elizaos--eliza/.github/workflows/ci.yaml

name: ci

# Cancel previous runs for the same PR/branch
concurrency:
  group: ci-${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
  cancel-in-progress: true

on:
  push:
    branches: [main]
  pull_request:
    branches: [main]
# Default to least privilege. Override per-job where needed.
permissions:
  contents: read

jobs:
  # Test job
  test:
    # Skip duplicate runs: run on push to main, or on pull_request events only
    if: github.event_name == 'pull_request' || (github.event_name == 'push' && github.ref_name == 'main')
    runs-on: ubuntu-latest
    # 45 not 35: typecheck runs at --concurrency=4 (see below, #15140), so a
    # near-total affected cone (e.g. a develop→main promote PR) needs headroom
    # on top of install + build + the 15-minute test step.
    timeout-minutes: 45
    env:
      # Baseline CI is secret-free. Live/provider-key E2E runs in dedicated
      # opt-in or post-merge workflows, not in the PR test job.
      PGLITE_WASM_MODE: node
    steps:
      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5
        with:
          # Full history so `turbo run typecheck --affected` can resolve the PR
          # merge base (#12341); a shallow clone degrades to typechecking all.
          fetch-depth: 0

      - name: Setup Node.js
        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e
        with:
          node-version: "24.15.0"

      - name: Setup workspace dependencies
        uses: ./.github/actions/setup-bun-workspace
        with:
          bun-version: "1.3.14" # pinned: floating canary writes lockfileVersion 2 and breaks --frozen-lockfile (#11184/#9454); packageManager bun@1.4.0-canary.1 is unresolvable (GH+npm 404)
          install-command: bun install
          install-native-deps: "false"
          skip-avatar-clone: "true"
          no-vision-deps: "true"

      - name: Create test env file
        run: |
          echo "TEST_DATABASE_CLIENT=pglite" > packages/core/.env.test
          echo "NODE_ENV=test" >> packages/core/.env.test

      - name: Build packages
        run: bun run build:core

      # PR lane: typecheck only the merge base's dependency cone; on push to
      # main typecheck the whole workspace (#12341). --concurrency=4 not 8:
      # a develop→main promote PR's affected cone is near-total, and eight
      # concurrent tsgo processes exhaust a 16 GB hosted runner (#15140);
      # mirrors develop-pr.yml so the PR lanes stay in agreement.
      - name: Run typecheck (affected — PR)
        if: github.event_name == 'pull_request'
        run: NODE_OPTIONS='--max-old-space-size=8192' node packages/scripts/run-turbo.mjs run typecheck --concurrency=4 --affected
        env:
          TURBO_SCM_BASE: ${{ github.event.pull_request.base.sha }}

      - name: Run typecheck (full — push)
        if: github.event_name != 'pull_request'
        run: bun run typecheck

      - name: Run tests
        timeout-minutes: 15
        env:
          NODE_OPTIONS: "--max-old-space-size=2048"
        run: bun run test:core

      - name: Run plugin tests
        timeout-minutes: 15
        env:
          NODE_OPTIONS: "--max-old-space-size=2048"
        run: bun run test:plugins

      - name: Run interop (TypeScript) tests
        timeout-minutes: 10
        run: |
          if [ -d packages/interop ]; then
            cd packages/interop && bun run test
          else
            echo "packages/interop is not present; skipping interop tests"
          fi

  # Lint and format job
  lint-and-format:
    # Skip duplicate runs: run on push to main, or on pull_request events only
    if: github.event_name == 'pull_request' || (github.event_name == 'push' && github.ref_name == 'main')
    runs-on: ubuntu-latest
    timeout-minutes: 10
    steps:
      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5
        with:
          # `audit:test-realness` compares touched tests against origin/develop.
          # Keep the merge base available so the diff-scoped ratchet runs in CI.
          fetch-depth: 0

      - name: Setup Node.js
        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e
        with:
          node-version: "24.15.0"

      - name: Setup workspace dependencies
        uses: ./.github/actions/setup-bun-workspace
        with:
          bun-version: "1.3.14" # pinned: floating canary writes lockfileVersion 2 and breaks --frozen-lockfile (#11184/#9454); packageManager bun@1.4.0-canary.1 is unresolvable (GH+npm 404)
          install-command: bun install
          install-native-deps: "false"
          install-protoc: "false"
          setup-python: "false"
          skip-avatar-clone: "true"
          no-vision-deps: "true"

