fix(inference): resolve scenario run state at the provider

Filter workflow runs by model, scenario, and precision before global run auto-selection or URL synchronization. Invalid scenario dates and run IDs now resolve synchronously, so July 4 single-turn state cannot leak into Agentic Traces. Remove the downstream fallback-heavy filtering and add focused date and run-coverage regressions.

中文：在全局运行自动选择和 URL 同步之前，按模型、场景和精度过滤 workflow runs。无效的场景日期与运行 ID 现在会同步纠正，避免 7 月 4 日的 single-turn 状态泄漏到 Agentic Traces；同时移除下游复杂回退逻辑并补充定向回归测试。

Author: cquil11

packages/app/cypress/support/mock-data.ts

@@ -447,7 +447,6 @@ export function createMockGlobalFilterContext(
     availabilityRows: undefined,
     workflowInfo: null,
     availableRuns: {},
-    runConfigs: [],
     workflowLoading: false,
     workflowError: null,
     ...overrides,

packages/app/src/components/GlobalFilterContext.tsx

@@ -36,7 +36,9 @@ import {
 import { computeAutoSwitchDecision } from '@/lib/unofficial-run-auto-switch';
 import { countCurvesByPrecision, resolveEffectivePrecisions } from '@/lib/default-precisions';
 import { resolveEffectiveSequence } from '@/lib/default-sequence';
-import type { AvailabilityRow, RunConfigRow, WorkflowInfoResponse } from '@/lib/api';
+import { scenarioRunIdsForDate } from '@/lib/run-configs';
+import { resolveRunDate } from '@/lib/run-date';
+import type { AvailabilityRow, WorkflowInfoResponse } from '@/lib/api';
 
 const RUNDATE_RE = /^\d{4}-\d{2}-\d{2}$/u;
 const RUNID_RE = /^[A-Za-z0-9_-]{1,64}$/u;
@@ -107,14 +109,6 @@ export interface GlobalFilterContextType {
   // Workflow info
   workflowInfo: { runInfoBySequence: Record<string, RunInfo> }[] | null;
   availableRuns: Record<string, RunInfo>;
-  /**
-   * Per-(run, config) coverage for the current date — which workflow runs
-   * produced benchmark data for which model / scenario / precision. Data-driven
-   * (from the benchmark rows), so it enumerates every run on the date including
-   * ones without a changelog entry. The run picker uses this to scope its list
-   * to the selected model + scenario (see `scenarioRunIdsForDate`).
-   */
-  runConfigs: RunConfigRow[];
   workflowLoading: boolean;
   workflowError: string | null;
 }
@@ -419,14 +413,10 @@ export function GlobalFilterProvider({
     setSelectedRunDateRev((v) => v + 1);
   }, []);
 
-  const effectiveRunDate = useMemo(() => {
-    if (availableDates.length === 0) return selectedRunDate;
-    const latest = availableDates.at(-1)!;
-    if (userPickedDateRef.current && selectedRunDate && availableDates.includes(selectedRunDate)) {
-      return selectedRunDate;
-    }
-    return latest;
-  }, [availableDates, selectedRunDate]);
+  const effectiveRunDate = useMemo(
+    () => resolveRunDate(availableDates, selectedRunDate, userPickedDateRef.current),
+    [availableDates, selectedRunDate],
+  );
 
   // Sync selectedRunDate state when effectiveRunDate changes
   useEffect(() => {
@@ -445,18 +435,33 @@ export function GlobalFilterProvider({
 
   const workflowError = workflowQueryError ? workflowQueryError.message : null;
 
-  const availableRuns = useMemo(
-    () => (workflowData ? buildRunInfo(workflowData) : {}),
-    [workflowData],
-  );
+  const dateRuns = useMemo(() => (workflowData ? buildRunInfo(workflowData) : {}), [workflowData]);
 
   const runConfigs = useMemo(() => workflowData?.runConfigs ?? [], [workflowData]);
 
+  // Keep run selection and g_runid scenario-safe at their source. Filtering
+  // later in InferenceContext leaves the global single-turn run ID alive.
+  const availableRuns = useMemo(() => {
+    const runIds = scenarioRunIdsForDate(
+      runConfigs,
+      dbModelKeys,
+      effectiveSequence,
+      effectivePrecisions,
+    );
+    return Object.fromEntries(Object.entries(dateRuns).filter(([runId]) => runIds.has(runId)));
+  }, [dateRuns, runConfigs, dbModelKeys, effectiveSequence, effectivePrecisions]);
+
   const workflowInfo = useMemo(
     () => (Object.keys(availableRuns).length > 0 ? [{ runInfoBySequence: availableRuns }] : null),
     [availableRuns],
   );
 
