test(app): add PR0.2 perf comparator gate

.github/workflows/perf-probe-baseline.yml

@@ -7,6 +7,7 @@ on:
       - "packages/app/e2e/perf/**"
       - "packages/app/e2e/fixtures.ts"
       - "packages/app/package.json"
+      - "packages/app/script/compare-perf.ts"
       - "packages/app/script/e2e-local.ts"
       - "packages/app/src/testing/perf-metrics*"
   workflow_dispatch:
@@ -18,11 +19,20 @@ jobs:
   perf-probe-baseline:
     runs-on: ubuntu-latest
     timeout-minutes: 30
+    env:
+      PERF_ARTIFACT_DIR: ${{ github.workspace }}/perf-artifacts
     steps:
       - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # actions/checkout@v6
         with:
+          path: head
           persist-credentials: false
 
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # actions/checkout@v6
+        with:
+          path: base
+          persist-credentials: false
+          ref: ${{ github.event.pull_request.base.sha || github.sha }}
+
       - uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # actions/[email protected]
         with:
           node-version: "24"
@@ -34,25 +44,52 @@ jobs:
       - uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # actions/cache@v5
         with:
           path: ~/.bun/install/cache
-          key: bun-${{ runner.os }}-${{ hashFiles('bun.lock') }}
+          key: bun-${{ runner.os }}-${{ hashFiles('head/bun.lock', 'base/bun.lock') }}
           restore-keys: |
             bun-${{ runner.os }}-
 
       - uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # actions/cache@v5
         with:
           path: ${{ github.workspace }}/.playwright-browsers
-          key: playwright-${{ runner.os }}-${{ hashFiles('packages/app/package.json', 'bun.lock') }}
+          key: playwright-${{ runner.os }}-${{ hashFiles('head/packages/app/package.json', 'head/bun.lock', 'base/packages/app/package.json', 'base/bun.lock') }}
+
+      - name: Install head dependencies
+        working-directory: head
+        run: bun install --frozen-lockfile
 
-      - run: bun install --frozen-lockfile
+      - name: Install base dependencies
+        working-directory: base
+        run: bun install --frozen-lockfile
 
       - name: Install Playwright browsers
-        working-directory: packages/app
+        working-directory: head/packages/app
         run: bunx playwright install --with-deps chromium
 
-      - name: Run perf probe baseline
+      - name: Sync perf harness into base checkout
+        run: |
+          rsync -a --delete head/packages/app/e2e/perf/ base/packages/app/e2e/perf/
+          cp head/packages/app/src/testing/perf-metrics.ts base/packages/app/src/testing/perf-metrics.ts
+
+      - name: Run perf probe baseline (base)
         env:
           CI: "true"
-        run: bun --cwd packages/app test:e2e:local:perf
+          PAWWORK_PERF_BRANCH: base
+          PAWWORK_PERF_OUTPUT: ${{ github.workspace }}/perf-artifacts/perf-base.json
+        run: bun --cwd base/packages/app test:e2e:local:perf
+
+      - name: Run perf probe baseline (head)
+        env:
+          CI: "true"
+          PAWWORK_PERF_BRANCH: head
+          PAWWORK_PERF_OUTPUT: ${{ github.workspace }}/perf-artifacts/perf-head.json
+        run: bun --cwd head/packages/app test:e2e:local:perf
+
+      - name: Compare base and head perf baselines
+        run: >
+          bun head/packages/app/script/compare-perf.ts
+          --base "${PERF_ARTIFACT_DIR}/perf-base.json"
+          --head "${PERF_ARTIFACT_DIR}/perf-head.json"
+          --output "${PERF_ARTIFACT_DIR}/perf-compare.json"
 
       - name: Upload perf probe artifacts
         if: always()
@@ -62,6 +99,8 @@ jobs:
           if-no-files-found: ignore
           retention-days: 7
           path: |
-            packages/app/e2e/perf-results
-            packages/app/e2e/playwright-report
-            packages/app/e2e/test-results
+            perf-artifacts
+            base/packages/app/e2e/playwright-report
+            base/packages/app/e2e/test-results
+            head/packages/app/e2e/playwright-report
+            head/packages/app/e2e/test-results

packages/app/e2e/perf/perf-probe.spec.ts

@@ -8,6 +8,7 @@ import { sessionPath } from "../utils"
 import { installPerfProbe, resetPerfProbe, snapshotPerfProbe, summarizeScenarioRuns } from "./probe"
 
 const outputPath = process.env.PAWWORK_PERF_OUTPUT ?? path.join(process.cwd(), "e2e", "perf-results", "pr0.1-baseline.json")
+const perfBranch = process.env.PAWWORK_PERF_BRANCH ?? "dev"
 
 const longMarkdown = [
   "# Baseline stream",
@@ -73,6 +74,11 @@ async function settleFrames(page: Parameters<typeof snapshotPerfProbe>[0], count
   }, count)
 }
 
