fork`, and `thread/read` (when `includeTurns` is true) responses. For all other responses and notifications returning a Thread, the turns field will be an empty list.",
"items": {
@@ -1567,6 +1578,14 @@
}
]
},
"ThreadSource": {
"enum": [
"user",
"subagent",
"memory_consolidation"
],
"type": "string"
},
"ThreadStatus": {
"oneOf": [
{
@@ -869,6 +869,17 @@
],
"description": "Current runtime status for the thread."
},
"threadSource": {
"anyOf": [
{
"$ref": "#/definitions/ThreadSource"
},
{
"type": "null"
}
],
"description": "Optional analytics source classification for this thread."
},
"turns": {
"description": "Only populated on `thread/resume`, `thread/rollback`, `thread/fork`, and `thread/read` (when `includeTurns` is true) responses. For all other responses and notifications returning a Thread, the turns field will be an empty list.",
"items": {
@@ -1567,6 +1578,14 @@
}
]
},
"ThreadSource": {
"enum": [
"user",
"subagent",
"memory_consolidation"
],
"type": "string"
},
"ThreadStatus": {
"oneOf": [
{
@@ -869,6 +869,17 @@
],
"description": "Current runtime status for the thread."
},
"threadSource": {
"anyOf": [
{
"$ref": "#/definitions/ThreadSource"
},
{
"type": "null"
}
],
"description": "Optional analytics source classification for this thread."
},
"turns": {
"description": "Only populated on `thread/resume`, `thread/rollback`, `thread/fork`, and `thread/read` (when `includeTurns` is true) responses. For all other responses and notifications returning a Thread, the turns field will be an empty list.",
"items": {
@@ -1567,6 +1578,14 @@
}
]
},
"ThreadSource": {
"enum": [
"user",
"subagent",
"memory_consolidation"
],
"type": "string"
},
"ThreadStatus": {
"oneOf": [
{
@@ -1419,6 +1419,17 @@
],
"description": "Current runtime status for the thread."
},
"threadSource": {
"anyOf": [
{
"$ref": "#/definitions/ThreadSource"
},
{
"type": "null"
}
],
"description": "Optional analytics source classification for this thread."
},
"turns": {
"description": "Only populated on `thread/resume`, `thread/rollback`, `thread/fork`, and `thread/read` (when `includeTurns` is true) responses. For all other responses and notifications returning a Thread, the turns field will be an empty list.",
"items": {
@@ -2117,6 +2128,14 @@
}
]
},
"ThreadSource": {
"enum": [
"user",
"subagent",
"memory_consolidation"
],
"type": "string"
},
"ThreadStatus": {
"oneOf": [
{
@@ -869,6 +869,17 @@
],
"description": "Current runtime status for the thread."
},
"threadSource": {
"anyOf": [
{
"$ref": "#/definitions/ThreadSource"
},
{
"type": "null"
}
],
"description": "Optional analytics source classification for this thread."
},
"turns": {
"description": "Only populated on `thread/resume`, `thread/rollback`, `thread/fork`, and `thread/read` (when `includeTurns` is true) responses. For all other responses and notifications returning a Thread, the turns field will be an empty list.",
"items": {
@@ -1567,6 +1578,14 @@
}
]
},
"ThreadSource": {
"enum": [
"user",
"subagent",
"memory_consolidation"
],
"type": "string"
},
"ThreadStatus": {
"oneOf": [
{
@@ -172,6 +172,14 @@
],
"type": "string"
},
"ThreadSource": {
"enum": [
"user",
"subagent",
"memory_consolidation"
],
"type": "string"
},
"ThreadStartSource": {
"enum": [
"startup",
@@ -312,6 +320,17 @@
"type": "null"
}
]
},
"threadSource": {
"anyOf": [
{
"$ref": "#/definitions/ThreadSource"
},
{
"type": "null"
}
],
"description": "Optional client-supplied analytics source classification for this thread."
}
},
"title": "ThreadStartParams",
@@ -1419,6 +1419,17 @@
],
"description": "Current runtime status for the thread."
},
"threadSource": {
"anyOf": [
{
"$ref": "#/definitions/ThreadSource"
},
{
"type": "null"
}
],
"description": "Optional analytics source classification for this thread."
},
"turns": {
"description": "Only populated on `thread/resume`, `thread/rollback`, `thread/fork`, and `thread/read` (when `includeTurns` is true) responses. For all other responses and notifications returning a Thread, the turns field will be an empty list.",
"items": {
@@ -2117,6 +2128,14 @@
}
]
},
"ThreadSource": {
"enum": [
"user",
"subagent",
"memory_consolidation"
],
"type": "string"
},
"ThreadStatus": {
"oneOf": [
{
@@ -869,6 +869,17 @@
],
"description": "Current runtime status for the thread."