+  const effectiveSelectedRunId = useMemo(() => {
+    const runIds = Object.keys(availableRuns);
+    if (runIds.includes(selectedRunId)) return selectedRunId;
+    return runIds.reduce((latest, runId) => (runId > latest ? runId : latest), '');
+  }, [availableRuns, selectedRunId]);
+
   // Auto-select latest run ID when availableRuns change
   const urlInitRef = useRef({ runIdApplied: false });
 
@@ -494,8 +499,10 @@ export function GlobalFilterProvider({
     }
     setUrlParams({
       g_model: selectedModel,
-      g_rundate: selectedRunDate,
-      g_runid: selectedRunId,
+      // Never write a stale URL date after model/scenario availability has
+      // already resolved it to a valid date (e.g. Agentic + 2026-07-04).
+      g_rundate: effectiveRunDate,
+      g_runid: effectiveSelectedRunId,
       // Don't pin the sequence to the URL until it's resolved from real
       // availability — writing the pre-load placeholder (8k/1k) would clobber a
       // shared `?i_seq=agentic-traces` link before the model's availability
@@ -507,8 +514,8 @@ export function GlobalFilterProvider({
     });
   }, [
     selectedModel,
-    selectedRunDate,
-    selectedRunId,
+    effectiveRunDate,
+    effectiveSelectedRunId,
     effectiveSequence,
     sequenceResolved,
     effectivePrecisions,
@@ -530,7 +537,7 @@ export function GlobalFilterProvider({
       selectedRunDate: effectiveRunDate,
       setSelectedRunDate: setSelectedRunDateManual,
       selectedRunDateRev,
-      selectedRunId,
+      selectedRunId: effectiveSelectedRunId,
       setSelectedRunId,
       availableModels,
       availableSequences,
@@ -540,7 +547,6 @@ export function GlobalFilterProvider({
       availabilityRows,
       workflowInfo,
       availableRuns,
-      runConfigs,
       workflowLoading,
       workflowError,
     }),
@@ -554,15 +560,14 @@ export function GlobalFilterProvider({
       effectiveRunDate,
       setSelectedRunDateManual,
       selectedRunDateRev,
-      selectedRunId,
+      effectiveSelectedRunId,
       availableModels,
       availableSequences,
       availablePrecisions,
       availableDates,
       availabilityRows,
       workflowInfo,
       availableRuns,
-      runConfigs,
       workflowLoading,
       workflowError,
     ],

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

@@ -63,7 +63,7 @@ import {
   resolveExclusionToggle,
   type ExclusionConflictPolicy,
 } from '@/lib/exclusion';
-import { filterRunsByModel, getDisplayLabel, restrictRunsToScenario } from '@/lib/utils';
+import { filterRunsByModel, getDisplayLabel } from '@/lib/utils';
 
 import {
   isAgenticOnlyXAxisMode,
@@ -72,7 +72,6 @@ import {
   type XAxisMode,
 } from './hooks/useChartData';
 import { resolveComparisonEntries } from './utils/comparisonEntry';
-import { scenarioRunIdsForDate } from './utils/runEnumeration';
 import { resolveLabelState, serializeLabelState } from './utils/label-defaults';
 import {
   EMPTY_QUICK_FILTERS,
@@ -136,7 +135,6 @@ export function InferenceProvider({
     availabilityRows,
     workflowInfo,
     availableRuns,
-    runConfigs,
     workflowError,
   } = useGlobalFilters();
 
@@ -370,50 +368,13 @@ export function InferenceProvider({
     [selectedModel],
   );
 
-  // DB model keys for the selected display model (e.g. ['dsv4']). Used both by
-  // the scenario run scoping below and the GPU comparison date picker further down.
-  const dbModelKeys = useMemo<string[]>(
-    () => DISPLAY_MODEL_TO_DB[selectedModel] ?? [selectedModel],
-    [selectedModel],
-  );
-
-  const changelogFilteredRuns = useMemo(
+  const filteredAvailableRuns = useMemo(
     () => filterRunsByModel(availableRuns, modelPrefixes, [...effectivePrecisions]),
     [availableRuns, modelPrefixes, effectivePrecisions],
   );
 
