perf(ci): surface keyed-list allocation in the /perf comment

tests/stress_perf/METHODOLOGY.md

@@ -257,8 +257,11 @@ a real keyed diff every tick. The workload is deterministic (fixed RNG seed, con
 row count — insertions paired with removals) so `main` and PR compare identical edit
 sequences, and its rows' labels are content-stable so a moved row's text never changes
 — isolating the **structural** (keyed-diff) signal from per-cell property updates. It
-reports the four headline metrics in its own table under the same interleaving, reps,
-warm-up, and 95%-CI gating as the headline leg, and is opt-out via
+reports the four headline metrics in its own table, plus an **allocation** sub-table
+(`Alloc bytes/render`, `Gen0 GC / 1k renders`) — the sensitive macro signal for
+keyed-diff *allocation* reductions the positional StocksGrid alloc table can't isolate,
+rendered only when the keyed leg reports the metric — all under the same interleaving,
+reps, warm-up, and 95%-CI gating as the headline leg, and is opt-out via
 `-IncludeKeyedList $false`. See
 [`ci/README.md`](ci/README.md#the-comment).
 

tests/stress_perf/ci/PerfLib.Tests.ps1

@@ -507,6 +507,45 @@ $noKeyedComment = Format-PerfComment -Main $main -Pr $pr -WinUI3 $null -Rust $nu
 Assert-True (-not ($noKeyedComment -like '*Keyed-list workload*')) 'keyed-list table omitted when keyed aggregates null'
 
 
+# ── Keyed-list allocation sub-table: shared PerfAllocMetricSpec over keyed aggregates ──
+# The keyed leg also renders an allocation sub-table (alloc bytes/render + Gen0 GC / 1k
+# renders) — the macro signal for keyed-DIFF allocation reductions. Alloc moves DOWN
+# main->PR (~20%, an improvement on a lower-is-better metric); tiny jitter keeps each
+# paired CI off 0. Magnitudes mirror a real StressPerf.KeyedList @50% run (~328K
+# bytes/render, ~63 Gen0/1k).
+$keyedAllocMain = Measure-PerfRuns -Runs @(
+    [pscustomobject]@{ RendersPerSec = 18.5; AvgReconcileMs = 6.98; AvgDiffMs = 6.86; AvgMemoryMB = 186; AllocBytesPerRender = 328000; Gen0PerKRenders = 63.2; Gen0 = 6; Gen1 = 2; Gen2 = 1; TotalRenders = 96; DurationSeconds = 5 }
+    [pscustomobject]@{ RendersPerSec = 18.6; AvgReconcileMs = 6.98; AvgDiffMs = 6.86; AvgMemoryMB = 186; AllocBytesPerRender = 328200; Gen0PerKRenders = 63.4; Gen0 = 6; Gen1 = 2; Gen2 = 1; TotalRenders = 96; DurationSeconds = 5 }
+    [pscustomobject]@{ RendersPerSec = 18.4; AvgReconcileMs = 6.98; AvgDiffMs = 6.86; AvgMemoryMB = 186; AllocBytesPerRender = 327800; Gen0PerKRenders = 63.0; Gen0 = 6; Gen1 = 2; Gen2 = 1; TotalRenders = 96; DurationSeconds = 5 }
+)
+$keyedAllocPr = Measure-PerfRuns -Runs @(
+    [pscustomobject]@{ RendersPerSec = 18.5; AvgReconcileMs = 6.98; AvgDiffMs = 6.86; AvgMemoryMB = 186; AllocBytesPerRender = 262000; Gen0PerKRenders = 50.2; Gen0 = 5; Gen1 = 2; Gen2 = 1; TotalRenders = 96; DurationSeconds = 5 }
