mirror of
https://github.com/openai/codex.git
synced 2026-04-24 06:35:50 +00:00
- rework codex analytics crate to use reducer / publish architecture - in anticipation of extensive codex analytics
448 lines
14 KiB
Rust
448 lines
14 KiB
Rust
use super::AnalyticsEventsQueue;
|
|
use super::AnalyticsFact;
|
|
use super::AnalyticsReducer;
|
|
use super::AppInvocation;
|
|
use super::AppMentionedInput;
|
|
use super::AppUsedInput;
|
|
use super::CodexAppMentionedEventRequest;
|
|
use super::CodexAppUsedEventRequest;
|
|
use super::CodexPluginEventRequest;
|
|
use super::CodexPluginUsedEventRequest;
|
|
use super::CustomAnalyticsFact;
|
|
use super::InvocationType;
|
|
use super::PluginState;
|
|
use super::PluginStateChangedInput;
|
|
use super::PluginUsedInput;
|
|
use super::SkillInvocation;
|
|
use super::SkillInvokedInput;
|
|
use super::TrackEventRequest;
|
|
use super::TrackEventsContext;
|
|
use super::codex_app_metadata;
|
|
use super::codex_plugin_metadata;
|
|
use super::codex_plugin_used_metadata;
|
|
use super::normalize_path_for_skill_id;
|
|
use codex_login::default_client::originator;
|
|
use codex_plugin::AppConnectorId;
|
|
use codex_plugin::PluginCapabilitySummary;
|
|
use codex_plugin::PluginId;
|
|
use codex_plugin::PluginTelemetryMetadata;
|
|
use pretty_assertions::assert_eq;
|
|
use serde_json::json;
|
|
use std::collections::HashSet;
|
|
use std::path::PathBuf;
|
|
use std::sync::Arc;
|
|
use std::sync::Mutex;
|
|
use tokio::sync::mpsc;
|
|
|
|
fn expected_absolute_path(path: &PathBuf) -> String {
|
|
std::fs::canonicalize(path)
|
|
.unwrap_or_else(|_| path.to_path_buf())
|
|
.to_string_lossy()
|
|
.replace('\\', "/")
|
|
}
|
|
|
|
#[test]
|
|
fn normalize_path_for_skill_id_repo_scoped_uses_relative_path() {
|
|
let repo_root = PathBuf::from("/repo/root");
|
|
let skill_path = PathBuf::from("/repo/root/.codex/skills/doc/SKILL.md");
|
|
|
|
let path = normalize_path_for_skill_id(
|
|
Some("https://example.com/repo.git"),
|
|
Some(repo_root.as_path()),
|
|
skill_path.as_path(),
|
|
);
|
|
|
|
assert_eq!(path, ".codex/skills/doc/SKILL.md");
|
|
}
|
|
|
|
#[test]
|
|
fn normalize_path_for_skill_id_user_scoped_uses_absolute_path() {
|
|
let skill_path = PathBuf::from("/Users/abc/.codex/skills/doc/SKILL.md");
|
|
|
|
let path = normalize_path_for_skill_id(
|
|
/*repo_url*/ None,
|
|
/*repo_root*/ None,
|
|
skill_path.as_path(),
|
|
);
|
|
let expected = expected_absolute_path(&skill_path);
|
|
|
|
assert_eq!(path, expected);
|
|
}
|
|
|
|
#[test]
|
|
fn normalize_path_for_skill_id_admin_scoped_uses_absolute_path() {
|
|
let skill_path = PathBuf::from("/etc/codex/skills/doc/SKILL.md");
|
|
|
|
let path = normalize_path_for_skill_id(
|
|
/*repo_url*/ None,
|
|
/*repo_root*/ None,
|
|
skill_path.as_path(),
|
|
);
|
|
let expected = expected_absolute_path(&skill_path);
|
|
|
|
assert_eq!(path, expected);
|
|
}
|
|
|
|
#[test]
|
|
fn normalize_path_for_skill_id_repo_root_not_in_skill_path_uses_absolute_path() {
|
|
let repo_root = PathBuf::from("/repo/root");
|
|
let skill_path = PathBuf::from("/other/path/.codex/skills/doc/SKILL.md");
|
|
|
|
let path = normalize_path_for_skill_id(
|
|
Some("https://example.com/repo.git"),
|
|
Some(repo_root.as_path()),
|
|
skill_path.as_path(),
|
|
);
|
|
let expected = expected_absolute_path(&skill_path);
|
|
|
|
assert_eq!(path, expected);
|
|
}
|
|
|