},
"threadSource": {
"anyOf": [
{
"$ref": "#/definitions/ThreadSource"
},
{
"type": "null"
}
],
"description": "Optional analytics source classification for this thread."
},
"turns": {
"description": "Only populated on `thread/resume`, `thread/rollback`, `thread/fork`, and `thread/read` (when `includeTurns` is true) responses. For all other responses and notifications returning a Thread, the turns field will be an empty list.",
"items": {
@@ -1567,6 +1578,14 @@
}
]
},
"ThreadSource": {
"enum": [
"user",
"subagent",
"memory_consolidation"
],
"type": "string"
},
"ThreadStatus": {
"oneOf": [
{
@@ -869,6 +869,17 @@
],
"description": "Current runtime status for the thread."
},
"threadSource": {
"anyOf": [
{
"$ref": "#/definitions/ThreadSource"
},
{
"type": "null"
}
],
"description": "Optional analytics source classification for this thread."
},
"turns": {
"description": "Only populated on `thread/resume`, `thread/rollback`, `thread/fork`, and `thread/read` (when `includeTurns` is true) responses. For all other responses and notifications returning a Thread, the turns field will be an empty list.",
"items": {
@@ -1567,6 +1578,14 @@
}
]
},
"ThreadSource": {
"enum": [
"user",
"subagent",
"memory_consolidation"
],
"type": "string"
},
"ThreadStatus": {
"oneOf": [
{
@@ -4,6 +4,7 @@
import type { AbsolutePathBuf } from "../AbsolutePathBuf";
import type { GitInfo } from "./GitInfo";
import type { SessionSource } from "./SessionSource";
import type { ThreadSource } from "./ThreadSource";
import type { ThreadStatus } from "./ThreadStatus";
import type { Turn } from "./Turn";
@@ -52,6 +53,10 @@ cliVersion: string,
* Origin of the thread (CLI, VSCode, codex exec, codex app-server, etc.).
*/
source: SessionSource,
/**
* Optional analytics source classification for this thread.
*/
threadSource: ThreadSource | null,
/**
* Optional random unique nickname assigned to an AgentControl-spawned sub-agent.
*/
@@ -6,6 +6,7 @@ import type { JsonValue } from "../serde_json/JsonValue";
import type { ApprovalsReviewer } from "./ApprovalsReviewer";
import type { AskForApproval } from "./AskForApproval";
import type { SandboxMode } from "./SandboxMode";
import type { ThreadSource } from "./ThreadSource";
/**
* There are two ways to fork a thread:
@@ -23,4 +24,7 @@ model?: string | null, modelProvider?: string | null, serviceTier?: ServiceTier
* Override where approval requests are routed for review on this thread
* and subsequent turns.
*/
approvalsReviewer?: ApprovalsReviewer | null, sandbox?: SandboxMode | null, config?: { [key in string]?: JsonValue } | null, baseInstructions?: string | null, developerInstructions?: string | null, ephemeral?: boolean};
approvalsReviewer?: ApprovalsReviewer | null, sandbox?: SandboxMode | null, config?: { [key in string]?: JsonValue } | null, baseInstructions?: string | null, developerInstructions?: string | null, ephemeral?: boolean, /**
* Optional client-supplied analytics source classification for this forked thread.
*/
threadSource?: ThreadSource | null};
@@ -0,0 +1,5 @@
// GENERATED CODE! DO NOT MODIFY BY HAND!
// This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
export type ThreadSource = "user" | "subagent" | "memory_consolidation";
@@ -7,10 +7,14 @@ import type { JsonValue } from "../serde_json/JsonValue";
import type { ApprovalsReviewer } from "./ApprovalsReviewer";
import type { AskForApproval } from "./AskForApproval";
import type { SandboxMode } from "./SandboxMode";
import type { ThreadSource } from "./ThreadSource";
import type { ThreadStartSource } from "./ThreadStartSource";
export type ThreadStartParams = {model?: string | null, modelProvider?: string | null, serviceTier?: ServiceTier | null | null, cwd?: string | null, approvalPolicy?: AskForApproval | null, /**
* Override where approval requests are routed for review on this thread
* and subsequent turns.
*/
approvalsReviewer?: ApprovalsReviewer | null, sandbox?: SandboxMode | null, config?: { [key in string]?: JsonValue } | null, serviceName?: string | null, baseInstructions?: string | null, developerInstructions?: string | null, personality?: Personality | null, ephemeral?: boolean | null, sessionStartSource?: ThreadStartSource | null};
approvalsReviewer?: ApprovalsReviewer | null, sandbox?: SandboxMode | null, config?: { [key in string]?: JsonValue } | null, serviceName?: string | null, baseInstructions?: string | null, developerInstructions?: string | null, personality?: Personality | null, ephemeral?: boolean | null, sessionStartSource?: ThreadStartSource | null, /**
* Optional client-supplied analytics source classification for this thread.
