From 99ba5b11205a3ec73d91a2ec655607ffeac85f0f Mon Sep 17 00:00:00 2001 From: Zyy Date: Sun, 18 Oct 2026 16:32:15 +0800 Subject: [PATCH] fix(openai): align request ordering and simplify timing metrics Preserve response.create field order and align OAuth query ordering with current official Codex sources. Stop adding the timing-metrics request header by default and remove the four unused engine TTFT and token interval fields throughout the backend, plugin observation contracts, and frontend. Keep rate calculations unchanged. Co-authored-by: Codex --- .../gateway-admin/src/model/observability.rs | 8 ---- .../tests/use_case/observability/mod.rs | 4 -- .../src/admin/observability/presenter.rs | 8 ---- .../src/admin/observability/wire.rs | 8 ---- .../gateway-api/src/key_usage/presenter.rs | 12 ------ .../openai/responses/websocket/protocol.rs | 3 +- .../tests/admin/observability/response.rs | 28 ------------- .../gateway-api/tests/key_usage/fixtures.rs | 6 +-- .../crates/gateway-api/tests/key_usage/mod.rs | 7 +--- .../openai/responses/websocket/protocol.rs | 20 +++++++++ backend/crates/gateway-core/src/engine/mod.rs | 4 -- .../gateway-core/src/engine/observation.rs | 16 -------- backend/crates/gateway-core/src/event.rs | 6 +-- .../gateway-core/tests/engine/coordinator.rs | 18 -------- .../runtime/src/adapter/observer.rs | 4 -- .../runtime/src/callback/facts.rs | 4 -- .../runtime/tests/generation/observer.rs | 7 +--- .../tests/generation/policy/facts/mod.rs | 4 +- .../sdk/src/call/observation.rs | 8 ---- .../sdk/tests/call/observation.rs | 4 +- .../postgres/execution/request_observation.rs | 25 ++--------- .../src/postgres/observability/mapping.rs | 8 ---- .../postgres/observability/queries/usage.rs | 4 +- .../tests/postgres/execution/mod.rs | 22 +--------- .../tests/postgres/observability/mod.rs | 4 +- .../providers/openai/src/credential/oauth.rs | 4 +- .../openai/src/provider/observation.rs | 12 ------ .../providers/openai/src/transport/headers.rs | 6 --- .../src/transport/protocol/responses.rs | 27 ------------ .../openai/tests/credential/oauth.rs | 4 +- .../openai/tests/provider/contract/timing.rs | 41 ++++--------------- .../tests/transport/websocket/fingerprint.rs | 8 ++-- docs/api.md | 6 +-- frontend/src/api/modules/usage.ts | 4 -- .../src/components/usage/shared/presenter.ts | 4 -- 35 files changed, 55 insertions(+), 303 deletions(-) diff --git a/backend/crates/gateway-admin/src/model/observability.rs b/backend/crates/gateway-admin/src/model/observability.rs index 0af4774dc..24f978e06 100644 --- a/backend/crates/gateway-admin/src/model/observability.rs +++ b/backend/crates/gateway-admin/src/model/observability.rs @@ -722,10 +722,6 @@ pub struct UsageListRecord { pub upstream_response_ms: Option, pub upstream_api_overhead_ms: Option, pub upstream_engine_ms: Option, - pub upstream_engine_iapi_ttft_ms: Option, - pub upstream_engine_service_ttft_ms: Option, - pub upstream_engine_iapi_tbt_ms: Option, - pub upstream_engine_service_tbt_ms: Option, pub latency_ms: Option, pub admission_decision_ms: Option, pub account_selection_wait_ms: Option, @@ -803,10 +799,6 @@ pub struct UsageRecord { pub upstream_response_ms: Option, pub upstream_api_overhead_ms: Option, pub upstream_engine_ms: Option, - pub upstream_engine_iapi_ttft_ms: Option, - pub upstream_engine_service_ttft_ms: Option, - pub upstream_engine_iapi_tbt_ms: Option, - pub upstream_engine_service_tbt_ms: Option, pub latency_ms: Option, pub admission_decision_ms: Option, pub account_selection_wait_ms: Option, diff --git a/backend/crates/gateway-admin/tests/use_case/observability/mod.rs b/backend/crates/gateway-admin/tests/use_case/observability/mod.rs index 361117142..b9b0d8a02 100644 --- a/backend/crates/gateway-admin/tests/use_case/observability/mod.rs +++ b/backend/crates/gateway-admin/tests/use_case/observability/mod.rs @@ -1390,10 +1390,6 @@ fn total_record( upstream_response_ms: None, upstream_api_overhead_ms: None, upstream_engine_ms: None, - upstream_engine_iapi_ttft_ms: None, - upstream_engine_service_ttft_ms: None, - upstream_engine_iapi_tbt_ms: None, - upstream_engine_service_tbt_ms: None, latency_ms: Some(100), admission_decision_ms: None, account_selection_wait_ms: None, diff --git a/backend/crates/gateway-api/src/admin/observability/presenter.rs b/backend/crates/gateway-api/src/admin/observability/presenter.rs index a67dbcce0..9035ef183 100644 --- a/backend/crates/gateway-api/src/admin/observability/presenter.rs +++ b/backend/crates/gateway-api/src/admin/observability/presenter.rs @@ -304,10 +304,6 @@ pub(crate) fn usage_list_record_view( upstream_response_ms: record.upstream_response_ms, upstream_api_overhead_ms: record.upstream_api_overhead_ms, upstream_engine_ms: record.upstream_engine_ms, - upstream_engine_iapi_ttft_ms: record.upstream_engine_iapi_ttft_ms, - upstream_engine_service_ttft_ms: record.upstream_engine_service_ttft_ms, - upstream_engine_iapi_tbt_ms: record.upstream_engine_iapi_tbt_ms, - upstream_engine_service_tbt_ms: record.upstream_engine_service_tbt_ms, }, first_token_latency_ms: record.first_token_ms, latency_ms: record.latency_ms, @@ -411,10 +407,6 @@ pub(crate) fn usage_record_view( upstream_response_ms: record.upstream_response_ms, upstream_api_overhead_ms: record.upstream_api_overhead_ms, upstream_engine_ms: record.upstream_engine_ms, - upstream_engine_iapi_ttft_ms: record.upstream_engine_iapi_ttft_ms, - upstream_engine_service_ttft_ms: record.upstream_engine_service_ttft_ms, - upstream_engine_iapi_tbt_ms: record.upstream_engine_iapi_tbt_ms, - upstream_engine_service_tbt_ms: record.upstream_engine_service_tbt_ms, }, attempt_index: None, attempt_count: u64::from(record.attempt_count), diff --git a/backend/crates/gateway-api/src/admin/observability/wire.rs b/backend/crates/gateway-api/src/admin/observability/wire.rs index 965de96a3..829465fcd 100644 --- a/backend/crates/gateway-api/src/admin/observability/wire.rs +++ b/backend/crates/gateway-api/src/admin/observability/wire.rs @@ -230,14 +230,6 @@ pub struct UsageLatencyDetailsView { pub upstream_api_overhead_ms: Option, #[serde(skip_serializing_if = "Option::is_none")] pub upstream_engine_ms: Option, - #[serde(skip_serializing_if = "Option::is_none")] - pub upstream_engine_iapi_ttft_ms: Option, - #[serde(skip_serializing_if = "Option::is_none")] - pub upstream_engine_service_ttft_ms: Option, - #[serde(skip_serializing_if = "Option::is_none")] - pub upstream_engine_iapi_tbt_ms: Option, - #[serde(skip_serializing_if = "Option::is_none")] - pub upstream_engine_service_tbt_ms: Option, } /// 单次上游尝试展示 diff --git a/backend/crates/gateway-api/src/key_usage/presenter.rs b/backend/crates/gateway-api/src/key_usage/presenter.rs index 5f4f6781f..511eb9057 100644 --- a/backend/crates/gateway-api/src/key_usage/presenter.rs +++ b/backend/crates/gateway-api/src/key_usage/presenter.rs @@ -213,14 +213,6 @@ struct OutputTimingView { #[serde(skip_serializing_if = "Option::is_none")] upstream_engine_ms: Option, #[serde(skip_serializing_if = "Option::is_none")] - upstream_engine_iapi_ttft_ms: Option, - #[serde(skip_serializing_if = "Option::is_none")] - upstream_engine_service_ttft_ms: Option, - #[serde(skip_serializing_if = "Option::is_none")] - upstream_engine_iapi_tbt_ms: Option, - #[serde(skip_serializing_if = "Option::is_none")] - upstream_engine_service_tbt_ms: Option, - #[serde(skip_serializing_if = "Option::is_none")] first_event_ms: Option, #[serde(skip_serializing_if = "Option::is_none")] first_reasoning_ms: Option, @@ -260,10 +252,6 @@ fn usage_record(value: UsageListRecord, time: crate::time::TimePresenter) -> Rec upstream_response_ms: value.upstream_response_ms, upstream_api_overhead_ms: value.upstream_api_overhead_ms, upstream_engine_ms: value.upstream_engine_ms, - upstream_engine_iapi_ttft_ms: value.upstream_engine_iapi_ttft_ms, - upstream_engine_service_ttft_ms: value.upstream_engine_service_ttft_ms, - upstream_engine_iapi_tbt_ms: value.upstream_engine_iapi_tbt_ms, - upstream_engine_service_tbt_ms: value.upstream_engine_service_tbt_ms, first_event_ms: value.first_event_ms, first_reasoning_ms: value.first_reasoning_ms, first_text_ms: value.first_text_ms, diff --git a/backend/crates/gateway-api/src/openai/responses/websocket/protocol.rs b/backend/crates/gateway-api/src/openai/responses/websocket/protocol.rs index 1ca95c858..61d71aa58 100644 --- a/backend/crates/gateway-api/src/openai/responses/websocket/protocol.rs +++ b/backend/crates/gateway-api/src/openai/responses/websocket/protocol.rs @@ -58,7 +58,8 @@ fn decode_response_create_inner( else { return Err(ResponseCreateFrameError::ExpectedObject); }; - match body.remove("type") { + // 保持剩余字段顺序，避免末尾元数据交换到模型等路由字段之前 + match body.shift_remove("type") { Some(Value::String(message_type)) if message_type == "response.create" => {} _ => return Err(ResponseCreateFrameError::UnsupportedType), } diff --git a/backend/crates/gateway-api/tests/admin/observability/response.rs b/backend/crates/gateway-api/tests/admin/observability/response.rs index a7b9100f6..807cce9ad 100644 --- a/backend/crates/gateway-api/tests/admin/observability/response.rs +++ b/backend/crates/gateway-api/tests/admin/observability/response.rs @@ -288,10 +288,6 @@ async fn usage_detail_should_keep_attempt_snapshot_contract() { record.upstream_response_ms = Some(1_000); record.upstream_api_overhead_ms = Some(120.25); record.upstream_engine_ms = Some(6400.0); - record.upstream_engine_iapi_ttft_ms = Some(650.5); - record.upstream_engine_service_ttft_ms = Some(720.25); - record.upstream_engine_iapi_tbt_ms = Some(18.45); - record.upstream_engine_service_tbt_ms = Some(20.12); fixture .usage_detail .lock() @@ -362,22 +358,6 @@ async fn usage_detail_should_keep_attempt_snapshot_contract() { value["data"]["latencyDetails"]["upstreamEngineMs"], json!(6400.0) ); - assert_eq!( - value["data"]["latencyDetails"]["upstreamEngineIapiTtftMs"], - json!(650.5) - ); - assert_eq!( - value["data"]["latencyDetails"]["upstreamEngineServiceTtftMs"], - json!(720.25) - ); - assert_eq!( - value["data"]["latencyDetails"]["upstreamEngineIapiTbtMs"], - json!(18.45) - ); - assert_eq!( - value["data"]["latencyDetails"]["upstreamEngineServiceTbtMs"], - json!(20.12) - ); assert!(value["data"].get("firstTokenMs").is_none()); assert!(value["data"].get("firstTokenLatencyMsDisplay").is_none()); assert!( @@ -734,10 +714,6 @@ pub(super) fn usage_record_with_account( upstream_response_ms: None, upstream_api_overhead_ms: None, upstream_engine_ms: None, - upstream_engine_iapi_ttft_ms: None, - upstream_engine_service_ttft_ms: None, - upstream_engine_iapi_tbt_ms: None, - upstream_engine_service_tbt_ms: None, latency_ms: None, admission_decision_ms: None, account_selection_wait_ms: None, @@ -877,10 +853,6 @@ async fn usage_route_should_expose_table_facts_without_detail_payload() { upstream_response_ms: Some(2_000), upstream_api_overhead_ms: None, upstream_engine_ms: None, - upstream_engine_iapi_ttft_ms: None, - upstream_engine_service_ttft_ms: None, - upstream_engine_iapi_tbt_ms: None, - upstream_engine_service_tbt_ms: None, latency_ms: Some(31), admission_decision_ms: Some(1), account_selection_wait_ms: Some(2), diff --git a/backend/crates/gateway-api/tests/key_usage/fixtures.rs b/backend/crates/gateway-api/tests/key_usage/fixtures.rs index 303d041da..674bb6259 100644 --- a/backend/crates/gateway-api/tests/key_usage/fixtures.rs +++ b/backend/crates/gateway-api/tests/key_usage/fixtures.rs @@ -140,11 +140,7 @@ fn usage_record() -> UsageListRecord { provider_processing_ms: None, upstream_response_ms: Some(1_000), upstream_api_overhead_ms: None, - upstream_engine_ms: None, - upstream_engine_iapi_ttft_ms: None, - upstream_engine_service_ttft_ms: None, - upstream_engine_iapi_tbt_ms: Some(2.450638), - upstream_engine_service_tbt_ms: None, + upstream_engine_ms: Some(2.450638), latency_ms: Some(1250), admission_decision_ms: None, account_selection_wait_ms: None, diff --git a/backend/crates/gateway-api/tests/key_usage/mod.rs b/backend/crates/gateway-api/tests/key_usage/mod.rs index 5e67149f4..3044cd112 100644 --- a/backend/crates/gateway-api/tests/key_usage/mod.rs +++ b/backend/crates/gateway-api/tests/key_usage/mod.rs @@ -320,7 +320,7 @@ async fn records_keep_pagination_and_hide_admin_and_upstream_data() { &record["latencyDetails"], &[ "upstreamResponseMs", - "upstreamEngineIapiTbtMs", + "upstreamEngineMs", "firstEventMs", "firstReasoningMs", "firstTextMs", @@ -328,10 +328,7 @@ async fn records_keep_pagination_and_hide_admin_and_upstream_data() { ); assert_eq!(record["latencyDetails"]["firstEventMs"], 100); assert_eq!