|
#[test]
|
|
fn app_mentioned_event_serializes_expected_shape() {
|
|
let tracking = TrackEventsContext {
|
|
model_slug: "gpt-5".to_string(),
|
|
thread_id: "thread-1".to_string(),
|
|
turn_id: "turn-1".to_string(),
|
|
};
|
|
let event = TrackEventRequest::AppMentioned(CodexAppMentionedEventRequest {
|
|
event_type: "codex_app_mentioned",
|
|
event_params: codex_app_metadata(
|
|
&tracking,
|
|
AppInvocation {
|
|
connector_id: Some("calendar".to_string()),
|
|
app_name: Some("Calendar".to_string()),
|
|
invocation_type: Some(InvocationType::Explicit),
|
|
},
|
|
),
|
|
});
|
|
|
|
let payload = serde_json::to_value(&event).expect("serialize app mentioned event");
|
|
|
|
assert_eq!(
|
|
payload,
|
|
json!({
|
|
"event_type": "codex_app_mentioned",
|
|
"event_params": {
|
|
"connector_id": "calendar",
|
|
"thread_id": "thread-1",
|
|
"turn_id": "turn-1",
|
|
"app_name": "Calendar",
|
|
"product_client_id": originator().value,
|
|
"invoke_type": "explicit",
|
|
"model_slug": "gpt-5"
|
|
}
|
|
})
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn app_used_event_serializes_expected_shape() {
|
|
let tracking = TrackEventsContext {
|
|
model_slug: "gpt-5".to_string(),
|
|
thread_id: "thread-2".to_string(),
|
|
turn_id: "turn-2".to_string(),
|
|
};
|
|
let event = TrackEventRequest::AppUsed(CodexAppUsedEventRequest {
|
|
event_type: "codex_app_used",
|
|
event_params: codex_app_metadata(
|
|
&tracking,
|
|
AppInvocation {
|
|
connector_id: Some("drive".to_string()),
|
|
app_name: Some("Google Drive".to_string()),
|
|
invocation_type: Some(InvocationType::Implicit),
|
|
},
|
|
),
|
|
});
|
|
|
|
let payload = serde_json::to_value(&event).expect("serialize app used event");
|
|
|
|
assert_eq!(
|
|
payload,
|
|
json!({
|
|
"event_type": "codex_app_used",
|
|
"event_params": {
|
|
"connector_id": "drive",
|
|
"thread_id": "thread-2",
|
|
"turn_id": "turn-2",
|
|
"app_name": "Google Drive",
|
|
"product_client_id": originator().value,
|
|
"invoke_type": "implicit",
|
|
"model_slug": "gpt-5"
|
|
}
|
|
})
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn app_used_dedupe_is_keyed_by_turn_and_connector() {
|
|
let (sender, _receiver) = mpsc::channel(1);
|
|
let queue = AnalyticsEventsQueue {
|
|
sender,
|
|
app_used_emitted_keys: Arc::new(Mutex::new(HashSet::new())),
|
|
plugin_used_emitted_keys: Arc::new(Mutex::new(HashSet::new())),
|
|
};
|
|
let app = AppInvocation {
|
|
connector_id: Some("calendar".to_string()),
|
|
app_name: Some("Calendar".to_string()),
|
|
invocation_type: Some(InvocationType::Implicit),
|
|
};
|
|
|
|
let turn_1 = TrackEventsContext {
|
|
model_slug: "gpt-5".to_string(),
|
|
thread_id: "thread-1".to_string(),
|
|
turn_id: "turn-1".to_string(),
|
|
};
|
|
let turn_2 = TrackEventsContext {
|
|
model_slug: "gpt-5".to_string(),
|
|
thread_id: "thread-1".to_string(),
|
|
turn_id: "turn-2".to_string(),
|
|
};
|
|
|
|
assert_eq!(queue.should_enqueue_app_used(&turn_1, &app), true);
|
|
assert_eq!(queue.should_enqueue_app_used(&turn_1, &app), false);
|
|
assert_eq!(queue.should_enqueue_app_used(&turn_2, &app), true);
|
|
}
|
|
|
|
#[test]
|
|
fn plugin_used_event_serializes_expected_shape() {
|
|
let tracking = TrackEventsContext {
|
|
model_slug: "gpt-5".to_string(),
|
|
thread_id: "thread-3".to_string(),
|
|
turn_id: "turn-3".to_string(),
|
|
};
|
|
