elizaos--eliza/.github/workflows/chat-shell-gestures.yml

name: Chat shell gestures

# Real-browser gesture + interleaving e2e for the floating chat shell
# (packages/ui ContinuousChatOverlay + home screen), the component-tree
# render-parity contract, and the CHAT_GESTURE_COVERAGE gate (#12188).
#
# All 11 __e2e__ runners compose the shared runner toolkit
# (packages/ui/src/testing/e2e-runner) and record a stable-named .webm. This lane
# drives the REAL surfaces with real pointer/touch gestures in headless chromium,
# runs the boot-free coverage gate that fails when a gesture-handler site lacks a
# matrix row, and uploads every runner's video + screenshots.
#
# One shell runner is intentionally NOT in this lane:
#   - run-fused-wake-integration-e2e drives the REAL native desktop wake producer
#     (libwakeword + the wakeword-cpp build), which this lane does not compile
#     (install-native-deps:false) — it self-skips without the lib, so it lives in
#     the native-desktop build lane.
#
# run-perf-gate-e2e USED to be excluded here for a CLS 0.80 failure, but that
# shift was the conversation-swipe layout thrash: #13531 removed swipe (one
# infinite thread) and #13826 retargeted the gate onto scroll + maximize/restore,
# so CLS is now 0.0000 on develop (stable across runs, not timing-flaky). It is
# re-enabled below (#14333) — CLS is structural so it will not flake on slower
# fleet hardware, and the frame budget carries ~3x margin (p95 ~10ms ≤ 33ms).
# Both gates self-verify their detector's teeth: each injects a real non-transient
# shift and asserts it is flagged, so a 0.0000 can never be a dead-observer pass.
#
# Path-gated to packages/ui (and the app-side gate + matrix) so it only runs when
# the surface it covers changes. The e2e runners bundle the fixtures with esbuild
# and stub @elizaos/core, so no core build is needed; the render-parity vitest
# imports the real @elizaos/core, so the shared i18n data is generated first.
on:
  pull_request:
    branches: [main]
    paths:
      - ".github/workflows/chat-shell-gestures.yml"
      - "package.json"
      - "bun.lock"
      - "packages/ui/**"
      - "packages/shared/**"
      - "packages/core/src/i18n/**"
      - "packages/app/test/chat-gesture-coverage.test.ts"
      - "packages/app/docs/CHAT_GESTURE_COVERAGE.md"
  push:
    branches: [main, develop]
    paths:
      - ".github/workflows/chat-shell-gestures.yml"
      - "package.json"
      - "bun.lock"
      - "packages/ui/**"
      - "packages/shared/**"
      - "packages/core/src/i18n/**"
      - "packages/app/test/chat-gesture-coverage.test.ts"
      - "packages/app/docs/CHAT_GESTURE_COVERAGE.md"
  workflow_dispatch:

# CI fan-out fix: the PR-scoped concurrency from #14069 fell back to
# github.run_id on push, so every develop push got a unique group and
# nothing ever superseded. A 37-merge wave queued thousands of push runs
# and starved the self-hosted fleet. Fall back to github.ref (all develop
# pushes share a group) and cancel superseded runs on push too. PR behavior
# is unchanged (pull_request.number still wins the key); merge_group and
# schedule events are not in the cancel set, so the merge queue and nightly
# runs always complete.
concurrency:
  group: chat-shell-gestures-${{ github.event.pull_request.number || github.ref }}
  cancel-in-progress: ${{ github.event_name == 'pull_request' || github.event_name == 'push' }}

permissions:
  contents: read

env:
  CI: "true"
  BUN_VERSION: "canary"
  NODE_VERSION: "24.15.0"
  NODE_NO_WARNINGS: "1"

jobs:
  chat-shell-gestures:
    name: Chat shell gesture + parity e2e
    runs-on: ${{ fromJSON(vars.HETZNER_FLEET_ONLINE == 'false' && '["ubuntu-24.04"]' || '["self-hosted","hetzner-robot"]') }}
    timeout-minutes: 40
    steps:
      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5
        with:
          submodules: false

