name: lifeops-quality-bench

# Recorded-baseline LifeOps quality benchmarks + regression gate (#10723).
#
# Two keyless, deterministic lanes over REAL LifeOps code paths:
#
#   triage      — the plugin-inbox triage classifier's prompt-build → parse →
#                 validate → fail-closed path driven over a committed labeled
#                 56-item corpus with a committed fixed-quality mock model
#                 (fixtures). Precision/recall/accuracy/macro-F1 gate against
#                 budgets.json floors and must reproduce baseline.json exactly.
#   timeliness  — the plugin-personal-assistant scheduled-task tick
#                 (processDueScheduledTasks) replayed over two committed 4-day
#                 2026 DST windows (spring-forward + fall-back) at a 5-minute
#                 cadence on a real PGlite runtime with an injected clock.
#                 Missed/duplicate/early/occurrence-mismatch counts must be 0
#                 and fire-time deviation must stay under budgets.json ceilings.
#
# No model bundle, no credentials — fully reproducible on a hosted runner
# (mirrors recall-bench.yml, #9956). A red gate means a real quality
# regression in triage parsing/validation or scheduler fire behavior.

on:
  pull_request:
    branches: [main]
    paths:
      - "packages/benchmarks/lifeops-quality/**"
      - "plugins/plugin-inbox/src/inbox/**"
      - "plugins/plugin-personal-assistant/src/lifeops/**"
      - "plugins/plugin-personal-assistant/test/helpers/**"
      - "plugins/plugin-scheduling/src/**"
      - "packages/core/src/services/triggerScheduling.ts"
      - ".github/workflows/lifeops-quality-bench.yml"
  schedule:
    # 05:40 UTC — alongside the other nightly benchmark lanes.
    - cron: "40 5 * * *"
  workflow_dispatch: {}

concurrency:
  group: lifeops-quality-bench-${{ github.ref }}
  cancel-in-progress: true

env:
  BUN_VERSION: "canary"
  NODE_VERSION: "24.15.0"

jobs:
  lifeops-quality-gate:
    name: triage P/R + reminder timeliness budget gate (keyless)
    runs-on: ${{ fromJSON(vars.HETZNER_FLEET_ONLINE == 'false' && '["ubuntu-24.04"]' || '["self-hosted","hetzner-robot"]') }}
    timeout-minutes: 45
    env:
      PGLITE_WASM_MODE: node
    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
          install-native-deps: "false"
          skip-avatar-clone: "true"
          no-vision-deps: "true"

      # The timeliness gate boots the personal-assistant plugin barrel, which
      # imports sibling plugin dists (same requirement as the Integration Lane
      # in test.yml). plugin-inbox is inside this dependency graph, so the
      # triage gate's classifier import is covered too. Turbo replays warm
      # runs from cache.
      - name: Build personal-assistant dependency graph
        run: node packages/scripts/run-turbo.mjs run build --filter='@elizaos/plugin-personal-assistant...'

      - name: Unit lane (metrics + oracle + corpus/fixture/baseline invariants)
        run: bun run --cwd packages/benchmarks/lifeops-quality test

      - name: Triage precision/recall gate (real classifier, committed fixtures)
        run: bun run --cwd packages/benchmarks/lifeops-quality bench:triage

      - name: Reminder timeliness gate (real scheduler tick, DST windows)
        timeout-minutes: 30
        run: bun run --cwd packages/benchmarks/lifeops-quality bench:timeliness

      - name: Upload measured results
        if: always()
        uses: actions/upload-artifact@v7
        with:
          name: lifeops-quality-results
          path: packages/benchmarks/lifeops-quality/results/*.json
          if-no-files-found: ignore