mirror of
https://github.com/pchuan98/codex.git
synced 2026-07-01 00:31:56 +08:00
[codex] Add turn profiling analytics (#26484)
## Summary Add flat profiling fields to `codex_turn_event` so analytics can explain where turn wall-clock time is spent without changing tool execution behavior. The profile reports: - time before the first sampling request - sampling time across all attempts and follow-ups - overhead between sampling requests - time blocked in the post-sampling tool drain - time after the final sampling request - sampling request and retry counts ## Implementation - Extend the existing turn timing state with constant-memory phase accounting and one RAII phase guard. - Observe sampling and the existing post-sampling drain only at turn orchestration boundaries. - Keep tool runtime, tool futures, response item handling, and turn lifecycle values unchanged. - Add the profiling fields directly to the existing analytics turn event without changing app-server protocol or rollout persistence. - Use the existing turn `status` to distinguish completed, failed, and interrupted profiles. Exact sampling/tool overlap is intentionally omitted because measuring tool completion accurately would require hooks in the tool execution path. ## Validation - Add app-server end-to-end coverage for a single-sampling turn with no blocking tool work. - Add app-server end-to-end coverage for `request_user_input` blocking followed by a second sampling request. - CI is running on the PR; tests were not executed locally per repository guidance.
This commit is contained in:
@@ -63,6 +63,8 @@ use crate::facts::SubAgentThreadStartedInput;
|
||||
use crate::facts::ThreadInitializationMode;
|
||||
use crate::facts::TrackEventsContext;
|
||||
use crate::facts::TurnCodexErrorFact;
|
||||
use crate::facts::TurnProfile;
|
||||
use crate::facts::TurnProfileFact;
|
||||
use crate::facts::TurnResolvedConfigFact;
|
||||
use crate::facts::TurnStatus;
|
||||
use crate::facts::TurnSteerRequestError;
|
||||
@@ -396,6 +398,18 @@ fn sample_turn_resolved_config(thread_id: &str, turn_id: &str) -> TurnResolvedCo
|
||||
}
|
||||
}
|
||||
|
||||
fn sample_turn_profile() -> TurnProfile {
|
||||
TurnProfile {
|
||||
before_first_sampling_ms: 100,
|
||||
sampling_ms: 700,
|
||||
between_sampling_overhead_ms: 50,
|
||||
tool_blocking_ms: 250,
|
||||
after_last_sampling_ms: 134,
|
||||
sampling_request_count: 2,
|
||||
sampling_retry_count: 1,
|
||||
}
|
||||
}
|
||||
|
||||
fn sample_turn_steer_request(
|
||||
thread_id: &str,
|
||||
expected_turn_id: &str,
|
||||
@@ -649,6 +663,18 @@ async fn ingest_turn_prerequisites(
|
||||
)
|
||||
.await;
|
||||
}
|
||||
|
||||
reducer
|
||||
.ingest(
|
||||
AnalyticsFact::Custom(CustomAnalyticsFact::TurnProfile(Box::new(
|
||||
TurnProfileFact {
|
||||
turn_id: "turn-2".to_string(),
|
||||
profile: sample_turn_profile(),
|
||||
},
|
||||
))),
|
||||
out,
|
||||
)
|
||||
.await;
|
||||
}
|
||||
|
||||
async fn ingest_review_prerequisites(
|
||||
@@ -3300,6 +3326,13 @@ fn turn_event_serializes_expected_shape() {
|
||||
output_tokens: None,
|
||||
reasoning_output_tokens: None,
|
||||
total_tokens: None,
|
||||
before_first_sampling_ms: 100,
|
||||
sampling_ms: 700,
|
||||
between_sampling_overhead_ms: 50,
|
||||
tool_blocking_ms: 250,
|
||||
after_last_sampling_ms: 134,
|
||||
sampling_request_count: 2,
|
||||
sampling_retry_count: 1,
|
||||
duration_ms: Some(1234),
|
||||
started_at: Some(455),
|
||||
completed_at: Some(456),
|
||||
@@ -3366,6 +3399,13 @@ fn turn_event_serializes_expected_shape() {
|
||||
"output_tokens": null,
|
||||
"reasoning_output_tokens": null,
|
||||
"total_tokens": null,
|
||||
"before_first_sampling_ms": 100,
|
||||
"sampling_ms": 700,
|
||||
"between_sampling_overhead_ms": 50,
|
||||
"tool_blocking_ms": 250,
|
||||
"after_last_sampling_ms": 134,
|
||||
"sampling_request_count": 2,
|
||||
"sampling_retry_count": 1,
|
||||
"duration_ms": 1234,
|
||||
"started_at": 455,
|
||||
"completed_at": 456
|
||||
|
||||
Reference in New Issue
Block a user