(record["latencyDetails"]["upstreamResponseMs"], 1000); - assert_eq!( - record["latencyDetails"]["upstreamEngineIapiTbtMs"], - 2.450638 - ); + assert_eq!(record["latencyDetails"]["upstreamEngineMs"], 2.450638); assert!(record["statusCode"].is_null()); } else { assert_eq!(record["statusCode"], 502); diff --git a/backend/crates/gateway-api/tests/openai/responses/websocket/protocol.rs b/backend/crates/gateway-api/tests/openai/responses/websocket/protocol.rs index 167ae5bc6..32e08913d 100644 --- a/backend/crates/gateway-api/tests/openai/responses/websocket/protocol.rs +++ b/backend/crates/gateway-api/tests/openai/responses/websocket/protocol.rs @@ -8,6 +8,26 @@ use serde_json::json; use super::decode_response_create; +#[test] +fn response_create_should_preserve_field_order_when_removing_frame_type() { + let expected = r#"{"model":"smart-code","stream":true,"input":"hello","future_field":{"z":1,"a":2},"client_metadata":{"thread_id":"thread","turn_id":"turn"}}"#; + for payload in [ + r#"{"type":"response.create","model":"smart-code","stream":true,"input":"hello","future_field":{"z":1,"a":2},"client_metadata":{"thread_id":"thread","turn_id":"turn"}}"#, + r#"{"model":"smart-code","stream":true,"type":"response.create","input":"hello","future_field":{"z":1,"a":2},"client_metadata":{"thread_id":"thread","turn_id":"turn"}}"#, + r#"{"model":"smart-code","stream":true,"input":"hello","future_field":{"z":1,"a":2},"client_metadata":{"thread_id":"thread","turn_id":"turn"},"type":"response.create"}"#, + ] { + let decoded = decode_response_create(payload).expect("decode response.create"); + let body = decoded + .operation() + .middleware_body() + .expect("encode transparent body"); + assert_eq!( + std::str::from_utf8(&body).expect("UTF-8 JSON body"), + expected, + ); + } +} + #[test] fn client_retry_identity_should_follow_each_frame_instead_of_handshake_metadata() { let mut headers = HeaderMap::new(); diff --git a/backend/crates/gateway-core/src/engine/mod.rs b/backend/crates/gateway-core/src/engine/mod.rs index 90898fe9e..0a8b6e7aa 100644 --- a/backend/crates/gateway-core/src/engine/mod.rs +++ b/backend/crates/gateway-core/src/engine/mod.rs @@ -955,10 +955,6 @@ pub struct ModelRequestTimings { pub upstream_response_ms: Option, pub upstream_api_overhead_ms: Option, pub upstream_engine_ms: Option, - pub upstream_engine_iapi_ttft_ms: Option, - pub upstream_engine_service_ttft_ms: Option, - pub upstream_engine_iapi_tbt_ms: Option, - pub upstream_engine_service_tbt_ms: Option, pub latency_ms: Option, } diff --git a/backend/crates/gateway-core/src/engine/observation.rs b/backend/crates/gateway-core/src/engine/observation.rs index 3a2e34cc2..d1a1d3b81 100644 --- a/backend/crates/gateway-core/src/engine/observation.rs +++ b/backend/crates/gateway-core/src/engine/observation.rs @@ -807,10 +807,6 @@ impl ResponseObservation { self.timings.upstream_response_ms = None; self.timings.upstream_api_overhead_ms = None; self.timings.upstream_engine_ms = None; - self.timings.upstream_engine_iapi_ttft_ms = None; - self.timings.upstream_engine_service_ttft_ms = None; - self.timings.upstream_engine_iapi_tbt_ms = None; - self.timings.upstream_engine_service_tbt_ms = None; } pub(super) fn observe_response(&mut self, observation: &ProviderResponseObservation) { @@ -848,17 +844,5 @@ impl ResponseObservation { if let Some(value) = observed.upstream_engine_ms { self.timings.upstream_engine_ms = Some(value); } - if let Some(value) = observed.upstream_engine_iapi_ttft_ms { - self.timings.upstream_engine_iapi_ttft_ms = Some(value); - } - if let Some(value) = observed.upstream_engine_service_ttft_ms { - self.timings.upstream_engine_service_ttft_ms = Some(value); - } - if let Some(value) = observed.upstream_engine_iapi_tbt_ms { - self.timings.upstream_engine_iapi_tbt_ms = Some(value); - } - if let Some(value) = observed.upstream_engine_service_tbt_ms { - self.timings.upstream_engine_service_tbt_ms = Some(value); - } } } diff --git a/backend/crates/gateway-core/src/event.rs b/backend/crates/gateway-core/src/event.rs index c00d9e4fb..4ab98ccc1 100644 --- a/backend/crates/gateway-core/src/event.rs +++ b/backend/crates/gateway-core/src/event.rs @@ -536,12 +536,8 @@ pub struct ProviderResponseTimings { pub upstream_response_ms: Option, /// 上游排除引擎与客户端工具时间后的 API 耗时 pub upstream_api_overhead_ms: Option, - /// 上游响应级引擎耗时；以下专项指标保留毫秒小数及各自内部计量层级 + /// 上游响应级引擎耗时，保留毫秒小数 pub upstream_engine_ms: Option, - pub upstream_engine_iapi_ttft_ms: Option, - pub upstream_engine_service_ttft_ms: Option, - pub upstream_engine_iapi_tbt_ms: Option, - pub upstream_engine_service_tbt_ms: Option, } /// Provider 已筛选的响应观测 JSON diff --git a/backend/crates/gateway-core/tests/engine/coordinator.rs b/backend/crates/gateway-core/tests/engine/coordinator.rs index fbd83b21b..d4c8a3546 100644 --- a/backend/crates/gateway-core/tests/engine/coordinator.rs +++ b/backend/crates/gateway-core/tests/engine/coordinator.rs @@ -505,10 +505,6 @@ struct FinalState { upstream_response_ms: Option, upstream_api_overhead_ms: Option, upstream_engine_ms: Option, - upstream_engine_iapi_ttft_ms: Option, - upstream_engine_service_ttft_ms: Option, - upstream_engine_iapi_tbt_ms: Option, - upstream_engine_service_tbt_ms: Option, provider_metadata_json: Option, cost_source: CostSource, cost_ticks: Option, @@ -684,12 +680,6 @@ impl ExecutionStore for FakeStore { upstream_response_ms: finalization.timings.upstream_response_ms, upstream_api_overhead_ms: finalization.timings.upstream_api_overhead_ms, upstream_engine_ms: finalization.timings.upstream_engine_ms, - upstream_engine_iapi_ttft_ms: finalization.timings.upstream_engine_iapi_ttft_ms, - upstream_engine_service_ttft_ms: finalization - .timings - .upstream_engine_service_ttft_ms, - upstream_engine_iapi_tbt_ms: finalization.timings.upstream_engine_iapi_tbt_ms, - upstream_engine_service_tbt_ms: finalization.timings.upstream_engine_service_tbt_ms, provider_metadata_json: finalization.provider_metadata_json, cost_source: finalization.cost.source(), cost_ticks: finalization @@ -2067,10 +2057,6 @@ fn discarded_attempt_observation_does_not_leak_into_retry_result() { upstream_response_ms: Some(7_000), upstream_api_overhead_ms: Some(120.25), upstream_engine_ms: Some(6400.0), - upstream_engine_iapi_ttft_ms: Some(650.5), - upstream_engine_service_ttft_ms: Some(720.25), - upstream_engine_iapi_tbt_ms: Some(18.45), - upstream_engine_service_tbt_ms: Some(20.12), ..ProviderResponseTimings::default() }); let second_observation = ProviderResponseObservation::new( @@ -2164,10 +2150,6 @@ fn discarded_attempt_observation_does_not_leak_into_retry_result() { assert_eq!