*/
threadSource?: ThreadSource | null};
@@ -396,6 +396,7 @@ export type { ThreadSetNameResponse } from "./ThreadSetNameResponse";
export type { ThreadShellCommandParams } from "./ThreadShellCommandParams";
export type { ThreadShellCommandResponse } from "./ThreadShellCommandResponse";
export type { ThreadSortKey } from "./ThreadSortKey";
export type { ThreadSource } from "./ThreadSource";
export type { ThreadSourceKind } from "./ThreadSourceKind";
export type { ThreadStartParams } from "./ThreadStartParams";
export type { ThreadStartResponse } from "./ThreadStartResponse";
@@ -2184,6 +2184,7 @@ mod tests {
cwd: cwd.clone(),
cli_version: "0.0.0".to_string(),
source: v2::SessionSource::Exec,
thread_source: None,
agent_nickname: None,
agent_role: None,
git_info: None,
@@ -2226,6 +2227,7 @@ mod tests {
"cwd": absolute_path_string("tmp"),
"cliVersion": "0.0.0",
"source": "exec",
"threadSource": null,
"agentNickname": null,
"agentRole": null,
"gitInfo": null,
@@ -6,6 +6,7 @@ use super::PermissionProfileSelectionParams;
use super::SandboxMode;
use super::SandboxPolicy;
use super::Thread;
use super::ThreadSource;
use super::Turn;
use super::TurnEnvironmentParams;
use super::shared::v2_enum_from_core;
@@ -134,6 +135,9 @@ pub struct ThreadStartParams {
pub ephemeral: Option<bool>,
#[ts(optional = nullable)]
pub session_start_source: Option<ThreadStartSource>,
/// Optional client-supplied analytics source classification for this thread.
#[ts(optional = nullable)]
pub thread_source: Option<ThreadSource>,
/// Optional sticky environments for this thread.
///
/// Omitted selects the default environment when environment access is
@@ -388,6 +392,9 @@ pub struct ThreadForkParams {
pub developer_instructions: Option<String>,
#[serde(default, skip_serializing_if = "std::ops::Not::not")]
pub ephemeral: bool,
/// Optional client-supplied analytics source classification for this forked thread.
#[ts(optional = nullable)]
pub thread_source: Option<ThreadSource>,
/// When true, return only thread metadata and live fork state without
/// populating `thread.turns`. This is useful when the client plans to call
/// `thread/turns/list` immediately after forking.
@@ -4,6 +4,7 @@ use super::ThreadStatus;
use super::TurnStatus;
use codex_protocol::protocol::SessionSource as CoreSessionSource;
use codex_protocol::protocol::SubAgentSource as CoreSubAgentSource;
use codex_protocol::protocol::ThreadSource as CoreThreadSource;
use codex_utils_absolute_path::AbsolutePathBuf;
use schemars::JsonSchema;
use serde::Deserialize;
@@ -60,6 +61,35 @@ impl From<SessionSource> for CoreSessionSource {
}
}
#[derive(Serialize, Deserialize, Debug, Clone, Copy, PartialEq, Eq, JsonSchema, TS)]
#[serde(rename_all = "snake_case")]
#[ts(rename_all = "snake_case", export_to = "v2/")]
pub enum ThreadSource {
User,
Subagent,
MemoryConsolidation,
}
impl From<CoreThreadSource> for ThreadSource {
fn from(value: CoreThreadSource) -> Self {
match value {
CoreThreadSource::User => ThreadSource::User,
CoreThreadSource::Subagent => ThreadSource::Subagent,
CoreThreadSource::MemoryConsolidation => ThreadSource::MemoryConsolidation,
}
}
}
impl From<ThreadSource> for CoreThreadSource {
fn from(value: ThreadSource) -> Self {
match value {
ThreadSource::User => CoreThreadSource::User,
ThreadSource::Subagent => CoreThreadSource::Subagent,
ThreadSource::MemoryConsolidation => CoreThreadSource::MemoryConsolidation,
}
}
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq, JsonSchema, TS)]
#[serde(rename_all = "camelCase")]
#[ts(export_to = "v2/")]
@@ -98,6 +128,8 @@ pub struct Thread {
pub cli_version: String,
/// Origin of the thread (CLI, VSCode, codex exec, codex app-server, etc.).
pub source: SessionSource,
/// Optional analytics source classification for this thread.
pub thread_source: Option<ThreadSource>,
/// Optional random unique nickname assigned to an AgentControl-spawned sub-agent.
pub agent_nickname: Option<String>,
/// Optional role (agent_role) assigned to an AgentControl-spawned sub-agent.