+    [pscustomobject]@{ RendersPerSec = 18.6; AvgReconcileMs = 6.98; AvgDiffMs = 6.86; AvgMemoryMB = 186; AllocBytesPerRender = 262200; Gen0PerKRenders = 50.4; Gen0 = 5; Gen1 = 2; Gen2 = 1; TotalRenders = 96; DurationSeconds = 5 }
+    [pscustomobject]@{ RendersPerSec = 18.4; AvgReconcileMs = 6.98; AvgDiffMs = 6.86; AvgMemoryMB = 186; AllocBytesPerRender = 261800; Gen0PerKRenders = 50.0; Gen0 = 5; Gen1 = 2; Gen2 = 1; TotalRenders = 96; DurationSeconds = 5 }
+)
+$keyedAllocSection = Format-PerfKeyedListSection -MainKeyed $keyedAllocMain -PrKeyed $keyedAllocPr -Percent 50
+$keyedAllocText = $keyedAllocSection -join "`n"
+Assert-Match $keyedAllocText 'Allocation (keyed-list)' 'keyed section renders the allocation sub-table when alloc present'
+Assert-Match $keyedAllocText 'Alloc bytes/render'      'keyed alloc sub-table has bytes/render row'
+Assert-Match $keyedAllocText 'Gen0 GC / 1k renders'    'keyed alloc sub-table has Gen0 row'
+$keyedAllocRow = ($keyedAllocSection | Where-Object { $_ -match 'Alloc bytes/render' }) -join ' '
+Assert-Match $keyedAllocRow 'improvement' 'keyed alloc DOWN main->PR reads improvement (lower-is-better honored)'
+# The allocation sub-table sits AFTER the keyed headline metrics table within the section.
+$idxKeyedHead  = $keyedAllocText.IndexOf('Avg Reconcile')
+$idxKeyedAlloc = $keyedAllocText.IndexOf('Allocation (keyed-list)')
+Assert-True (($idxKeyedHead -ge 0) -and ($idxKeyedHead -lt $idxKeyedAlloc)) 'keyed alloc sub-table follows the keyed headline metrics table'
+
+# Omitted when the keyed aggregates carry no alloc metrics (legacy keyed head). The
+# $keyedMain/$keyedPr aggregates above were built without alloc fields.
+Assert-True (-not ($keyedSectionText -like '*Allocation (keyed-list)*')) 'keyed alloc sub-table omitted when keyed aggregates lack alloc'
+
+# In a full comment the positional StocksGrid allocation table and the keyed allocation
+# sub-table are DISTINCT, separately-labelled tables (positional vs keyed workload allocs).
+$bothAllocComment = Format-PerfComment -Main $allocMain -Pr $allocPr -WinUI3 $null -Rust $null -MainKeyed $keyedAllocMain -PrKeyed $keyedAllocPr -Context $ctx
+Assert-Match $bothAllocComment 'Allocation (Reactor)'    'full comment keeps the StocksGrid allocation table'
+Assert-Match $bothAllocComment 'Allocation (keyed-list)' 'full comment adds the distinct keyed allocation sub-table'
+
+
 # ── Reconciler micro-suite: Read-MicroBenchResults / comparison / render ──────
 function New-MicroRow {
     param([string]$BenchId, [string]$Name, [string]$Variant, [int]$Rep, [double]$MeanNs, [double]$AllocBytes, [string]$Status = 'ok', [int]$Iterations = 1)