(finalization.upstream_response_ms, None); assert_eq!(finalization.upstream_api_overhead_ms, None); assert_eq!(finalization.upstream_engine_ms, None); - assert_eq!(finalization.upstream_engine_iapi_ttft_ms, None); - assert_eq!(finalization.upstream_engine_service_ttft_ms, None); - assert_eq!(finalization.upstream_engine_iapi_tbt_ms, None); - assert_eq!(finalization.upstream_engine_service_tbt_ms, None); let contexts = provider.contexts.lock().unwrap(); assert_eq!(contexts.len(), 2); assert_eq!( diff --git a/backend/crates/gateway-plugin/runtime/src/adapter/observer.rs b/backend/crates/gateway-plugin/runtime/src/adapter/observer.rs index d64a06da6..6aa31818f 100644 --- a/backend/crates/gateway-plugin/runtime/src/adapter/observer.rs +++ b/backend/crates/gateway-plugin/runtime/src/adapter/observer.rs @@ -543,10 +543,6 @@ fn wire_timings(observation: &RequestObservation) -> RequestTimings { upstream_response_ms: timings.upstream_response_ms, upstream_api_overhead_ms: timings.upstream_api_overhead_ms, upstream_engine_ms: timings.upstream_engine_ms, - upstream_engine_iapi_ttft_ms: timings.upstream_engine_iapi_ttft_ms, - upstream_engine_service_ttft_ms: timings.upstream_engine_service_ttft_ms, - upstream_engine_iapi_tbt_ms: timings.upstream_engine_iapi_tbt_ms, - upstream_engine_service_tbt_ms: timings.upstream_engine_service_tbt_ms, latency_ms: timings.latency_ms, } } diff --git a/backend/crates/gateway-plugin/runtime/src/callback/facts.rs b/backend/crates/gateway-plugin/runtime/src/callback/facts.rs index aca9a8353..cc12d9498 100644 --- a/backend/crates/gateway-plugin/runtime/src/callback/facts.rs +++ b/backend/crates/gateway-plugin/runtime/src/callback/facts.rs @@ -132,10 +132,6 @@ fn observation(value: &ProviderResponseObservation) -> facts::ResponseObservatio upstream_response_ms: timings.upstream_response_ms, upstream_api_overhead_ms: timings.upstream_api_overhead_ms, upstream_engine_ms: timings.upstream_engine_ms, - upstream_engine_iapi_ttft_ms: timings.upstream_engine_iapi_ttft_ms, - upstream_engine_service_ttft_ms: timings.upstream_engine_service_ttft_ms, - upstream_engine_iapi_tbt_ms: timings.upstream_engine_iapi_tbt_ms, - upstream_engine_service_tbt_ms: timings.upstream_engine_service_tbt_ms, latency_ms: None, }, client_headers: value diff --git a/backend/crates/gateway-plugin/runtime/tests/generation/observer.rs b/backend/crates/gateway-plugin/runtime/tests/generation/observer.rs index 5d26d78ba..77f1a53fc 100644 --- a/backend/crates/gateway-plugin/runtime/tests/generation/observer.rs +++ b/backend/crates/gateway-plugin/runtime/tests/generation/observer.rs @@ -817,7 +817,7 @@ async fn completed_observation_contains_terminal_cost_timings_and_failure() { .with_timings(ModelRequestTimings { first_text_ms: Some(12), upstream_response_ms: Some(7_000), - upstream_engine_iapi_tbt_ms: Some(2.450638), + upstream_engine_ms: Some(2.450638), latency_ms: Some(34), ..ModelRequestTimings::default() }), @@ -831,10 +831,7 @@ async fn completed_observation_contains_terminal_cost_timings_and_failure() { assert_eq!(observed["usage"]["cost"]["total"]["currency"], "USD"); assert_eq!(observed["usage"]["timings"]["first_text_ms"], 12); assert_eq!(observed["usage"]["timings"]["upstream_response_ms"], 7_000); - assert_eq!( - observed["usage"]["timings"]["upstream_engine_iapi_tbt_ms"], - 2.450638 - ); + assert_eq!(observed["usage"]["timings"]["upstream_engine_ms"], 2.450638); assert_eq!(observed["usage"]["timings"]["latency_ms"], 34); assert_eq!(observed["usage"]["failure"]["outcome"], "failed"); assert_eq!(observed["usage"]["failure"]["attempt_count"], 2); diff --git a/backend/crates/gateway-plugin/runtime/tests/generation/policy/facts/mod.rs b/backend/crates/gateway-plugin/runtime/tests/generation/policy/facts/mod.rs index fb7ba93a3..22c595ffb 100644 --- a/backend/crates/gateway-plugin/runtime/tests/generation/policy/facts/mod.rs +++ b/backend/crates/gateway-plugin/runtime/tests/generation/policy/facts/mod.rs @@ -186,7 +186,7 @@ async fn facts_are_readable_without_replacing_or_duplicating_the_original_execut .with_timings(ProviderResponseTimings { headers_ms: Some(19), upstream_response_ms: Some(7_000), - upstream_engine_iapi_tbt_ms: Some(2.450638), + upstream_engine_ms: Some(2.450638), ..Default::default() }), ); @@ -273,7 +273,7 @@ async fn facts_are_readable_without_replacing_or_duplicating_the_original_execut ); assert_eq!(facts["observation"]["timings"]["headers_ms"], 19); assert_eq!( - facts["observation"]["timings"]["upstream_engine_iapi_tbt_ms"], + facts["observation"]["timings"]["upstream_engine_ms"], 2.450638 ); assert_eq!( diff --git a/backend/crates/gateway-plugin/sdk/src/call/observation.rs b/backend/crates/gateway-plugin/sdk/src/call/observation.rs index ae7b43424..658da10de 100644 --- a/backend/crates/gateway-plugin/sdk/src/call/observation.rs +++ b/backend/crates/gateway-plugin/sdk/src/call/observation.rs @@ -110,14 +110,6 @@ pub struct RequestTimings { #[serde(default, skip_serializing_if = "Option::is_none")] pub upstream_engine_ms: Option, #[serde(default, skip_serializing_if = "Option::is_none")] - pub upstream_engine_iapi_ttft_ms: Option, - #[serde(default, skip_serializing_if = "Option::is_none")] - pub upstream_engine_service_ttft_ms: Option, - #[serde(default, skip_serializing_if = "Option::is_none")] - pub upstream_engine_iapi_tbt_ms: Option, - #[serde(default, skip_serializing_if = "Option::is_none")] - pub upstream_engine_service_tbt_ms: Option, - #[serde(default, skip_serializing_if = "Option::is_none")] pub latency_ms: Option, } diff --git a/backend/crates/gateway-plugin/sdk/tests/call/observation.rs b/backend/crates/gateway-plugin/sdk/tests/call/observation.rs index 592c06c85..ce16cdfd4 100644 --- a/backend/crates/gateway-plugin/sdk/tests/call/observation.rs +++ b/backend/crates/gateway-plugin/sdk/tests/call/observation.rs @@ -204,13 +204,13 @@ fn cost_timings_and_failure_keep_unknown_facts_explicit_and_safe() { let timings = RequestTimings { first_text_ms: Some(12), upstream_response_ms: Some(7_000), - upstream_engine_iapi_tbt_ms: Some(2.450638), + upstream_engine_ms: Some(2.450638), latency_ms: Some(34), ..RequestTimings::default() }; assert_eq!