      - name: Setup Node.js
        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e
        with:
          node-version: ${{ env.NODE_VERSION }}

      - name: Setup workspace dependencies
        uses: ./.github/actions/setup-bun-workspace
        with:
          bun-version: ${{ env.BUN_VERSION }}
          install-command: bun install --ignore-scripts --no-frozen-lockfile
          install-native-deps: "false"
          skip-avatar-clone: "true"
          no-vision-deps: "true"

      # The render-parity contract imports the real @elizaos/core, whose i18n
      # module loads generated keyword data that is gitignored. Generate it so
      # the vitest run resolves (mirrors the attachment-journey-videos lane).
      - name: Ensure generated shared i18n data
        run: node packages/app-core/scripts/ensure-shared-i18n-data.mjs

      - name: Install Playwright chromium + webkit
        run: bunx playwright install --with-deps chromium webkit

      # Boot-free coverage gate: fails when a gesture-handler site in
      # packages/ui/src lacks a CHAT_GESTURE_COVERAGE matrix row (#12188).
      - name: Chat gesture coverage gate
        run: bun run --cwd packages/app test -- chat-gesture-coverage

      # Component-tree render parity (jsdom/vitest) — ThreadLine vs MessageContent
      # render the same structure for a shared message corpus.
      - name: Render-parity contract
        run: bun run --cwd packages/ui test -- src/components/chat/render-parity.contract.test.tsx

      # Conversation-nav interleaving fuzz (jsdom) — the pure most-recent-first
      # invariants across new / select sequences (#10042). Chat-to-chat swipe
      # was removed by the single-infinite-thread redesign (#13531), so the swipe
      # e2e + its jank hook were retired in #13826; the remaining overlay gesture
      # cost is now covered by the maximize/restore perf gate below.
      - name: Conversation-nav unit + interleaving
        run: bun run --cwd packages/ui test -- src/components/shell/conversation-nav.test.ts

      # The iOS-style chat-sheet detent/gesture state machine (mouse + touch).
      - name: Chat-sheet gesture e2e
        run: bun run --cwd packages/ui test:chat-sheet-e2e
      - name: Chat-sheet Safari/WebKit gesture smoke
        run: bun run --cwd packages/ui test:chat-sheet-safari-e2e

      # "can't scroll chat on web" repro (#chat-scroll-web): seeds a long
      # transcript, opens the sheet to FULL, and asserts the transcript scroller
      # resolves a BOUNDED clientHeight (so there is overflow) and that a real
      # vertical finger-drag moves scrollTop natively instead of being hijacked
      # into the sheet pull. RED before the fix, GREEN after.
      - name: Chat-scroll web e2e
        run: bun run --cwd packages/ui test:chat-scroll-web-e2e

      # Transcript is vertical-only (#14328): an over-wide child + diagonal wheel
      # must not pan #continuous-thread sideways; a designed inner scroller still
      # scrolls in its own row and does not chain. Both engines — the axis lock is
      # a *desktop trackpad* deltaX bug and WebKit's scroll semantics differ, so
      # the acceptance bar requires the assertion to hold on WebKit too.
      - name: Chat transcript axis-lock e2e (chromium)
        run: bun run --cwd packages/ui test:chat-scroll-axis-lock-e2e
      - name: Chat transcript axis-lock e2e (webkit)
        run: ENGINE=webkit bun run --cwd packages/ui test:chat-scroll-axis-lock-e2e

      # TopicGroup flick-collapse/expand gestures.
      - name: TopicGroup gesture e2e
        run: bun run --cwd packages/ui test:chatux-gesture-e2e

      # Home↔launcher pager swipe, notification pull, launcher long-press
      # (real CDP touch on mobile + fine-pointer desktop edge buttons).
      - name: Home-screen gesture e2e
        run: bun run --cwd packages/ui test:home-screen-e2e

