deepseek-harness/.github/workflows/ci.yml

name: CI

on:
  push:
    branches: [main, master]
  pull_request:

concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

jobs:
  checks:
    runs-on: ubuntu-latest
    strategy:
      fail-fast: false
      matrix:
        node: [24, 26]
    name: node ${{ matrix.node }}
    steps:
      - uses: actions/checkout@v6

      - uses: actions/setup-node@v6
        with:
          node-version: ${{ matrix.node }}

      - name: Enable corepack (pnpm)
        run: corepack enable

      - name: Install (immutable)
        run: pnpm install --frozen-lockfile

      - name: Constraints
        run: pnpm run constraints

      # Before lint: the type-aware ESLint config resolves vendor packages via
      # their built declarations (tsconfig.typecheck.json -> vendor/*/lib),
      # which `pnpm run typecheck` emits. Lint on a fresh checkout would otherwise
      # see unresolved types and erupt with no-unsafe-* errors.
      - name: Typecheck (src + tests + examples)
        run: pnpm run typecheck

      - name: Lint
        run: pnpm run lint

      # Doc-sync gates (doc-sync-enforcement RFC). doc-typecheck compiles the fenced ts blocks in
      # the docs and resolves vendor packages via their built declarations, which
      # the typecheck step above emits — so it runs after typecheck. The cordis
      # catalog freshness check, type-equiv check, and markdown wrap/link checks
      # only read source. Same `doc-sync` script the pre-push hook runs
      # (quality-gates RFC: one source of truth).
      - name: Doc-sync gates (doc code blocks + cordis catalog + type-equiv + markdown wrap/links)
        run: pnpm run doc-sync

      # Module-graph freshness: regenerate docs/module-graph.md from the
      # packages' peerDependencies and fail if it differs from the committed
      # file. Only reads source package.json — no build needed.
      - name: Module-graph freshness
        run: pnpm run verify-module-graph

      - name: Tests with coverage gate (per-file 100%)
        run: pnpm run test:coverage

      # ACP snapshot tests (acp-snapshot-tests RFC): boot the real acp-agent
      # subprocess and replay recorded session-log fixtures, diffing the
      # normalized stdout transcript + re-persisted log against committed
      # goldens. KEYLESS by design — the same `test:snapshot` script the pre-push
      # hook runs (one source of truth), so the full-transcript regression net
      # is part of every PR gate, not just local pre-push.
      - name: Snapshot tests (ACP transcript replay)
        run: pnpm run test:snapshot

      # Before hygiene: publint validates the packed artifacts (lib/index.js),
      # which only the tsdown bundling step emits.
      - name: Build (tsc -b + tsdown bundles)
        run: pnpm run build

      - name: Hygiene (knip + publint)
        run: pnpm run knip && pnpm run publint

      - name: Demo smoke test
        run: |
          set -euo pipefail
          out=$(printf 'echo ci smoke\n' | timeout 60 node --expose-internals --import tsx examples/echo-agent/start.ts 2>&1)
          echo "$out"
          echo "$out" | grep -q '\[tool call\] echo({"text":"ci smoke"})'
          echo "$out" | grep -q '\[tool result\] ECHO: CI SMOKE'
          # The JSONL backend (root ./.sessions, no cwd → _no-cwd bucket) writes a
          # per-run session log named main-session-<uuid>.jsonl. Assert one exists.
          ls .sessions/_no-cwd/main-session-*.jsonl >/dev/null
          rm -rf .sessions