( serde_json::to_value(&timings).unwrap(), - json!({"first_text_ms":12,"upstream_response_ms":7000,"upstream_engine_iapi_tbt_ms":2.450638,"latency_ms":34}) + json!({"first_text_ms":12,"upstream_response_ms":7000,"upstream_engine_ms":2.450638,"latency_ms":34}) ); let failure = RequestFailure { diff --git a/backend/crates/gateway-store/src/postgres/execution/request_observation.rs b/backend/crates/gateway-store/src/postgres/execution/request_observation.rs index 9f7830d3b..676d42d7d 100644 --- a/backend/crates/gateway-store/src/postgres/execution/request_observation.rs +++ b/backend/crates/gateway-store/src/postgres/execution/request_observation.rs @@ -107,14 +107,6 @@ struct UpstreamTimings { api_overhead_ms: Option, #[serde(skip_serializing_if = "Option::is_none")] engine_ms: Option, - #[serde(skip_serializing_if = "Option::is_none")] - engine_iapi_ttft_ms: Option, - #[serde(skip_serializing_if = "Option::is_none")] - engine_service_ttft_ms: Option, - #[serde(skip_serializing_if = "Option::is_none")] - engine_iapi_tbt_ms: Option, - #[serde(skip_serializing_if = "Option::is_none")] - engine_service_tbt_ms: Option, } #[derive(Default, Serialize)] @@ -229,16 +221,9 @@ impl RequestObservation { value.retry_after_ms, ])?; // serde_json 会把非有限浮点数写成 null，先拒绝以免把非法指标伪装成缺失 - for value in [ - timings.upstream_api_overhead_ms, - timings.upstream_engine_ms, - timings.upstream_engine_iapi_ttft_ms, - timings.upstream_engine_service_ttft_ms, - timings.upstream_engine_iapi_tbt_ms, - timings.upstream_engine_service_tbt_ms, - ] - .into_iter() - .flatten() + for value in [timings.upstream_api_overhead_ms, timings.upstream_engine_ms] + .into_iter() + .flatten() { if !value.is_finite() || value < 0.0 || value >= i64::MAX as f64 { return Err(invalid( @@ -263,10 +248,6 @@ impl RequestObservation { response_ms: timings.upstream_response_ms, api_overhead_ms: timings.upstream_api_overhead_ms, engine_ms: timings.upstream_engine_ms, - engine_iapi_ttft_ms: timings.upstream_engine_iapi_ttft_ms, - engine_service_ttft_ms: timings.upstream_engine_service_ttft_ms, - engine_iapi_tbt_ms: timings.upstream_engine_iapi_tbt_ms, - engine_service_tbt_ms: timings.upstream_engine_service_tbt_ms, }), }), transport: Some(TransportObservation { diff --git a/backend/crates/gateway-store/src/postgres/observability/mapping.rs b/backend/crates/gateway-store/src/postgres/observability/mapping.rs index f6bbca0da..97293b4c4 100644 --- a/backend/crates/gateway-store/src/postgres/observability/mapping.rs +++ b/backend/crates/gateway-store/src/postgres/observability/mapping.rs @@ -350,10 +350,6 @@ pub(crate) fn usage_list_record_from_row( upstream_response_ms: optional_unsigned(row, "upstream_response_ms")?, upstream_api_overhead_ms: get(row, "upstream_api_overhead_ms")?, upstream_engine_ms: get(row, "upstream_engine_ms")?, - upstream_engine_iapi_ttft_ms: get(row, "upstream_engine_iapi_ttft_ms")?, - upstream_engine_service_ttft_ms: get(row, "upstream_engine_service_ttft_ms")?, - upstream_engine_iapi_tbt_ms: get(row, "upstream_engine_iapi_tbt_ms")?, - upstream_engine_service_tbt_ms: get(row, "upstream_engine_service_tbt_ms")?, latency_ms: optional_unsigned(row, "latency_ms")?, admission_decision_ms: optional_unsigned(row, "admission_decision_ms")?, account_selection_wait_ms: optional_unsigned(row, "account_selection_wait_ms")?, @@ -446,10 +442,6 @@ pub(crate) fn usage_record_from_row(row: &sqlx::postgres::PgRow) -> StoreResult< upstream_response_ms: optional_unsigned(row, "upstream_response_ms")?, upstream_api_overhead_ms: get(row, "upstream_api_overhead_ms")?, upstream_engine_ms: get(row, "upstream_engine_ms")?, - upstream_engine_iapi_ttft_ms: get(row, "upstream_engine_iapi_ttft_ms")?, - upstream_engine_service_ttft_ms: get(row, "upstream_engine_service_ttft_ms")?, - upstream_engine_iapi_tbt_ms: get(row, "upstream_engine_iapi_tbt_ms")?, - upstream_engine_service_tbt_ms: get(row, "upstream_engine_service_tbt_ms")?, latency_ms: optional_unsigned(row, "latency_ms")?, admission_decision_ms: optional_unsigned(row, "admission_decision_ms")?, account_selection_wait_ms: optional_unsigned(row, "account_selection_wait_ms")?, diff --git a/backend/crates/gateway-store/src/postgres/observability/queries/usage.rs b/backend/crates/gateway-store/src/postgres/observability/queries/usage.rs index f4661b579..fc195ef05 100644 --- a/backend/crates/gateway-store/src/postgres/observability/queries/usage.rs +++ b/backend/crates/gateway-store/src/postgres/observability/queries/usage.rs @@ -128,7 +128,7 @@ pub(crate) const USAGE_LIST_RECORD_SELECT: &str = mr.transport_decision_wait_ms, mr.connect_ms, mr.headers_ms, mr.first_event_ms, mr.first_reasoning_ms, mr.first_text_ms, mr.first_token_ms, mr.provider_processing_ms, mr.upstream_response_ms, - mr.upstream_api_overhead_ms, mr.upstream_engine_ms, mr.upstream_engine_iapi_ttft_ms, mr.upstream_engine_service_ttft_ms, mr.upstream_engine_iapi_tbt_ms, mr.upstream_engine_service_tbt_ms, mr.latency_ms, mr.admission_decision_ms, + mr.upstream_api_overhead_ms, mr.upstream_engine_ms, mr.latency_ms, mr.admission_decision_ms, mr.account_selection_wait_ms, mr.capacity_used_slots, mr.capacity_total_slots, host(mr.client_ip) as client_ip, mr.user_agent, mr.reasoning_effort, mr.reasoning_preset, mr.subagent_kind, mr.compact, @@ -157,7 +157,7 @@ pub(crate) const USAGE_RECORD_DETAIL_SELECT: &str = mr.cost_currency, mr.transport_decision_wait_ms, mr.connect_ms, mr.headers_ms, mr.first_event_ms, mr.first_reasoning_ms, mr.first_text_ms, mr.first_token_ms, mr.provider_processing_ms, mr.upstream_response_ms, - mr.upstream_api_overhead_ms, mr.upstream_engine_ms, mr.upstream_engine_iapi_ttft_ms, mr.upstream_engine_service_ttft_ms, mr.upstream_engine_iapi_tbt_ms, mr.upstream_engine_service_tbt_ms, mr.latency_ms, mr.admission_decision_ms, + mr.upstream_api_overhead_ms, mr.upstream_engine_ms, mr.latency_ms, mr.admission_decision_ms, mr.account_selection_wait_ms, mr.capacity_used_slots, mr.capacity_total_slots, host(mr.client_ip) as