deepseek-harness/scripts/check-workspace-constraints.ts

240 lines
7.8 KiB
TypeScript
Raw Normal View History

2026-06-16 14:55:37 +08:00
/**
* Workspace package invariant checks for package-manager-independent quality
* gates.
*
* Run: `tsx scripts/check-workspace-constraints.ts`.
*/
import { existsSync, readdirSync, readFileSync } from 'node:fs'
2026-06-16 14:55:37 +08:00
import { join, relative, resolve } from 'node:path'
const root = resolve(import.meta.dirname, '..')
// vendor/* is single-level; packages/<group>/<pkg> nests one level deeper
// (the group dirs — core/llm/bash/… — are pure containers with no manifest).
const workspaceGlobs = [
{ dir: 'vendor', depth: 1 },
{ dir: 'packages', depth: 2 },
] as const
2026-06-16 14:55:37 +08:00
const vendoredPackages = new Set([
'cordis',
'cosmokit',
'schemastery',
'@cordisjs/plugin-loader',
'@cordisjs/plugin-include',
'@cordisjs/plugin-group',
'@cordisjs/plugin-timer',
'@cordisjs/plugin-hmr',
'@cordisjs/plugin-logger-console',
])
const localArtifactDirs = new Set(['node_modules'])
2026-06-16 14:55:37 +08:00
/** The subset of package.json fields this constraint check cares about. */
interface PackageManifest {
name?: string
version?: string
private?: boolean
type?: string
main?: string
types?: string
bin?: string | Record<string, string>
exports?: Record<
string,
| {
types?: string
default?: string
}
| undefined
>
files?: string[]
2026-06-16 14:55:37 +08:00
peerDependencies?: Record<string, string>
devDependencies?: Record<string, string>
}
/** One workspace manifest and its repo-relative path. */
interface WorkspaceManifest {
dir: string
manifest: PackageManifest
}
function readJson(path: string): PackageManifest {
return JSON.parse(readFileSync(path, 'utf8')) as PackageManifest
}
const rootManifest = readJson(join(root, 'package.json'))
const repositoryVersion = rootManifest.version
/** Repo-relative dirs holding a package.json, walked to the configured depth. */
function packageDirs(base: string, depth: number): string[] {
if (depth === 1) {
return readdirSync(join(root, base), { withFileTypes: true })
.filter(entry => entry.isDirectory())
.filter(entry => !localArtifactDirs.has(entry.name))
.filter(entry => existsSync(join(root, base, entry.name, 'package.json')))
.map(entry => join(base, entry.name))
}
return readdirSync(join(root, base), { withFileTypes: true })
.filter(entry => entry.isDirectory())
.filter(entry => !localArtifactDirs.has(entry.name))
.flatMap(group => packageDirs(join(base, group.name), depth - 1))
}
2026-06-16 14:55:37 +08:00
function workspaceManifests(): WorkspaceManifest[] {
const manifests: WorkspaceManifest[] = [
{ dir: '.', manifest: rootManifest },
2026-06-16 14:55:37 +08:00
]
for (const { dir: base, depth } of workspaceGlobs) {
for (const dir of packageDirs(base, depth)) {
2026-06-16 14:55:37 +08:00
manifests.push({ dir, manifest: readJson(join(root, dir, 'package.json')) })
}
}
return manifests
}
const dshPackageFiles = [
'lib/index.js',
'lib/types/**/*.d.ts',
'lib/types/**/*.d.ts.map',
'src',
] as const
const dshBinPackageFiles = [
'lib/index.js',
'lib/bin.js',
'lib/types/**/*.d.ts',
'lib/types/**/*.d.ts.map',
'src',
] as const
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
const dshWorkerPackageFiles = [
'lib/index.js',
'lib/worker.cjs',
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
'lib/types/**/*.d.ts',
'lib/types/**/*.d.ts.map',
'src',
] as const
const packageFileExtras: Readonly<Record<string, readonly string[]>> = {
'@deepseek-ai/dsh-helper': ['lib/assets'],
'@deepseek-ai/dsh-scripts': [
'lib/dev/tsdown-config.js',
'lib/local-plugin-loader-hooks.js',
'lib/assets',
],
}
function sameStringList(actual: readonly string[] | undefined, expected: readonly string[]): boolean {
return !!actual && actual.length === expected.length && actual.every((value, index) => value === expected[index])
}
function expectedDshPackageFiles(manifest: PackageManifest): readonly string[] {
const extras = manifest.name ? packageFileExtras[manifest.name] ?? [] : []
if (extras.length > 0) {
return [
'lib/index.js',
...manifest.bin ? ['lib/bin.js'] : [],
...extras,
'lib/types/**/*.d.ts',
'lib/types/**/*.d.ts.map',
'src',
]
}
workflow: swap the engine's internals to node:worker_threads In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
2026-07-09 18:39:31 +08:00
if (manifest.bin) return dshBinPackageFiles
// A declared "./worker" subpath export sanctions the one extra runtime
// bundle a worker-thread entry needs (and NodeNext/publint then validate
// that subpath's targets like any other export).