-  // Run ids that actually produced data for the selected model + scenario on the
-  // date, derived from per-(run, config) coverage (independent of the chart's
-  // "as of run" query, so no circular dependency). `/api/v1/workflow-info`
-  // returns every run on a date across all models/scenarios, so without this a
-  // same-day run for a different scenario (e.g. a single_turn sweep while viewing
-  // Agentic Traces) would leak into the picker and poison the "as of run" cutoff.
-  const scenarioRunIds = useMemo(
-    () =>
-      scenarioRunIdsForDate(runConfigs, dbModelKeys, effectiveSequence, [...effectivePrecisions]),
-    [runConfigs, dbModelKeys, effectiveSequence, effectivePrecisions],
-  );
-
-  // The picker list: the changelog/precision-scoped runs, further restricted to
-  // the ones that shipped data for the selected scenario. When the date has
-  // coverage rows but none for this scenario (e.g. only single_turn sweeps ran
-  // that day while viewing Agentic Traces) the picker hides (null) rather than
-  // listing other-scenario runs; only when coverage data is unavailable
-  // altogether (old dates / JSON snapshots) does it fall back to the
-  // changelog-scoped list so the selector still renders.
-  const filteredAvailableRuns = useMemo(
-    () =>
-      restrictRunsToScenario(
-        changelogFilteredRuns,
-        availableRuns,
-        scenarioRunIds,
-        runConfigs.length > 0,
-      ),
-    [changelogFilteredRuns, availableRuns, scenarioRunIds, runConfigs],
-  );
-
   const effectiveSelectedRunId = useMemo(() => {
-    if (!filteredAvailableRuns) return selectedRunId;
+    if (!filteredAvailableRuns) return '';
     const filteredRunIds = Object.keys(filteredAvailableRuns);
     if (filteredRunIds.length === 0 || filteredRunIds.includes(selectedRunId)) return selectedRunId;
     return filteredRunIds.reduce((max, id) => (id > max ? id : max), filteredRunIds[0]);
@@ -523,6 +484,11 @@ export function InferenceProvider({
   );
 
   // For GPU comparison date picker — use shared availability data from global filters
+  const dbModelKeys = useMemo<string[]>(
+    () => DISPLAY_MODEL_TO_DB[selectedModel] ?? [selectedModel],
+    [selectedModel],
+  );
+
   const dateRangeAvailableDates = useMemo(() => {
     if (selectedGPUs.length === 0) return availableDates;
     if (!availabilityRows) return availableDates;

packages/app/src/components/inference/utils/runEnumeration.test.ts

@@ -2,7 +2,7 @@ import { describe, expect, it } from 'vitest';
 
 import type { RunConfigRow } from '@/lib/api';
 
-import { dataRunsForDate, scenarioRunIdsForDate } from './runEnumeration';
+import { dataRunsForDate } from './runEnumeration';
 
 function rc(over: Partial<RunConfigRow>): RunConfigRow {
   return {
@@ -24,16 +24,6 @@ function rc(over: Partial<RunConfigRow>): RunConfigRow {
   };
 }
 