client_ip, mr.user_agent, mr.reasoning_effort, mr.reasoning_preset, mr.request_kind, diff --git a/backend/crates/gateway-store/tests/postgres/execution/mod.rs b/backend/crates/gateway-store/tests/postgres/execution/mod.rs index ac68ff817..7efbf0a32 100644 --- a/backend/crates/gateway-store/tests/postgres/execution/mod.rs +++ b/backend/crates/gateway-store/tests/postgres/execution/mod.rs @@ -2168,10 +2168,6 @@ async fn shared_core_usage_and_timings_preserve_fields_and_reject_invalid_phases upstream_response_ms: Some(1_000), upstream_api_overhead_ms: Some(120.25), upstream_engine_ms: Some(6400.0), - upstream_engine_iapi_ttft_ms: Some(650.5), - upstream_engine_service_ttft_ms: Some(720.25), - upstream_engine_iapi_tbt_ms: Some(18.45), - upstream_engine_service_tbt_ms: Some(20.12), latency_ms: Some(9), }; ExecutionStore::finalize_model_request(&store, finalization) @@ -2202,22 +2198,6 @@ async fn shared_core_usage_and_timings_preserve_fields_and_reject_invalid_phases } assert_eq!(persisted["upstream_api_overhead_ms"].as_f64(), Some(120.25)); assert_eq!(persisted["upstream_engine_ms"].as_f64(), Some(6400.0)); - assert_eq!( - persisted["upstream_engine_iapi_ttft_ms"].as_f64(), - Some(650.5) - ); - assert_eq!( - persisted["upstream_engine_service_ttft_ms"].as_f64(), - Some(720.25) - ); - assert_eq!( - persisted["upstream_engine_iapi_tbt_ms"].as_f64(), - Some(18.45) - ); - assert_eq!( - persisted["upstream_engine_service_tbt_ms"].as_f64(), - Some(20.12) - ); let invalid_id = "req_invalid_phase"; seed_running_request(&database.pool, invalid_id) .await @@ -2233,7 +2213,7 @@ async fn shared_core_usage_and_timings_preserve_fields_and_reject_invalid_phases assert_eq!(stored_row(&database.pool, invalid_id).await, before); for invalid_ms in [-1.0, f64::NAN, f64::INFINITY, i64::MAX as f64] { let mut invalid = successful_core_finalization(invalid_id); - invalid.timings.upstream_engine_iapi_tbt_ms = Some(invalid_ms); + invalid.timings.upstream_engine_ms = Some(invalid_ms); let error = ExecutionStore::finalize_model_request(&store, invalid) .await .expect_err("invalid official timing must not silently become missing"); diff --git a/backend/crates/gateway-store/tests/postgres/observability/mod.rs b/backend/crates/gateway-store/tests/postgres/observability/mod.rs index 4094db295..abdb17342 100644 --- a/backend/crates/gateway-store/tests/postgres/observability/mod.rs +++ b/backend/crates/gateway-store/tests/postgres/observability/mod.rs @@ -110,7 +110,7 @@ async fn output_throughput_uses_official_response_duration_without_local_fallbac 'firstTokenMs', $2::bigint, 'latencyMs', $3::bigint), 'upstream', coalesce(request_observation_json #> '{timings,upstream}', '{}'::jsonb) || jsonb_build_object( - 'responseMs', $4::bigint, 'engineIapiTbtMs', 2.450638)))) + 'responseMs', $4::bigint, 'engineMs', 2.450638)))) where id = 'req_observe_success'", ) .bind(output) @@ -150,8 +150,6 @@ async fn output_throughput_uses_official_response_duration_without_local_fallbac detail.request.upstream_response_ms, record.upstream_response_ms ); - assert_eq!(record.upstream_engine_iapi_tbt_ms, Some(2.450638)); - assert_eq!(detail.request.upstream_engine_iapi_tbt_ms, Some(2.450638)); super::drain_analytics(&database.pool).await; let summary = repository diff --git a/backend/crates/providers/openai/src/credential/oauth.rs b/backend/crates/providers/openai/src/credential/oauth.rs index 082f842dc..e3e534b05 100644 --- a/backend/crates/providers/openai/src/credential/oauth.rs +++ b/backend/crates/providers/openai/src/credential/oauth.rs @@ -776,12 +776,12 @@ fn authorization_url( .append_pair("response_type", "code") .append_pair("client_id", oauth_client_id) .append_pair("redirect_uri", OFFICIAL_CODEX_REDIRECT_URI) - .append_pair("scope", AUTHORIZATION_SCOPE) .append_pair("code_challenge", challenge.as_str()) .append_pair("code_challenge_method", "S256") + .append_pair("state", pending.state.expose_secret()) + .append_pair("scope", AUTHORIZATION_SCOPE) .append_pair("id_token_add_organizations", "true") .append_pair("codex_cli_simplified_flow", "true") - .append_pair("state", pending.state.expose_secret()) .append_pair("originator", AUTHORIZATION_ORIGINATOR) .append_pair("codex_app_version", desktop_version) .append_pair("source_surface_stable_id", &stable_id) diff --git a/backend/crates/providers/openai/src/provider/observation.rs b/backend/crates/providers/openai/src/provider/observation.rs index 091768d61..e1f269516 100644 --- a/backend/crates/providers/openai/src/provider/observation.rs +++ b/backend/crates/providers/openai/src/provider/observation.rs @@ -199,18 +199,6 @@ impl OpenAiResponseObservationState { if metrics.upstream_engine_ms.is_some() { self.timings.upstream_engine_ms = metrics.upstream_engine_ms; } - if metrics.upstream_engine_iapi_ttft_ms.is_some() { - self.timings.upstream_engine_iapi_ttft_ms = metrics.upstream_engine_iapi_ttft_ms; - } - if metrics.upstream_engine_service_ttft_ms.is_some() { - self.timings.upstream_engine_service_ttft_ms = metrics.upstream_engine_service_ttft_ms; - } - if metrics.upstream_engine_iapi_tbt_ms.is_some() { - self.timings.upstream_engine_iapi_tbt_ms = metrics.upstream_engine_iapi_tbt_ms; - } - if metrics.upstream_engine_service_tbt_ms.is_some() { - self.timings.upstream_engine_service_tbt_ms = metrics.upstream_engine_service_tbt_ms; - } self.timings != previous } diff --git a/backend/crates/providers/openai/src/transport/headers.rs b/backend/crates/providers/openai/src/transport/headers.rs index e0d90c87b..9e1377d2f 100644 --- a/backend/crates/providers/openai/src/transport/headers.rs +++ b/backend/crates/providers/openai/src/transport/headers.rs @@ -165,12 +165,6 @@ impl CodexBackendClient { context: CodexRequestContext<'_>, ) -> CodexClientResult { let mut headers = self.response_headers(profile, request, context)?; - if !headers.contains_key("x-responsesapi-include-timing-metrics") { - headers.insert( - HeaderName::from_static("x-responsesapi-include-timing-metrics"), - HeaderValue::from_static("true"), - ); - } headers.insert( HeaderName::from_static("openai-beta"), HeaderValue::from_static("responses_websockets=2026-02-06"), diff --git a/backend/crates/providers/openai/src/transport/protocol/responses.rs b/backend/crates/providers/openai/src/transport/protocol/responses.rs index 06fe682ea..3a1e4b960 