Add OSL / E2EL x-axis metric as the agentic default / 新增 OSL / E2EL X 轴指标并设为智能体默认

packages/app/cypress/e2e/gpu-compare-agentic-detail.cy.ts

@@ -1,4 +1,4 @@
-import { unlockAgenticGate } from '../support/e2e';
+import { interceptDerivedAgenticMetrics, unlockAgenticGate } from '../support/e2e';
 
 // ---------------------------------------------------------------------------
 // Spec-scoped fixture helpers
@@ -147,6 +147,9 @@ describe('GPU comparison agentic point detail', () => {
       );
       request.reply({ body: result });
     });
+    // The agentic default x-axis mode (OSL / E2EL) fetches derived metrics on
+    // mount; without values every point drops out of the (remapped) data set.
+    interceptDerivedAgenticMetrics();
 
     cy.visit('/inference?g_model=DeepSeek-V4-Pro&i_seq=agentic-traces&i_prec=fp4', {
       onBeforeLoad(win) {
@@ -206,6 +209,7 @@ describe('GPU comparison agentic point detail', () => {
       'agenticAvailability',
     );
     cy.intercept('GET', '/api/v1/benchmarks*', { body: agenticBenchmarks }).as('agenticBenchmarks');
+    interceptDerivedAgenticMetrics();
 
     cy.visit(
       '/inference?g_model=DeepSeek-V4-Pro&i_seq=agentic-traces&i_prec=fp4&i_gpus=b200_sglang,b200_vllm&i_dates=2026-06-12&i_dstart=2026-06-12&i_dend=2026-06-12',

packages/app/cypress/e2e/overlay-legend-remove.cy.ts

@@ -9,7 +9,7 @@
  * appeared to do nothing. The legend toggle already had the overlay-aware
  * split (`unifiedToggle`); the X now shares it (`handleRemoveHwType`).
  */
-import { unlockAgenticGate } from '../support/e2e';
+import { interceptDerivedAgenticMetrics, unlockAgenticGate } from '../support/e2e';
 import {
   countVisible,
   interceptOverlayRun,
@@ -20,13 +20,18 @@ import {
 describe('Official legend X works while an unofficial overlay is loaded', () => {
   before(() => {
     interceptOverlayRun();
+    // The agentic default mode is OSL / E2EL (which suppresses overlays and
+    // fetches derived metrics) — stub the fetch, then switch to Interactivity
+    // where the overlay renders.
+    interceptDerivedAgenticMetrics();
     cy.visit(`/inference?unofficialrun=${OVERLAY_RUN_ID}&i_seq=agentic-traces&i_pctl=p90`, {
       onBeforeLoad(win) {
         win.localStorage.setItem('inferencex-star-modal-dismissed', String(Date.now()));
         unlockAgenticGate(win);
       },
     });
     cy.wait('@unofficialRun');
+    cy.get('[data-testid="x-axis-mode-interactivity"]').click();
     cy.get('[data-testid="chart-figure"]').should('have.length.at.least', 1);
     cy.get('[data-testid="inference-chart-display"] svg .unofficial-overlay-pt').should(
       'have.length',

packages/app/cypress/e2e/overlay-optimal-only.cy.ts

@@ -10,7 +10,7 @@
  * dashed roofline (the monotone spline between C=8 and C=2 passes within
  * ~0.5% of it) while the official twin was hidden.
  */
-import { unlockAgenticGate } from '../support/e2e';
+import { interceptDerivedAgenticMetrics, unlockAgenticGate } from '../support/e2e';
 import {
   countVisible,
   interceptOverlayRun,
@@ -21,13 +21,18 @@ import {
 describe('Overlay points respect Optimal Only (agentic interactivity)', () => {
   before(() => {
     interceptOverlayRun();
+    // The agentic default mode is OSL / E2EL (which suppresses overlays and
+    // fetches derived metrics) — stub the fetch, then switch to the
+    // Interactivity mode this suite is about.
+    interceptDerivedAgenticMetrics();
     cy.visit(`/inference?unofficialrun=${OVERLAY_RUN_ID}&i_seq=agentic-traces&i_pctl=p90`, {
       onBeforeLoad(win) {
         win.localStorage.setItem('inferencex-star-modal-dismissed', String(Date.now()));
         unlockAgenticGate(win);
       },
     });
     cy.wait('@unofficialRun');
+    cy.get('[data-testid="x-axis-mode-interactivity"]').click();
     cy.get('[data-testid="chart-figure"]').should('have.length.at.least', 1);
     cy.get('[data-testid="x-axis-mode-interactivity"]').should(
       'have.attr',