+async function cooldownAfterRun(page: Parameters<typeof snapshotPerfProbe>[0]) {
+  await settleFrames(page, 6)
+  await page.waitForTimeout(250)
+}
+
 async function navigateProjectHome(page: Parameters<typeof snapshotPerfProbe>[0], directory: string) {
   await page.goto(sessionPath(directory))
   await expect(page.locator('[data-component="session-new-home"]')).toBeVisible()
@@ -148,9 +154,10 @@ test.describe("PR0.1 perf probe baseline", () => {
       await settleFrames(page, 3)
       await page.keyboard.press("Escape")
       runs.push(await snapshotPerfProbe(page))
+      if (run < 2) await cooldownAfterRun(page)
     }
 
-    scenarioResults.push(summarizeScenarioRuns({ branch: "dev", scenario: "homepage-cold", runs }))
+    scenarioResults.push(summarizeScenarioRuns({ branch: perfBranch, scenario: "homepage-cold", runs }))
   })
 
   test("session-streaming-long emits a 3-run JSON baseline", async ({ page, project, llm }) => {
@@ -192,9 +199,10 @@ test.describe("PR0.1 perf probe baseline", () => {
       secondWave.resolve()
       await send
       runs.push(await snapshotPerfProbe(page))
+      if (run < 2) await cooldownAfterRun(page)
     }
 
-    scenarioResults.push(summarizeScenarioRuns({ branch: "dev", scenario: "session-streaming-long", runs }))
+    scenarioResults.push(summarizeScenarioRuns({ branch: perfBranch, scenario: "session-streaming-long", runs }))
   })
 
   test("tool-call-expand emits a 3-run JSON baseline", async ({ page, project, llm }) => {
@@ -221,9 +229,10 @@ test.describe("PR0.1 perf probe baseline", () => {
       await expect(trigger).toHaveAttribute("aria-expanded", "true")
       await settleFrames(page, 4)
       runs.push(await snapshotPerfProbe(page))
+      if (run < 2) await cooldownAfterRun(page)
     }
 
-    scenarioResults.push(summarizeScenarioRuns({ branch: "dev", scenario: "tool-call-expand", runs }))
+    scenarioResults.push(summarizeScenarioRuns({ branch: perfBranch, scenario: "tool-call-expand", runs }))
   })
 
   test("session-scroll-reading emits a 3-run JSON baseline", async ({ page, project }) => {
@@ -258,9 +267,10 @@ test.describe("PR0.1 perf probe baseline", () => {
         await page.mouse.wheel(0, 3600)
         await settleFrames(page, 4)
         runs.push(await snapshotPerfProbe(page))
+        if (run < 2) await cooldownAfterRun(page)
       })
     }
 
-    scenarioResults.push(summarizeScenarioRuns({ branch: "dev", scenario: "session-scroll-reading", runs }))
+    scenarioResults.push(summarizeScenarioRuns({ branch: perfBranch, scenario: "session-scroll-reading", runs }))
   })
 })

packages/app/script/compare-perf.ts

@@ -0,0 +1,50 @@
+import fs from "node:fs/promises"
+import path from "node:path"
+import { comparePerfBaselines, type PerfScenarioSummary } from "../src/testing/perf-metrics"
+
+function readArg(flag: string) {
+  const index = process.argv.indexOf(flag)
+  if (index === -1) return undefined
+  const value = process.argv[index + 1]
+  if (!value || value.startsWith("--")) return undefined
+  return value
+}
+
+async function readPerfFile(filePath: string) {
+  const payload = JSON.parse(await fs.readFile(filePath, "utf8")) as PerfScenarioSummary[]
+  if (!Array.isArray(payload)) {
+    throw new Error(`Expected an array of perf scenarios in ${filePath}`)
+  }
+  return payload
+}
+
+async function main() {
+  const basePath = readArg("--base")
+  const headPath = readArg("--head")
+  const outputPath = readArg("--output")
+
+  if (!basePath || !headPath) {
+    throw new Error("Usage: bun script/compare-perf.ts --base <perf-base.json> --head <perf-head.json> [--output <path>]")
+  }
+
+  const [base, head] = await Promise.all([readPerfFile(basePath), readPerfFile(headPath)])
+  const comparison = comparePerfBaselines({ base, head })
+
+  if (outputPath) {
+    await fs.mkdir(path.dirname(outputPath), { recursive: true })
+    await fs.writeFile(outputPath, `${JSON.stringify(comparison, null, 2)}\n`)
+  }
+
+  const summary = {
+    pass: comparison.pass,
+    failures: comparison.failures,
+    warnings: comparison.warnings,
+  }
+  console.log(JSON.stringify(summary, null, 2))
+
+  if (!comparison.pass) {
+    process.exitCode = 1
+  }
+}
+
+await main()