100644 --- a/backend/crates/providers/openai/src/transport/protocol/responses.rs +++ b/backend/crates/providers/openai/src/transport/protocol/responses.rs @@ -255,10 +255,6 @@ pub(crate) fn response_duration_ms(value: &Value) -> Option { pub(crate) struct ResponseTimingMetrics { pub upstream_api_overhead_ms: Option, pub upstream_engine_ms: Option, - pub upstream_engine_iapi_ttft_ms: Option, - pub upstream_engine_service_ttft_ms: Option, - pub upstream_engine_iapi_tbt_ms: Option, - pub upstream_engine_service_tbt_ms: Option, } impl ResponseTimingMetrics { @@ -287,7 +283,6 @@ impl ResponseTimingMetrics { return Self { upstream_api_overhead_ms: overhead, upstream_engine_ms: milliseconds(path, "engine_wall_ms"), - ..Self::default() }; } // 直接返回的专项指标保留原口径，明确标为整轮累计的值不能归入单次请求 @@ -303,16 +298,6 @@ impl ResponseTimingMetrics { "responses_duration_excl_engine_and_client_tool_time_ms", ), upstream_engine_ms: milliseconds(metrics, "engine_service_total_ms"), - upstream_engine_iapi_ttft_ms: milliseconds(metrics, "engine_iapi_ttft_total_ms"), - upstream_engine_service_ttft_ms: milliseconds(metrics, "engine_service_ttft_total_ms"), - upstream_engine_iapi_tbt_ms: milliseconds( - metrics, - "engine_iapi_tbt_across_engine_calls_ms", - ), - upstream_engine_service_tbt_ms: milliseconds( - metrics, - "engine_service_tbt_across_engine_calls_ms", - ), } } @@ -323,18 +308,6 @@ impl ResponseTimingMetrics { if incoming.upstream_engine_ms.is_some() { self.upstream_engine_ms = incoming.upstream_engine_ms; } - if incoming.upstream_engine_iapi_ttft_ms.is_some() { - self.upstream_engine_iapi_ttft_ms = incoming.upstream_engine_iapi_ttft_ms; - } - if incoming.upstream_engine_service_ttft_ms.is_some() { - self.upstream_engine_service_ttft_ms = incoming.upstream_engine_service_ttft_ms; - } - if incoming.upstream_engine_iapi_tbt_ms.is_some() { - self.upstream_engine_iapi_tbt_ms = incoming.upstream_engine_iapi_tbt_ms; - } - if incoming.upstream_engine_service_tbt_ms.is_some() { - self.upstream_engine_service_tbt_ms = incoming.upstream_engine_service_tbt_ms; - } } } diff --git a/backend/crates/providers/openai/tests/credential/oauth.rs b/backend/crates/providers/openai/tests/credential/oauth.rs index f56bfc838..6867bd816 100644 --- a/backend/crates/providers/openai/tests/credential/oauth.rs +++ b/backend/crates/providers/openai/tests/credential/oauth.rs @@ -265,12 +265,12 @@ async fn authorize_url_matches_the_official_desktop_parameter_contract() { "response_type", "client_id", "redirect_uri", - "scope", "code_challenge", "code_challenge_method", + "state", + "scope", "id_token_add_organizations", "codex_cli_simplified_flow", - "state", "originator", "codex_app_version", "source_surface_stable_id", diff --git a/backend/crates/providers/openai/tests/provider/contract/timing.rs b/backend/crates/providers/openai/tests/provider/contract/timing.rs index 81cf635a5..4fff42bfa 100644 --- a/backend/crates/providers/openai/tests/provider/contract/timing.rs +++ b/backend/crates/providers/openai/tests/provider/contract/timing.rs @@ -66,9 +66,10 @@ async fn observe_timing_events(websocket: bool, events: Vec) -> ProviderR let mut ws = crate::transport::accept_codex_test_websocket_with( socket, |request: &tokio_tungstenite::tungstenite::handshake::server::Request, response| { - assert_eq!( - request.headers()["x-responsesapi-include-timing-metrics"], - "true" + assert!( + !request + .headers() + .contains_key("x-responsesapi-include-timing-metrics") ); response.headers_mut().insert( "sec-websocket-extensions", @@ -125,19 +126,11 @@ async fn official_response_duration_is_observed_independently_of_the_request_clo let metrics = json!({"type":"responsesapi.websocket_timing","timing_metrics":{ "responses_duration_excl_engine_and_client_tool_time_ms":120.25, "engine_service_total_ms":6400.0, - "engine_iapi_ttft_total_ms":650.5, - "engine_service_ttft_total_ms":720.25, - "engine_iapi_tbt_across_engine_calls_ms":18.45, - "engine_service_tbt_across_engine_calls_ms":20.12 }}); let wrong_id = json!({"type":"responsesapi.websocket_timing","response_id":"resp_other","timing_metrics":{"engine_service_total_ms":999.0}}); let invalid = json!({"type":"responsesapi.websocket_timing","timing_metrics":{ "responses_duration_excl_engine_and_client_tool_time_ms":null, "engine_service_total_ms":"100", - "engine_iapi_ttft_total_ms":-1, - "engine_service_ttft_total_ms":1e99, - "engine_iapi_tbt_across_engine_calls_ms":{}, - "engine_service_tbt_across_engine_calls_ms":[] }}); let stale = json!({"type":"responsesapi.websocket_timing","timing_metrics":{"engine_service_total_ms":999.0}}); let events = [stale, created, metrics, wrong_id, invalid, completed]; @@ -145,10 +138,6 @@ async fn official_response_duration_is_observed_independently_of_the_request_clo assert_eq!(timings.upstream_response_ms, Some(7_000)); assert_eq!(timings.upstream_api_overhead_ms, Some(120.25)); assert_eq!(timings.upstream_engine_ms, Some(6400.0)); - assert_eq!(timings.upstream_engine_iapi_ttft_ms, Some(650.5)); - assert_eq!(timings.upstream_engine_service_ttft_ms, Some(720.25)); - assert_eq!(timings.upstream_engine_iapi_tbt_ms, Some(18.45)); - assert_eq!(timings.upstream_engine_service_tbt_ms, Some(20.12)); assert_eq!(timings.first_token_ms, None); assert!(timings.first_event_ms.is_some_and(|value| value >= 20_000)); } @@ -197,7 +186,6 @@ async fn response_critical_path_is_observed_without_logical_turn_totals_on_both_ let mut metrics = response_critical_path_event(); // 同帧即使携带整轮专项值，也不能与响应级 critical path 混算 metrics["timing_metrics"]["engine_service_total_ms"] = json!(25_000); - metrics["timing_metrics"]["engine_iapi_ttft_total_ms"] = json!(500); let mut events = critical_path_response_events(metrics); let mut wrong_id = response_critical_path_event(); wrong_id["timing_metrics"]["response_id"] = json!("resp_other"); @@ -208,10 +196,6 @@ async fn response_critical_path_is_observed_without_logical_turn_totals_on_both_ assert!((timings.upstream_api_overhead_ms.unwrap() - 81.409594).abs() < 0.000001); assert_eq!(timings.upstream_response_ms, Some(7000)); assert_eq!(timings.first_token_ms, None); - assert_eq!(timings.upstream_engine_iapi_ttft_ms, None); - assert_eq!(timings.upstream_engine_service_ttft_ms, None); - assert_eq!(timings.upstream_engine_iapi_tbt_ms, None); - assert_eq!