      # Seeded launcher long-loop (#12375): 500 real CDP-touch gestures over the
      # composed home↔launcher surface, every §D invariant checked after each
      # command, with a full walkthrough video. Pinned seed for a deterministic
      # gate; fuzz locally by unsetting ELIZA_LOOP_SEED.
      - name: Launcher gesture long-loop e2e
        env:
          ELIZA_LOOP_SEED: "12375"
        run: bun run --cwd packages/ui test:launcher-loop-e2e

      # Bottom-bar state-machine gestures.
      - name: Bottombar gesture e2e
        run: bun run --cwd packages/ui test:bottombar-e2e

      # Warm-up 503 eviction: optimistic bubble survives the reconcile reload +
      # retry-once delivery (records the recovery flow).
      - name: Warm-up eviction e2e
        run: bun run --cwd packages/ui test:warmup-eviction-e2e

      # /chat ambient orange-pulse background: sample the 30s CSS animation
      # across its named peaks while recording a .webm.
      - name: Chat ambient pulse e2e
        run: bun run --cwd packages/ui test:chat-ambient-e2e

      # Perf gates: drive the overlay under thread-scroll + pull-to-maximize /
      # top-pull-restore, feed real PerformanceObserver + rAF entries into the
      # shared frame-budget + layout-stability detectors, hard-fail on dropped-
      # frame % / p95 / CLS. Each gate first proves its CLS detector has teeth by
      # injecting a real non-transient shift and asserting it is flagged (#14333),
      # so a true CLS of 0.0000 cannot be a vacuous pass from a dead observer.
      - name: Chat overlay perf gate
        run: bun run --cwd packages/ui test:chat-perf-gate

      # Scroll + maximize/restore perf gate over the REAL overlay (#9954 item 5,
      # retargeted off the removed swipe path by #13826). Hard-fails on
      # dropped-frame % / p95 frame time / CLS ≤ 0.1. Re-enabled in this lane by
      # #14333 now that the swipe-CLS 0.80 is gone (CLS 0.0000 on develop).
      - name: Chat overlay scroll/maximize perf gate
        run: bun run --cwd packages/ui test:perf-gate-e2e

      # #9142 Part 2: capture a dense CDP frame burst across the pill→open spring
      # (animations ON) and run the single-frame-flash + two-pills-crossfade
      # detectors. The harness was merged (#10356/#10374) but ran in NO workflow,
      # so a transient glitch could still ship. Run under bun (resolves the
      # esbuild/pixelmatch/pngjs deps directly, regardless of the node-run
      # portability fallback in #10400).
      - name: Frame-glitch (transient) e2e
        run: bun packages/ui/src/components/shell/__e2e__/run-chat-sheet-frame-glitch-e2e.mjs

      # Self-test: --canary injects a one-frame wrong state and asserts the
      # detectors FIRE on it; the harness exits 0 iff they do (and non-zero if it
      # has gone blind). This guards against the detectors silently degrading.
      - name: Frame-glitch canary self-test
        run: bun packages/ui/src/components/shell/__e2e__/run-chat-sheet-frame-glitch-e2e.mjs --canary

      - name: Upload gesture videos + screenshots
        if: always()
        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a
        with:
          name: chat-shell-gesture-artifacts
          path: |
            packages/ui/src/components/shell/__e2e__/output/
            packages/ui/src/components/shell/__e2e__/output-webkit/
            packages/ui/src/components/shell/__e2e__/output-chatux/
            packages/ui/src/components/shell/__e2e__/output-home/
            packages/ui/src/components/shell/__e2e__/output-launcher-loop/
            packages/ui/src/components/shell/__e2e__/output-bottombar/
            packages/ui/src/components/shell/__e2e__/output-warmup-eviction/
            packages/ui/src/components/shell/__e2e__/output-perf-gate/
            packages/ui/src/components/shell/__e2e__/output-frame-glitch/
          if-no-files-found: warn
          retention-days: 14