packages/app/cypress/e2e/ttft-x-axis-toggle.cy.ts

@@ -1,26 +1,4 @@
-import { unlockAgenticGate } from '../support/e2e';
-
-const interceptDerivedMetrics = () => {
-  cy.intercept('GET', '/api/v1/derived-agentic-metrics*', (request) => {
-    const ids = new URL(request.url).searchParams.get('ids')?.split(',').filter(Boolean) ?? [];
-    request.reply({
-      body: Object.fromEntries(
-        ids.map((id, index) => [
-          id,
-          {
-            id: Number(id),
-            normalized_session_time_s: 60 + index,
-            p90_prefill_tps_per_user: 100 + index,
-            p75_normalized_e2e_400_s: 8 + index,
-            p90_normalized_e2e_400_s: 12 + index,
-            p75_osl_per_e2el: 40 + index,
-            p90_osl_per_e2el: 25 + index,
-          },
-        ]),
-      ),
-    });
-  }).as('derivedAgenticMetrics');
-};
+import { interceptDerivedAgenticMetrics, unlockAgenticGate } from '../support/e2e';
 
 // This spec exercises the agentic x-axis modes, which only exist when the
 // selected model resolves to the Agentic Traces scenario. The default e2e
@@ -148,10 +126,9 @@ const interceptFixedSequenceData = () => {
 describe('X-Axis Mode Toggle (inference chart)', () => {
   before(() => {
     interceptAgenticData();
-    // Stub derived metrics before the visit: if the agentic DEFAULT x-axis mode
-    // is (or becomes) a derived mode that fetches /derived-agentic-metrics on
-    // mount, the chart must not sit on its loading skeleton.
-    interceptDerivedMetrics();
+    // The agentic default mode is OSL / E2EL, which fetches derived metrics
+    // on first render — stub them before the visit.
+    interceptDerivedAgenticMetrics();
     cy.visit('/inference?i_seq=agentic-traces', {
       onBeforeLoad(win) {
         win.localStorage.setItem('inferencex-star-modal-dismissed', String(Date.now()));
@@ -162,14 +139,32 @@ describe('X-Axis Mode Toggle (inference chart)', () => {
     cy.get('[data-testid="chart-figure"]').should('have.length.at.least', 1);
   });
 
-  it('shows Interactivity by default for the agentic view', () => {
+  it('shows OSL / E2EL by default for the agentic view, as the leftmost option', () => {
     cy.get('[data-testid="scenario-selector"]').should('contain.text', 'Agentic Traces');
     cy.get('[data-testid="x-axis-mode-ttft"]').should('be.visible');
     cy.get('[data-testid="x-axis-mode-e2e"]').should('be.visible');
-    cy.get('[data-testid="x-axis-mode-normalized-e2e"]').should('be.visible');
-    cy.get('[data-testid="x-axis-mode-interactivity"]')
+    cy.get('[data-testid="x-axis-mode-interactivity"]').should('be.visible');
+    cy.get('[data-testid="x-axis-mode-osl-e2el"]')
       .should('be.visible')
       .and('have.attr', 'aria-selected', 'true');
+    // OSL / E2EL leads the mode list for agentic.
+    cy.get('[data-testid="x-axis-mode-buttons"] [role="tab"]')
+      .first()
+      .should('have.attr', 'data-testid', 'x-axis-mode-osl-e2el');
+    cy.get('[data-testid="chart-figure"] h2').should('contain.text', 'P90 OSL / E2EL');
+    cy.get('[data-testid="chart-figure"] svg').should(
+      'contain.text',
+      'P90 OSL / E2EL (tok/s/user)',
+    );
+  });
+
+  it('switches to Interactivity and updates the heading', () => {
+    cy.get('[data-testid="x-axis-mode-interactivity"]').click();
+    cy.get('[data-testid="x-axis-mode-interactivity"]').should(
+      'have.attr',
+      'aria-selected',
+      'true',
+    );
     cy.get('[data-testid="chart-figure"] h2').should('contain.text', 'Interactivity');
   });
 