(timings.upstream_engine_service_tbt_ms, None); } } @@ -252,12 +236,10 @@ async fn critical_path_rejects_mismatched_identity_and_incomplete_or_cumulative_ "timing_scope":"logical_turn", "engine_service_total_ms":25_000, "responses_duration_excl_engine_and_client_tool_time_ms":500, - "engine_iapi_ttft_total_ms":200 }}); let timings = observe_timing_events(false, critical_path_response_events(metrics)).await; assert_eq!(timings.upstream_engine_ms, None); assert_eq!(timings.upstream_api_overhead_ms, None); - assert_eq!(timings.upstream_engine_iapi_ttft_ms, None); } #[tokio::test] @@ -288,10 +270,6 @@ async fn timing_frames_outside_the_active_response_do_not_enter_request_metrics( let timing = json!({"type":"responsesapi.websocket_timing","timing_metrics":{ "responses_duration_excl_engine_and_client_tool_time_ms":0, "engine_service_total_ms":450, - "engine_iapi_ttft_total_ms":211, - "engine_service_ttft_total_ms":233, - "engine_iapi_tbt_across_engine_calls_ms":2.450638, - "engine_service_tbt_across_engine_calls_ms":5.267279 }}); let created = json!({"type":"response.created","response":{"id":"resp_boundary"}}); let completed = json!({"type":"response.completed","response":{"id":"resp_boundary","status":"completed","output":[],"usage":{"input_tokens":1,"output_tokens":1,"total_tokens":2}}}); @@ -311,10 +289,6 @@ async fn timing_frames_outside_the_active_response_do_not_enter_request_metrics( let timings = finish_timings(&mut stream, ProviderResponseTimings::default()).await; assert_eq!(timings.upstream_api_overhead_ms, None); assert_eq!(timings.upstream_engine_ms, None); - assert_eq!(timings.upstream_engine_iapi_ttft_ms, None); - assert_eq!(timings.upstream_engine_service_ttft_ms, None); - assert_eq!(timings.upstream_engine_iapi_tbt_ms, None); - assert_eq!(timings.upstream_engine_service_tbt_ms, None); assert_eq!(timings.first_token_ms, None); server.await.unwrap(); } @@ -395,9 +369,10 @@ async fn structural_frames_start_ttft_before_content_on_http_and_websocket() { socket, |request: &tokio_tungstenite::tungstenite::handshake::server::Request, response| { - assert_eq!( - request.headers()["x-responsesapi-include-timing-metrics"], - "true" + assert!( + !request + .headers() + .contains_key("x-responsesapi-include-timing-metrics") ); response.headers_mut().insert( "sec-websocket-extensions", diff --git a/backend/crates/providers/openai/tests/transport/websocket/fingerprint.rs b/backend/crates/providers/openai/tests/transport/websocket/fingerprint.rs index 95308c596..08439fd92 100644 --- a/backend/crates/providers/openai/tests/transport/websocket/fingerprint.rs +++ b/backend/crates/providers/openai/tests/transport/websocket/fingerprint.rs @@ -110,8 +110,7 @@ async fn official_websocket_wire_fingerprint_should_remain_aligned() { opening.lines().next(), Some("GET /backend-api/codex/responses HTTP/1.1") ); - // 固定身份字段沿用官方画像，专项计时头按官方客户端在 openai-beta 后插入 - // HeaderMap 序列化会随新增头调整迭代顺序，锁定启用计时后的完整 opening + // 固定身份字段沿用官方画像，锁定默认不请求专项计时的完整 opening assert_eq!( read_header_names(&opening), vec![ @@ -124,7 +123,7 @@ async fn official_websocket_wire_fingerprint_should_remain_aligned() { "authorization", "user-agent", "originator", - "x-responsesapi-include-timing-metrics", + "openai-beta", "version", "x-codex-beta-features", "x-client-request-id", @@ -133,13 +132,12 @@ async fn official_websocket_wire_fingerprint_should_remain_aligned() { "x-codex-window-id", "x-codex-turn-metadata", "x-codex-routing-hint", - "openai-beta", "sec-websocket-extensions", ] ); assert_eq!( read_header_value(&opening, "x-responsesapi-include-timing-metrics"), - Some("true"), + None, ); assert_eq!( read_header_value(&opening, "sec-websocket-extensions"), diff --git a/docs/api.md b/docs/api.md index 1b9bf742e..dd7804a28 100644 --- a/docs/api.md +++ b/docs/api.md @@ -2055,7 +2055,7 @@ OpenAI 仅使用同一条 `response.completed` 中的 `created_at` 与 `complete `latencyDetails` 还可包含以下上游性能指标，单位为毫秒，保留上游返回的小数。 OpenAI 从当前响应的 `responsesapi.websocket_timing.timing_metrics` 读取， -WebSocket 握手默认请求专项计时，客户端显式提供的开关保留原值。 +WebSocket 握手不主动添加专项计时请求头，客户端显式提供的开关保留原值。 各字段独立可选；响应开始前、终态后的计时和明确属于其他响应的事件不写入当前请求，重试时清空 `critical_path` 仅采集 `scope=response`、`coverage=complete` 且边界为 @@ -2067,10 +2067,6 @@ WebSocket 握手默认请求专项计时，客户端显式提供的开关保留 | --- | --- | | `upstreamApiOverheadMs` | API 排除引擎与客户端工具时间后的耗时 | | `upstreamEngineMs` | 响应级引擎耗时，取完整 critical path 的墙钟时间或直接返回的 Engine Service 时间 | -| `upstreamEngineIapiTtftMs` | Engine IAPI TTFT 总计 | -| `upstreamEngineServiceTtftMs` | Engine Service TTFT 总计 | -| `upstreamEngineIapiTbtMs` | 跨引擎调用的 IAPI Token 间隔 | -| `upstreamEngineServiceTbtMs` | 跨引擎调用的 Service Token 间隔 | 以上指标按上游内部口径展示，不相加重建总耗时，不替换请求级 `firstTokenLatencyMs`。 它们仅补充性能诊断，不改变列表与聚合统计的速率分母 diff --git a/frontend/src/api/modules/usage.ts b/frontend/src/api/modules/usage.ts index 883d1d52e..684983f4f 100644 --- a/frontend/src/api/modules/usage.ts +++ b/frontend/src/api/modules/usage.ts @@ -59,10 +59,6 @@ export interface UsageLatencyDetails { upstreamResponseMs?: number upstreamApiOverheadMs?: number upstreamEngineMs?: number - upstreamEngineIapiTtftMs?: number - upstreamEngineServiceTtftMs?: number - upstreamEngineIapiTbtMs?: number - upstreamEngineServiceTbtMs?: number admissionDecisionMs?: number accountSelectionWaitMs?: number capacityUsedSlots?: number diff --git a/frontend/src/components/usage/shared/presenter.ts b/frontend/src/components/usage/shared/presenter.ts index 3e2da867d..2ae83732f 100644 --- a/frontend/src/components/usage/shared/presenter.ts +++ b/frontend/src/components/usage/shared/presenter.ts @@ -197,10 +197,6 @@ export function usageLatencyDetails(record: UsageLatencyRecord) { const performanceItems = [ { label: 'API 开销', value: durationValue(latencyDetails?.upstreamApiOverheadMs) }, { label: '引擎耗时', value: durationValue(latencyDetails?.upstreamEngineMs) }, - { label: 'TTFT · IAPI', value: durationValue(latencyDetails?.upstreamEngineIapiTtftMs) }, - { label: 'TTFT · Service', value: durationValue(latencyDetails?.upstreamEngineServiceTtftMs) }, - { label: 'Token 间隔 · IAPI', value: durationValue(latencyDetails?.upstreamEngineIapiTbtMs) }, - { label: 'Token 间隔 · Service', value: durationValue(latencyDetails?.upstreamEngineServiceTbtMs) }, ] for (const item of performanceItems) { if (item.value !== null)