Emit accepted line fingerprint analytics (#21601)

## Why

Codex assisted-code attribution needs a client-side accepted-code source
that does not upload raw code. This adds a hash-only analytics event
derived from the turn diff so downstream attribution can compare
accepted Codex lines against commit or PR diffs.

## What Changed

- Parse accepted/effective added lines from the final turn diff and emit
`codex_accepted_line_fingerprints` analytics.
- Hash repo, path, and normalized line content before upload; raw code
and raw diffs are not included in the event.
- Chunk large fingerprint payloads and send accepted-line fingerprint
events in isolated requests while preserving normal batching for other
analytics events.
- Canonicalize Git remote URLs before repo hashing so SSH/HTTPS GitHub
remotes join to the same repo hash.
- Add parser coverage for unified diff hunk lines that look like `+++`
or `---` file headers.

## Verification

- `cargo test -p codex-analytics`
- `cargo test -p codex-git-utils canonicalize_git_remote_url`
- `just fix -p codex-analytics`
- `just bazel-lock-check`
- `git diff --check`
This commit is contained in:
alexsong-oai authored and GitHub committed 2026-05-08 12:16:24 -07:00
1 parent 9183503b97
commit bbb6bf0a37
10 files changed
+882 -27

No files matched your search

+69
View File
@@ -1,6 +1,14 @@
use super::AnalyticsEventsClient;
use super::AnalyticsEventsQueue;
use super::track_event_request_batches;
use crate::events::CodexAcceptedLineFingerprintsEventParams;
use crate::events::CodexAcceptedLineFingerprintsEventRequest;
use crate::events::SkillInvocationEventParams;
use crate::events::SkillInvocationEventRequest;
use crate::events::TrackEventRequest;
use crate::facts::AcceptedLineFingerprint;
use crate::facts::AnalyticsFact;
use crate::facts::InvocationType;
use codex_app_server_protocol::ApprovalsReviewer as AppServerApprovalsReviewer;
use codex_app_server_protocol::AskForApproval as AppServerAskForApproval;
use codex_app_server_protocol::ClientRequest;
@@ -31,6 +39,47 @@ use std::sync::Mutex;
use tokio::sync::mpsc;
use tokio::sync::mpsc::error::TryRecvError;
fn sample_accepted_line_fingerprint_event(thread_id: &str) -> TrackEventRequest {
TrackEventRequest::AcceptedLineFingerprints(Box::new(
CodexAcceptedLineFingerprintsEventRequest {
event_type: "codex_accepted_line_fingerprints",
event_params: CodexAcceptedLineFingerprintsEventParams {
event_type: "codex.accepted_line_fingerprints",
turn_id: "turn-1".to_string(),
thread_id: thread_id.to_string(),
product_surface: Some("codex".to_string()),
model_slug: Some("gpt-5.1-codex".to_string()),
completed_at: 1,
repo_hash: None,
accepted_added_lines: 1,
accepted_deleted_lines: 0,
line_fingerprints: vec![AcceptedLineFingerprint {
path_hash: "path-hash".to_string(),
line_hash: "line-hash".to_string(),
}],
},
},
))
}
fn sample_regular_track_event(thread_id: &str) -> TrackEventRequest {
TrackEventRequest::SkillInvocation(SkillInvocationEventRequest {
event_type: "skill_invocation",
skill_id: format!("skill-{thread_id}"),
skill_name: "doc".to_string(),
event_params: SkillInvocationEventParams {
product_client_id: None,
skill_scope: None,
plugin_id: None,
repo_url: None,
thread_id: Some(thread_id.to_string()),
turn_id: Some("turn-1".to_string()),
invoke_type: Some(InvocationType::Explicit),
model_slug: Some("gpt-5.1-codex".to_string()),
},
})
}
fn client_with_receiver() -> (AnalyticsEventsClient, mpsc::Receiver<AnalyticsFact>) {
let (sender, receiver) = mpsc::channel(8);
let queue = AnalyticsEventsQueue {
@@ -222,3 +271,23 @@ fn track_response_only_enqueues_analytics_relevant_responses() {
);
assert!(matches!(receiver.try_recv(), Err(TryRecvError::Empty)));
}
#[test]
fn track_event_request_batches_only_isolates_accepted_line_fingerprint_events() {
let batches = track_event_request_batches(vec![
sample_regular_track_event("thread-1"),
sample_regular_track_event("thread-2"),
sample_accepted_line_fingerprint_event("thread-3"),
sample_accepted_line_fingerprint_event("thread-4"),
sample_regular_track_event("thread-5"),
sample_regular_track_event("thread-6"),
]);
assert_eq!(batches.len(), 4);
assert_eq!(batches[0].len(), 2);
assert_eq!(batches[1].len(), 1);
assert_eq!(batches[2].len(), 1);
assert_eq!(batches[3].len(), 2);
assert!(batches[1][0].should_send_in_isolated_request());
assert!(batches[2][0].should_send_in_isolated_request());
}