@@ -230,6 +225,9 @@ describe('X-Axis Mode Toggle (inference chart)', () => {
 
   it('honors explicit label URL overrides for the agentic view', () => {
     interceptAgenticData();
+    // Fresh page load → fresh React Query cache → the default OSL / E2EL
+    // mode refetches derived metrics.
+    interceptDerivedAgenticMetrics();
     cy.visit('/inference?i_seq=agentic-traces&i_label=0&i_advlabel=0&i_linelabel=1', {
       onBeforeLoad(win) {
         win.localStorage.setItem('inferencex-star-modal-dismissed', String(Date.now()));
@@ -255,30 +253,27 @@ describe('X-Axis Mode Toggle (inference chart)', () => {
     cy.get('[data-testid="chart-figure"] svg').should('contain.text', 'P90 End-to-end Latency (s)');
   });
 
-  it('switches to request-level normalized E2E at 400 output tokens', () => {
-    interceptDerivedMetrics();
-    cy.get('[data-testid="x-axis-mode-normalized-e2e"]').click();
-    cy.wait('@derivedAgenticMetrics');
-    cy.get('[data-testid="x-axis-mode-normalized-e2e"]').should(
-      'have.attr',
-      'aria-selected',
-      'true',
-    );
-    cy.get('[data-testid="chart-figure"] h2').should(
-      'contain.text',
-      'P90 Normalized E2E @ 400 output tokens',
-    );
+  it('switches back to request-level OSL / E2EL', () => {
+    // No cy.wait here: the derived metrics were fetched (and stubbed) on the
+    // initial default-mode load and are still fresh in the React Query cache
+    // (staleTime 5 min), so re-entering the mode fires no new request.
+    cy.get('[data-testid="x-axis-mode-osl-e2el"]').click();
+    cy.get('[data-testid="x-axis-mode-osl-e2el"]').should('have.attr', 'aria-selected', 'true');
+    cy.get('[data-testid="chart-figure"] h2').should('contain.text', 'P90 OSL / E2EL');
     cy.get('[data-testid="chart-figure"] svg').should(
       'contain.text',
-      'P90 Normalized E2E @ 400 output tokens (s)',
+      'P90 OSL / E2EL (tok/s/user)',
     );
 
     cy.get('[data-testid="percentile-selector"]').click();
     cy.contains('[role="option"]', 'p75').click();
-    cy.get('[data-testid="chart-figure"] h2').should(
-      'contain.text',
-      'P75 Normalized E2E @ 400 output tokens',
-    );
+    cy.get('[data-testid="chart-figure"] h2').should('contain.text', 'P75 OSL / E2EL');
+
+    // The percentile selector is shared page state for the whole suite —
+    // restore the p90 default so later tests assert against a known value.
+    cy.get('[data-testid="percentile-selector"]').click();
+    cy.contains('[role="option"]', 'p90').click();
+    cy.get('[data-testid="chart-figure"] h2').should('contain.text', 'P90 OSL / E2EL');
   });
 
   it('switches back to Interactivity', () => {
@@ -289,14 +284,52 @@ describe('X-Axis Mode Toggle (inference chart)', () => {
       'true',
     );
     cy.get('[data-testid="chart-figure"] h2').should('contain.text', 'Interactivity');
-    // Percentile was switched to p75 in the previous test — the axis label follows.
+    cy.get('[data-testid="chart-figure"] svg').should(
+      'contain.text',
+      'P90 Interactivity (tok/s/user)',
+    );
+  });
+
+  it('follows the percentile selector in the Interactivity axis label', () => {
+    // Select p75 here rather than inheriting it from another test — the axis
+    // label must track the selector on its own.
+    cy.get('[data-testid="x-axis-mode-interactivity"]').click();
+    cy.get('[data-testid="percentile-selector"]').click();
+    cy.contains('[role="option"]', 'p75').click();
     cy.get('[data-testid="chart-figure"] svg').should(
       'contain.text',
       'P75 Interactivity (tok/s/user)',
     );
   });
 });
 