let event = TrackEventRequest::PluginUsed(CodexPluginUsedEventRequest {
|
|
event_type: "codex_plugin_used",
|
|
event_params: codex_plugin_used_metadata(&tracking, sample_plugin_metadata()),
|
|
});
|
|
|
|
let payload = serde_json::to_value(&event).expect("serialize plugin used event");
|
|
|
|
assert_eq!(
|
|
payload,
|
|
json!({
|
|
"event_type": "codex_plugin_used",
|
|
"event_params": {
|
|
"plugin_id": "sample@test",
|
|
"plugin_name": "sample",
|
|
"marketplace_name": "test",
|
|
"has_skills": true,
|
|
"mcp_server_count": 2,
|
|
"connector_ids": ["calendar", "drive"],
|
|
"product_client_id": originator().value,
|
|
"thread_id": "thread-3",
|
|
"turn_id": "turn-3",
|
|
"model_slug": "gpt-5"
|
|
}
|
|
})
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn plugin_management_event_serializes_expected_shape() {
|
|
let event = TrackEventRequest::PluginInstalled(CodexPluginEventRequest {
|
|
event_type: "codex_plugin_installed",
|
|
event_params: codex_plugin_metadata(sample_plugin_metadata()),
|
|
});
|
|
|
|
let payload = serde_json::to_value(&event).expect("serialize plugin installed event");
|
|
|
|
assert_eq!(
|
|
payload,
|
|
json!({
|
|
"event_type": "codex_plugin_installed",
|
|
"event_params": {
|
|
"plugin_id": "sample@test",
|
|
"plugin_name": "sample",
|
|
"marketplace_name": "test",
|
|
"has_skills": true,
|
|
"mcp_server_count": 2,
|
|
"connector_ids": ["calendar", "drive"],
|
|
"product_client_id": originator().value
|
|
}
|
|
})
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn plugin_used_dedupe_is_keyed_by_turn_and_plugin() {
|
|
let (sender, _receiver) = mpsc::channel(1);
|
|
let queue = AnalyticsEventsQueue {
|
|
sender,
|
|
app_used_emitted_keys: Arc::new(Mutex::new(HashSet::new())),
|
|
plugin_used_emitted_keys: Arc::new(Mutex::new(HashSet::new())),
|
|
};
|
|
let plugin = sample_plugin_metadata();
|
|
|
|
let turn_1 = TrackEventsContext {
|
|
model_slug: "gpt-5".to_string(),
|
|
thread_id: "thread-1".to_string(),
|
|
turn_id: "turn-1".to_string(),
|
|
};
|
|
let turn_2 = TrackEventsContext {
|
|
model_slug: "gpt-5".to_string(),
|
|
thread_id: "thread-1".to_string(),
|
|
turn_id: "turn-2".to_string(),
|
|
};
|
|
|
|
assert_eq!(queue.should_enqueue_plugin_used(&turn_1, &plugin), true);
|
|
assert_eq!(queue.should_enqueue_plugin_used(&turn_1, &plugin), false);
|
|
assert_eq!(queue.should_enqueue_plugin_used(&turn_2, &plugin), true);
|
|
}
|
|
|
|
#[tokio::test]
|
|
async fn reducer_ingests_skill_invoked_fact() {
|
|
let mut reducer = AnalyticsReducer;
|
|
let mut events = Vec::new();
|
|
let tracking = TrackEventsContext {
|
|
model_slug: "gpt-5".to_string(),
|
|
thread_id: "thread-1".to_string(),
|
|
turn_id: "turn-1".to_string(),
|
|
};
|
|
let skill_path = PathBuf::from("/Users/abc/.codex/skills/doc/SKILL.md");
|
|
let expected_skill_id = super::skill_id_for_local_skill(
|
|
/*repo_url*/ None,
|
|
/*repo_root*/ None,
|
|
skill_path.as_path(),
|
|
"doc",
|
|
);
|
|
|
|
reducer
|
|
.ingest(
|
|
AnalyticsFact::Custom(CustomAnalyticsFact::SkillInvoked(SkillInvokedInput {
|
|
tracking,
|
|
invocations: vec![SkillInvocation {
|
|
skill_name: "doc".to_string(),
|
|
skill_scope: codex_protocol::protocol::SkillScope::User,
|
|
skill_path,
|
|
invocation_type: InvocationType::Explicit,
|
|
}],
|
|
})),
|
|
&mut events,
|
|
)
|
|
.await;
|
|
|
|
let payload = serde_json::to_value(&events).expect("serialize events");