tests/stress_perf/ci/PerfLib.ps1

@@ -745,9 +745,10 @@ function Format-PerfSkipFloorSection {
 function Format-PerfKeyedListSection {
     <#
     .SYNOPSIS
-        Render the keyed-list workload table: the four headline metrics measured on
-        StressPerf.KeyedList — a ~500-row stably keyed list whose rows are reordered /
-        inserted / removed each tick. Empty array when there is nothing to show.
+        Render the keyed-list workload section: the four headline metrics plus an
+        allocation sub-table measured on StressPerf.KeyedList — a ~500-row stably keyed
+        list whose rows are reordered / inserted / removed each tick. Empty array when
+        there is nothing to show.
     .DESCRIPTION
         Unlike the positional StocksGrid headline/skip-floor legs (whose cells mutate
         in place by index, always taking ChildReconciler.ReconcilePositional), this is
@@ -756,9 +757,13 @@ function Format-PerfKeyedListSection {
         the sensitive macro measure for keyed-diff optimizations (keyed-list diff,
         keyed structural-skip) that the StocksGrid workload can never exercise. Reuses
         the same paired-Δ 95% CI machinery (Get-PerfDelta over the index-aligned
-        per-run samples) as the headline table. Returns an empty array when either
-        aggregate is $null (keyed-list leg disabled, build omitted, or one side
-        produced no metrics), so the caller renders nothing.
+        per-run samples) as the headline table. Also appends an **allocation** sub-table
+        — the shared PerfAllocMetricSpec (alloc bytes/render + Gen0 GC / 1k renders) over
+        the keyed aggregates — the sensitive macro signal for keyed-DIFF allocation
+        reductions that the positional StocksGrid allocation table can never isolate;
+        rendered only when the keyed leg reported allocation metrics. Returns an empty
+        array when either aggregate is $null (keyed-list leg disabled, build omitted, or
+        one side produced no metrics), so the caller renders nothing.
     .PARAMETER MainKeyed  Aggregated baseline keyed-list metrics (Measure-PerfRuns), or $null.
     .PARAMETER PrKeyed     Aggregated PR-head keyed-list metrics, or $null.
     .PARAMETER Percent     The mutation percent the keyed-list leg ran at (heading / preamble).
@@ -791,6 +796,38 @@ function Format-PerfKeyedListSection {
             (Get-PerfStatusGlyph $delta.Status)))
     }
     $lines.Add('')
+
+    # Allocation sub-table for the keyed workload: the shared PerfAllocMetricSpec
+    # (Alloc bytes/render, Gen0 GC / 1k renders) rendered over the keyed aggregates with
+    # the identical paired-Δ 95% CI machinery used above. This is the sensitive MACRO
+    # signal for keyed-DIFF allocation reductions — allocBytesPerRender tracks reorder
+    # volume on the keyed (ReconcileKeyed → ReconcileKeyedMiddle / LIS) path, an alloc
+    # signal the positional StocksGrid allocation table can never isolate. Rendered only
+    # when the keyed leg reported allocation metrics (every StressPerf.KeyedList build
+    # does; n/a only for a legacy head opened before the metric landed).
+    $hasKeyedAlloc = ($null -ne $MainKeyed.AllocBytesPerRender) -or ($null -ne $PrKeyed.AllocBytesPerRender) -or
+                     ($null -ne $MainKeyed.Gen0PerKRenders) -or ($null -ne $PrKeyed.Gen0PerKRenders)
+    if ($hasKeyedAlloc) {
+        $lines.Add('**Allocation (keyed-list)** &mdash; lower is better')
+        $lines.Add('')
+        $lines.Add('| Metric | `main` (baseline) | This PR | Δ (95% CI) | Status |')
+        $lines.Add('|---|--:|--:|--:|:--|')
+        foreach ($m in $script:PerfAllocMetricSpec) {
+            $bVal = $MainKeyed.($m.Key)
+            $pVal = $PrKeyed.($m.Key)
+            $spread = [math]::Max([double]$MainKeyed."$($m.Key)Spread", [double]$PrKeyed."$($m.Key)Spread")
+            $delta = Get-PerfDelta -Baseline $bVal -Candidate $pVal -LowerIsBetter $m.LowerIsBetter -SpreadPct $spread `
+                -BaselineSamples $MainKeyed."$($m.Key)Samples" -CandidateSamples $PrKeyed."$($m.Key)Samples"
+            $lines.Add(('| {0} {1} | {2} | {3} | {4} | {5} |' -f `
+                    $m.Label, $m.Arrow, `
+                (Format-PerfNumber $bVal $m.Digits), `
+                (Format-PerfNumber $pVal $m.Digits), `
+                (Format-PerfDeltaCell $delta), `
+                (Get-PerfStatusGlyph $delta.Status)))
+        }
+        $lines.Add('')
+    }
+
     return $lines.ToArray()
 }
 

tests/stress_perf/ci/README.md

@@ -232,7 +232,11 @@ Several tables plus footnotes:
   `ReconcileKeyedMiddle`, the LIS-based minimal-move pass) instead of the positional
   re-walk the StocksGrid tables measure — so this is the sensitive macro signal for
   **keyed-diff** optimizations (keyed-list diff, keyed structural-skip) that the
-  positional cells can never exercise. Same paired-CI gating as Table 1; omitted
+  positional cells can never exercise. It also carries its own **allocation**
+  sub-table (`Alloc bytes/render` + `Gen0 GC / 1k renders` over the keyed aggregates,
+  same spec as the StocksGrid allocation table) — the sensitive macro signal for
+  keyed-diff *allocation* reductions the positional alloc table can't isolate, rendered
+  only when the keyed leg reports the metric. Same paired-CI gating as Table 1; omitted
   when `-IncludeKeyedList $false`, the workload build fails, or a side produces no
   metrics.
 - **Reconciler micro-benchmarks** — per-bench `ns/op` and `B/op` from the