-/** A single_turn (fixed-seq) run config for the given isl/osl. */
-function single(over: Partial<RunConfigRow>): RunConfigRow {
-  return rc({ benchmark_type: 'single_turn', isl: 8192, osl: 1024, ...over });
-}
-
-/** An agentic_traces run config (null isl/osl, as ingested for agentic rows). */
-function agentic(over: Partial<RunConfigRow>): RunConfigRow {
-  return rc({ benchmark_type: 'agentic_traces', isl: null, osl: null, ...over });
-}
-
 const SCOPE = {
   modelDbKeys: ['minimaxm3'],
   selectedGPUs: ['mi300x_vllm'],
@@ -121,66 +111,3 @@ describe('dataRunsForDate', () => {
     expect(dataRunsForDate([rc({ model: 'dsr1' })], SCOPE)).toEqual([]);
   });
 });
-
-// Mirrors the repro: on one date the same model has a single_turn run and an
-// agentic run; each scenario must list ONLY its own run.
-const ids = (rows: RunConfigRow[], model: string[], seq: string, prec: string[] = []) =>
-  [...scenarioRunIdsForDate(rows, model, seq, prec)].toSorted();
-
-describe('scenarioRunIdsForDate', () => {
-  it('agentic scenario excludes runs that only produced single_turn data', () => {
-    const rows = [
-      agentic({ github_run_id: 28955639528, model: 'dsv4' }), // dsv4 agentic
-      single({ github_run_id: 28900000001, model: 'dsv4' }), // dsv4 single_turn (leaks today)
-      single({ github_run_id: 28900000002, model: 'glm5' }), // other model
-    ];
-    expect(ids(rows, ['dsv4'], 'agentic-traces')).toEqual(['28955639528']);
-  });
-
-  it('single_turn scenario excludes agentic-only runs', () => {
-    const rows = [
-      agentic({ github_run_id: 1, model: 'dsv4' }),
-      single({ github_run_id: 2, model: 'dsv4' }),
-    ];
-    expect(ids(rows, ['dsv4'], '8k/1k')).toEqual(['2']);
-  });
-
-  it('lists a run that produced data for both scenarios under each scenario', () => {
-    const rows = [
-      agentic({ github_run_id: 42, model: 'dsv4' }),
-      single({ github_run_id: 42, model: 'dsv4' }), // same run, both types
-    ];
-    expect(ids(rows, ['dsv4'], 'agentic-traces')).toEqual(['42']);
-    expect(ids(rows, ['dsv4'], '8k/1k')).toEqual(['42']);
-  });
-
-  it('scopes to the selected model DB keys', () => {
-    const rows = [
-      agentic({ github_run_id: 1, model: 'dsv4' }),
-      agentic({ github_run_id: 2, model: 'glm5' }),
-    ];
-    expect(ids(rows, ['dsv4'], 'agentic-traces')).toEqual(['1']);
-  });
-
-  it('respects precision scoping when precisions are provided', () => {
-    const rows = [
-      agentic({ github_run_id: 1, model: 'dsv4', precision: 'fp4' }),
-      agentic({ github_run_id: 2, model: 'dsv4', precision: 'fp8' }),
-    ];
-    expect(ids(rows, ['dsv4'], 'agentic-traces', ['fp4'])).toEqual(['1']);
-    // Empty precisions = no precision constraint.
-    expect(ids(rows, ['dsv4'], 'agentic-traces')).toEqual(['1', '2']);
-  });
-
-  it('dedupes a run appearing across multiple matching configs', () => {
-    const rows = [
-      agentic({ github_run_id: 7, model: 'dsv4', hardware: 'b200' }),
-      agentic({ github_run_id: 7, model: 'dsv4', hardware: 'gb200' }),
-    ];
-    expect(ids(rows, ['dsv4'], 'agentic-traces')).toEqual(['7']);
-  });
-
-  it('returns an empty set when there is no coverage data', () => {
-    expect(scenarioRunIdsForDate([], ['dsv4'], 'agentic-traces').size).toBe(0);
-  });
-});

packages/app/src/components/inference/utils/runEnumeration.ts

@@ -15,8 +15,6 @@
  * chart keys them.
  */
 
-import { rowToSequence } from '@semianalysisai/inferencex-constants';
-
 import type { AggDataEntry } from '@/components/inference/types';
 import type { RunConfigRow } from '@/lib/api';
 import { getHardwareKey } from '@/lib/chart-utils';
@@ -80,38 +78,3 @@ export function dataRunsForDate(runConfigs: RunConfigRow[], scope: RunScope): Da
 
   return [...byRun.values()].toSorted((a, b) => a.runStartedAt.localeCompare(b.runStartedAt));
 }
-
-/**
- * GitHub run ids (as strings) that produced benchmark data for the given model
- * DB keys + scenario (sequence) — and, when `precisions` is non-empty, only for
- * those precisions — on a date. Derived from per-(run, config) coverage
- * ({@link RunConfigRow}, i.e. the benchmark rows themselves), so a run that
- * shipped data without a changelog entry still counts.
- *
- * The run picker uses this to list ONLY the runs that actually produced data for
- * the currently selected model + scenario. `/api/v1/workflow-info` returns every
- * run on a date across all models and scenarios, so without this scoping a
- * same-day run for a different scenario (e.g. a `single_turn` sweep while the
- * user is viewing Agentic Traces) leaks into the picker — and selecting it
- * poisons the "as of run" cutoff, blanking the chart.
- *
- * Scenario matching mirrors the chart's own row filter (`rowToSequence(row) ===
- * selectedSequence` in useChartData), so the picker and the plotted data always
- * agree on which runs are relevant.
- */
-export function scenarioRunIdsForDate(
-  runConfigs: RunConfigRow[],
-  modelDbKeys: string[],
-  sequence: string,
-  precisions: string[] = [],
-): Set<string> {
-  const precSet = precisions.length > 0 ? new Set(precisions) : null;
-  const ids = new Set<string>();
-  for (const rc of runConfigs) {
-    if (!modelDbKeys.includes(rc.model)) continue;
-    if (precSet && !precSet.has(rc.precision)) continue;
-    if (rowToSequence(rc) !== sequence) continue;
-    ids.add(String(rc.github_run_id));
-  }
-  return ids;
-}