|
|
assert_eq!(
|
|
payload,
|
|
json!([{
|
|
"event_type": "skill_invocation",
|
|
"skill_id": expected_skill_id,
|
|
"skill_name": "doc",
|
|
"event_params": {
|
|
"product_client_id": originator().value,
|
|
"skill_scope": "user",
|
|
"repo_url": null,
|
|
"thread_id": "thread-1",
|
|
"invoke_type": "explicit",
|
|
"model_slug": "gpt-5"
|
|
}
|
|
}])
|
|
);
|
|
}
|
|
|
|
#[tokio::test]
|
|
async fn reducer_ingests_app_and_plugin_facts() {
|
|
let mut reducer = AnalyticsReducer;
|
|
let mut events = Vec::new();
|
|
let tracking = TrackEventsContext {
|
|
model_slug: "gpt-5".to_string(),
|
|
thread_id: "thread-1".to_string(),
|
|
turn_id: "turn-1".to_string(),
|
|
};
|
|
|
|
reducer
|
|
.ingest(
|
|
AnalyticsFact::Custom(CustomAnalyticsFact::AppMentioned(AppMentionedInput {
|
|
tracking: tracking.clone(),
|
|
mentions: vec![AppInvocation {
|
|
connector_id: Some("calendar".to_string()),
|
|
app_name: Some("Calendar".to_string()),
|
|
invocation_type: Some(InvocationType::Explicit),
|
|
}],
|
|
})),
|
|
&mut events,
|
|
)
|
|
.await;
|
|
reducer
|
|
.ingest(
|
|
AnalyticsFact::Custom(CustomAnalyticsFact::AppUsed(AppUsedInput {
|
|
tracking: tracking.clone(),
|
|
app: AppInvocation {
|
|
connector_id: Some("drive".to_string()),
|
|
app_name: Some("Drive".to_string()),
|
|
invocation_type: Some(InvocationType::Implicit),
|
|
},
|
|
})),
|
|
&mut events,
|
|
)
|
|
.await;
|
|
reducer
|
|
.ingest(
|
|
AnalyticsFact::Custom(CustomAnalyticsFact::PluginUsed(PluginUsedInput {
|
|
tracking,
|
|
plugin: sample_plugin_metadata(),
|
|
})),
|
|
&mut events,
|
|
)
|
|
.await;
|
|
|
|
let payload = serde_json::to_value(&events).expect("serialize events");
|
|
assert_eq!(payload.as_array().expect("events array").len(), 3);
|
|
assert_eq!(payload[0]["event_type"], "codex_app_mentioned");
|
|
assert_eq!(payload[1]["event_type"], "codex_app_used");
|
|
assert_eq!(payload[2]["event_type"], "codex_plugin_used");
|
|
}
|
|
|
|
#[tokio::test]
|
|
async fn reducer_ingests_plugin_state_changed_fact() {
|
|
let mut reducer = AnalyticsReducer;
|
|
let mut events = Vec::new();
|
|
|
|
reducer
|
|
.ingest(
|
|
AnalyticsFact::Custom(CustomAnalyticsFact::PluginStateChanged(
|
|
PluginStateChangedInput {
|
|
plugin: sample_plugin_metadata(),
|
|
state: PluginState::Disabled,
|
|
},
|
|
)),
|
|
&mut events,
|
|
)
|
|
.await;
|
|
|
|
let payload = serde_json::to_value(&events).expect("serialize events");
|
|
assert_eq!(
|
|
payload,
|
|
json!([{
|
|
"event_type": "codex_plugin_disabled",
|
|
"event_params": {
|
|
"plugin_id": "sample@test",
|
|
"plugin_name": "sample",
|
|
"marketplace_name": "test",
|
|
"has_skills": true,
|
|
"mcp_server_count": 2,
|
|
"connector_ids": ["calendar", "drive"],
|
|
"product_client_id": originator().value
|
|
}
|
|
}])
|
|
);
|
|
}
|
|
|
|
fn sample_plugin_metadata() -> PluginTelemetryMetadata {
|
|
PluginTelemetryMetadata {
|
|
plugin_id: PluginId::parse("sample@test").expect("valid plugin id"),
|
|
capability_summary: Some(PluginCapabilitySummary {
|
|
config_name: "sample@test".to_string(),
|
|
display_name: "sample".to_string(),
|
|
description: None,
|
|
has_skills: true,
|
|
mcp_server_names: vec!["mcp-1".to_string(), "mcp-2".to_string()],
|
|
app_connector_ids: vec![
|
|
AppConnectorId("calendar".to_string()),
|
|
AppConnectorId("drive".to_string()),
|
|
],
|
|
}),
|
|
}
|
|
}
|