+describe('X-axis mode URL param', () => {
+  // Regression: the reconcile effect used to run before availability resolved
+  // the sequence. It recorded the fixed-seq placeholder kind, then treated the
+  // switch to agentic as a user-driven kind change and clobbered the
+  // URL-restored mode with the agentic default (OSL / E2EL).
+  it('keeps a URL-restored mode through the agentic sequence resolving', () => {
+    interceptAgenticData();
+    interceptDerivedAgenticMetrics();
+    cy.visit('/inference?i_seq=agentic-traces&i_xmode=interactivity', {
+      onBeforeLoad(win) {
+        win.localStorage.setItem('inferencex-star-modal-dismissed', String(Date.now()));
+        unlockAgenticGate(win);
+      },
+    });
+    cy.get('[data-testid="scenario-selector"]').should('contain.text', 'Agentic Traces');
+    cy.get('[data-testid="x-axis-mode-interactivity"]').should(
+      'have.attr',
+      'aria-selected',
+      'true',
+    );
+    // Assert on the rendered chart too: the clobber happened one tick after
+    // the buttons first painted, so a button-only check could pass too early.
+    cy.get('[data-testid="chart-figure"] h2').should('contain.text', 'Interactivity');
+    cy.get('[data-testid="x-axis-mode-osl-e2el"]').should('have.attr', 'aria-selected', 'false');
+  });
+});
+
 describe('Default scenario', () => {
   it('bare /inference defaults to 8K / 1K even when the model has agentic data', () => {
     // Availability contains BOTH agentic and fixed-seq rows for the default
@@ -411,9 +444,8 @@ const interceptAgenticDataWithOverlay = () => {
 describe('X-Axis Mode Toggle — overlay path (finding #8 regression guard)', () => {
   before(() => {
     interceptAgenticDataWithOverlay();
-    // Same as the main suite: keep the visit independent of the agentic default
-    // x-axis mode (a derived default fetches /derived-agentic-metrics on mount).
-    interceptDerivedMetrics();
+    // Default agentic mode is OSL / E2EL → derived metrics fetch on mount.
+    interceptDerivedAgenticMetrics();
     cy.visit(`/inference?unofficialrun=${OVERLAY_RUN_ID}&i_seq=agentic-traces`, {
       onBeforeLoad(win) {
         win.localStorage.setItem('inferencex-star-modal-dismissed', String(Date.now()));
@@ -463,18 +495,14 @@ describe('X-Axis Mode Toggle — overlay path (finding #8 regression guard)', ()
     });
   });
 
-  it('normalized-e2e mode shows suppression banner for unofficial-run overlays', () => {
-    interceptDerivedMetrics();
-    cy.get('[data-testid="x-axis-mode-normalized-e2e"]').click();
-    cy.get('[data-testid="x-axis-mode-normalized-e2e"]').should(
-      'have.attr',
-      'aria-selected',
-      'true',
-    );
+  it('osl-e2el mode shows suppression banner for unofficial-run overlays', () => {
+    // Derived metrics are cached from the initial default-mode load.
+    cy.get('[data-testid="x-axis-mode-osl-e2el"]').click();
+    cy.get('[data-testid="x-axis-mode-osl-e2el"]').should('have.attr', 'aria-selected', 'true');
     // The suppression message appears because isUnofficialRun is true and the
-    // mode is 'normalized-e2e' (documented in ChartDisplay.tsx ~line 640).
+    // mode is 'osl-e2el' (documented in ChartDisplay.tsx).
     cy.contains(
-      'Normalized E2E requires persisted per-request traces, so unofficial-run overlays are unavailable for this experimental view.',
+      'OSL / E2EL requires persisted per-request traces, so unofficial-run overlays are unavailable for this experimental view.',
     ).should('be.visible');
   });
 });

