deepseek-harness/scripts/gen-module-graph.ts

/**
 * Generate (and verify) the module dependency graph in docs/module-graph.md.
 *
 * The architectural shape of the harness lives implicitly in each package's
 * `peerDependencies` — the canonical runtime-dependency signal (devDeps mirror
 * these as `workspace:^` plus test-only extras, which would add noise). This
 * script reads every `packages/* /* /package.json`, keeps only the
 * `@deepseek-ai/dsh-*` peer edges (dropping the `cordis` peer), and renders a
 * GitHub-viewable Mermaid graph grouped by `packages/<group>/` plus a
 * dependency table.
 *
 * The file is fully generated — never hand-edit it. Output is deterministic
 * (packages and edges sorted) so a regenerate-and-diff freshness check is
 * stable.
 *
 *   `tsx scripts/gen-module-graph.ts`          → write docs/module-graph.md
 *   `tsx scripts/gen-module-graph.ts --check`  → exit 1 if the committed file
 *                                                is stale (CI / pre-push gate)
 */

import { resolve } from 'node:path'
import { readFileSync, writeFileSync } from 'node:fs'
import {
  collectPackageGraph,
  escapeMermaidLabel as escLabel,
  graphNodeId as nodeId,
  type PackageGraphNode,
} from './package-graph.ts'

const root = resolve(import.meta.dirname, '..')
const OUT = 'docs/module-graph.md'
type Pkg = PackageGraphNode

const GROUP_ORDER = [
  'util',
  'llm',
  'core',
  'bash',
  'fs',
  'skill',
  'compact',
  'subagent',
  'web',
  'timeout',
  'todo',
  'mode',
  'cordis',
  'hooks',
  'session-persistence',
  'support',
  'ui',
]

function packageLink(pkg: Pkg): string {
  return `[\`${pkg.short}\`](../${pkg.rel})`
}

/** Render the full docs/module-graph.md content (pure, deterministic). */
function render(pkgs: Pkg[]): string {
  const edges: string[] = []
  for (const p of pkgs) {
    for (const d of p.deps) edges.push(`  ${nodeId('pkg', p.short)} --> ${nodeId('pkg', d)}`)
  }
  const byShort = new Map(pkgs.map(pkg => [pkg.short, pkg]))
  const groups = [...new Set(pkgs.map(pkg => pkg.group))].sort((a, b) => {
    const ia = GROUP_ORDER.indexOf(a)
    const ib = GROUP_ORDER.indexOf(b)
    const na = ia === -1 ? Number.MAX_SAFE_INTEGER : ia
    const nb = ib === -1 ? Number.MAX_SAFE_INTEGER : ib
    return na - nb || a.localeCompare(b)
  })
  const groupBlocks: string[] = []
  for (const group of groups) {
    groupBlocks.push(`  subgraph ${nodeId('group', group)}["packages/${escLabel(group)}"]`)
    for (const pkg of pkgs.filter(p => p.group === group).sort((a, b) => a.short.localeCompare(b.short))) {
      groupBlocks.push(`    ${nodeId('pkg', pkg.short)}["${escLabel(pkg.short)}"]`)
    }
    groupBlocks.push('  end')
  }
  const rows = pkgs.map((p) => {
    const deps = p.deps.length ? p.deps.map((d) => {
      const dep = byShort.get(d)
      return dep ? packageLink(dep) : `\`${d}\``
    }).join(', ') : '—'
    return `| ${packageLink(p)} | \`${p.group}\` | ${deps} |`
  })
  return [
    '<!-- Generated by scripts/gen-module-graph.ts — do not edit by hand.',
    '     Run `pnpm run gen-module-graph` to regenerate. -->',
    '',
    '# Module dependency graph',
    '',
    'Inter-package dependencies among the `@deepseek-ai/dsh-*` harness packages, derived from each package\'s `peerDependencies` (the canonical runtime-dependency signal) and grouped by the `packages/<group>/<pkg>` hierarchy. An edge `a --> b` means package `a` depends on package `b`. Names have the `@deepseek-ai/dsh-` prefix stripped.',
    '',
    '```mermaid',
    'flowchart TD',
    ...groupBlocks,
    ...edges,
    '```',
    '',
    '| Package | Group | Depends on |',
    '| --- | --- | --- |',
    ...rows,
    '',
  ].join('\n')
}

const content = render(collectPackageGraph(root, GROUP_ORDER, 'gen-module-graph'))

if (process.argv.includes('--check')) {
  let committed: string | null = null
  try {
    committed = readFileSync(resolve(root, OUT), 'utf8')
  } catch {
    // Only an ENOENT (file not yet generated) is expected here; readFileSync of
    // a present-but-unreadable file is not a state this repo produces. Either
    // way the remedy is the same — regenerate — so we treat a read failure as
    // "stale" and fall through to the failure branch below.
    committed = null
  }
  if (committed === content) {
    console.log(`gen-module-graph: ${OUT} is up to date.`)
    process.exit(0)
  }
  console.error(`gen-module-graph: ${OUT} is stale. Run \`pnpm run gen-module-graph\` and commit ${OUT}.`)
  process.exit(1)
}

writeFileSync(resolve(root, OUT), content)
console.log(`gen-module-graph: wrote ${OUT}.`)