      - name: Prompt secret scan
        run: cd packages/prompts && bun run check:secrets

      - name: Type safety ratchet self-test
        run: bun run audit:type-safety-ratchet:self-test

      - name: Type safety ratchet
        run: bun run audit:type-safety-ratchet

      - name: Check format
        run: bun run format:check

      - name: Run lint
        run: bun run lint

      # UI render-time determinism gate. Fails on NEW Date.now()/Math.random()/
      # crypto.randomUUID()/locale-defaulted toLocale* in a component/hook render
      # path (the source of flaky screenshots + meaningless snapshots). The
      # existing backlog is tracked in packages/scripts/ui-determinism-baseline.json;
      # only regressions beyond it fail. Self-test asserts the AST classifier.
      - name: UI determinism self-test
        run: bun run audit:ui-determinism:self-test

      - name: UI determinism gate
        run: bun run audit:ui-determinism

      # Anti-larp test gate (#10718). Fails on focused tests (.only / fit /
      # fdescribe — a single .only silently drops every sibling test in the file)
      # and on orphaned hardcoded skips (it.skip("name", fn) with no reason,
      # tracking issue, deny-list ref, or Playwright skip-annotation). Legitimate
      # conditional/env-gated skips (cond ? describe : describe.skip,
      # test.skip(cond, reason)) are allowed. Self-test asserts the classifier.
      - name: Anti-larp test gate self-test
        run: bun run audit:focused-tests:self-test

      - name: Anti-larp test gate
        run: bun run audit:focused-tests

      - name: Test realness ratchet
        run: bun run audit:test-realness

      # Per-plugin mock-LLM e2e coverage. The seeded allowlist carries
      # historical debt; new unsuppressed gaps fail the main gate (#13620).
      - name: Per-plugin e2e coverage
        run: node packages/scripts/lint-lane-coverage.mjs

  # Build job
  build:
    # Skip duplicate runs: run on push to main, or on pull_request events only
    if: github.event_name == 'pull_request' || (github.event_name == 'push' && github.ref_name == 'main')
    runs-on: ubuntu-latest
    timeout-minutes: 15
    steps:
      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5

      - name: Setup Node.js
        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e
        with:
          node-version: "24.15.0"

      - name: Setup workspace dependencies
        uses: ./.github/actions/setup-bun-workspace
        with:
          bun-version: "1.3.14" # pinned: floating canary writes lockfileVersion 2 and breaks --frozen-lockfile (#11184/#9454); packageManager bun@1.4.0-canary.1 is unresolvable (GH+npm 404)
          install-command: bun install
          install-native-deps: "false"
          install-protoc: "false"
          setup-python: "false"
          skip-avatar-clone: "true"
          no-vision-deps: "true"

      - name: Build packages
        run: bun run build:core

  # Dev startup + HMR job: prove `bun run dev` boots to a usable state quickly
  # and that edits at every package dependency depth propagate to the running
  # client over HMR. Guards against startup-time regressions and broken
  # src/-resolution or workspace-source watching.
  dev-startup:
    if: github.event_name == 'pull_request' || (github.event_name == 'push' && github.ref_name == 'main')
    runs-on: ubuntu-latest
    timeout-minutes: 25
    steps:
      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5

      - name: Setup Node.js
        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e
        with:
          node-version: "24.15.0"

      - name: Setup workspace dependencies
        uses: ./.github/actions/setup-bun-workspace
        with:
          bun-version: "1.3.14" # pinned: floating canary writes lockfileVersion 2 and breaks --frozen-lockfile (#11184/#9454); packageManager bun@1.4.0-canary.1 is unresolvable (GH+npm 404)
          install-command: bun install
          install-native-deps: "false"
          install-protoc: "false"
          setup-python: "false"
          skip-avatar-clone: "true"
          no-vision-deps: "true"

      - name: Build packages
        run: bun run build

      - name: Remove source-adjacent build output
        run: bun run clean:stale-js

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

      # The product gate is 60s (the script default enforced on dev machines).
      # Shared CI runners are ~2-4 cores vs a dev workstation, so the CI ceiling
      # is relaxed to 90s — still catches a startup-time doubling, without
      # flaky false-failures. Lower this if runner class improves.
      - name: Dev startup budget (boots + ready under budget)
        env:
          ELIZA_DEV_STARTUP_BUDGET_MS: "90000"
        run: bun run test:dev-startup

      - name: HMR propagation across dependency levels
        run: bun run test:hmr