packages/app/cypress/support/e2e.ts

@@ -37,3 +37,30 @@ export function unlockAgenticGate(win: Window): void {
     // agentic surfaces are public regardless.
   }
 }
+
+/**
+ * Stub `/api/v1/derived-agentic-metrics` with deterministic per-id values.
+ *
+ * OSL / E2EL is the DEFAULT x-axis mode for agentic scenarios, so any spec
+ * that loads the agentic view fires this fetch on mount — without a stub the
+ * fixture server has no DB and the chart sits on its loading skeleton until
+ * the query errors out. Values are index-stable so axis positions are
+ * deterministic. Register BEFORE `cy.visit`.
+ */
+export function interceptDerivedAgenticMetrics(): void {
+  cy.intercept('GET', '/api/v1/derived-agentic-metrics*', (request) => {
+    const ids = new URL(request.url).searchParams.get('ids')?.split(',').filter(Boolean) ?? [];
+    request.reply({
+      body: Object.fromEntries(
+        ids.map((id, index) => [
+          id,
+          {
+            id: Number(id),
+            p75_osl_per_e2el: 40 + index,
+            p90_osl_per_e2el: 25 + index,
+          },
+        ]),
+      ),
+    });
+  }).as('derivedAgenticMetrics');
+}

packages/app/src/app/api/v1/derived-agentic-metrics/route.ts

@@ -35,12 +35,9 @@ const getCachedDerivedAgenticMetrics = cachedQuery(
  *
  * Returns per-id derived metrics computed live from the stored aiperf
  * profile_export.jsonl blobs:
- *  - normalized_session_time_s: mean across sessions of session e2e time
- *    (Σ per-turn request_latency) rescaled by mean_load / session_load.
- *  - p90_prefill_tps_per_user: P90 of per-turn prefill TPS/user (ISL / TTFT)
- *    across every turn in every session.
- *  - p75/p90_normalized_e2e_400_s: percentile of per-request
- *    TTFT + 399 × observed ITL.
+ *  - p75/p90_osl_per_e2el: slow-tail OSL / E2E-latency in tok/s/user,
+ *    computed as 1 / pXX(per-request E2EL/OSL) across every turn in every
+ *    session — plain interactivity charged for the prefill wait.
  *
  * Ids without a trace_replay blob or with unparseable records are omitted.
  */

packages/app/src/components/inference/InferenceContext.tsx

@@ -611,14 +611,20 @@ export function InferenceProvider({
 
   // Reconcile the x-axis mode with the scenario kind:
   //  - On mount with no `i_xmode` URL param: snap to the kind's natural default
-  //    (interactivity for both agentic and fixed-sequence scenarios). The state was initialized
+  //    (OSL / E2EL for agentic — the "north star" e2e-interactivity view —
+  //    and interactivity for fixed-sequence scenarios). The state was initialized
   //    to a SSR-stable constant so server and client render the same DOM; this
   //    effect fixes it up after hydration.
   //  - When the user later switches sequence kinds: snap to the new kind's
   //    natural default (the prior selection was for a different kind, so it
   //    doesn't carry over).
   const lastSeqKindRef = useRef<ReturnType<typeof sequenceKind> | null>(null);
   useEffect(() => {
+    // Wait for availability to resolve the sequence. Before it does,
+    // `effectiveSequence` is a fixed-seq placeholder; recording that kind here
+    // would make the later switch to agentic look like a user-driven kind
+    // change and clobber a URL-restored `i_xmode` with the kind's default.
+    if (!sequenceResolved) return;
     const kind = sequenceKind(effectiveSequence);
     const isInitialMount = lastSeqKindRef.current === null;
     const isAgenticOnlyMode = isAgenticOnlyXAxisMode(selectedXAxisMode);
@@ -642,8 +648,8 @@ export function InferenceProvider({
       // — fall through to the default snap below.
       return;
     }
-    handleSetXAxisMode('interactivity');
-  }, [effectiveSequence, selectedXAxisMode, handleSetXAxisMode]);
+    handleSetXAxisMode(kind === 'agentic' ? 'osl-e2el' : 'interactivity');
+  }, [sequenceResolved, effectiveSequence, selectedXAxisMode, handleSetXAxisMode]);
 
   // Reconcile selectedE2eXAxisMetric whenever the mode, sequence kind, or
   // agentic percentile changes. For fixed-seq the JSONB only carries