if (manifest.exports?.['./worker']) return dshWorkerPackageFiles
return dshPackageFiles
}
2026-06-16 14:55:37 +08:00
function checkWorkspace({ dir, manifest }: WorkspaceManifest): string[] {
const errors: string[] = []
const label = manifest.name ?? dir
if (manifest.private !== true) {
errors.push(`${label}: package.json must set "private": true`)
}
if (manifest.name && vendoredPackages.has(manifest.name)) {
return errors
}
if (manifest.name?.startsWith('@deepseek-ai/dsh-') && manifest.name !== '@deepseek-ai/dsh-root') {
const peer = manifest.peerDependencies?.cordis
const dev = manifest.devDependencies?.cordis
if (!peer) errors.push(`${label}: cordis must be a peerDependency`)
if (!dev) errors.push(`${label}: cordis must also be a devDependency`)
if (peer && dev && peer !== dev) {
errors.push(`${label}: cordis peer (${peer}) and dev (${dev}) ranges must match`)
}
if (manifest.version !== repositoryVersion) {
errors.push(`${label}: package.json version must match root version ${repositoryVersion ?? '(missing)'}`)
2026-06-16 14:55:37 +08:00
}
if (manifest.type !== 'module') {
errors.push(`${label}: package.json must set "type": "module"`)
}
if (manifest.main !== 'lib/index.js') {
errors.push(`${label}: package.json must set "main": "lib/index.js"`)
}
if (manifest.types !== 'lib/types/index.d.ts') {
errors.push(`${label}: package.json must set "types": "lib/types/index.d.ts"`)
}
if (manifest.exports?.['.']?.types !== './lib/types/index.d.ts') {
errors.push(`${label}: package.json exports["."].types must be "./lib/types/index.d.ts"`)
}
if (manifest.exports?.['.']?.default !== './lib/index.js') {
errors.push(`${label}: package.json exports["."].default must be "./lib/index.js"`)
}
const expectedFiles = expectedDshPackageFiles(manifest)
if (!sameStringList(manifest.files, expectedFiles)) {
errors.push(`${label}: package.json files must be ${JSON.stringify(expectedFiles)}`)
}
2026-06-16 14:55:37 +08:00
}
return errors.map(error => `${relative(root, join(root, dir, 'package.json'))}: ${error}`)
}
/**
* Enforce `packages/<group>/<pkg>`: groups are open-named containers without a
* package.json, and packages may be neither flat nor more deeply nested.
*/
function checkHierarchyShape(): string[] {
const errors: string[] = []
const packagesRoot = join(root, 'packages')
for (const group of readdirSync(packagesRoot, { withFileTypes: true })) {
if (!group.isDirectory()) continue
const groupRel = join('packages', group.name)
if (existsSync(join(packagesRoot, group.name, 'package.json'))) {
errors.push(`${groupRel}: a group dir must not contain a package.json — packages live at packages/<group>/<pkg>, not directly under packages/`)
continue
}
for (const pkg of readdirSync(join(packagesRoot, group.name), { withFileTypes: true })) {
if (!pkg.isDirectory()) continue
if (localArtifactDirs.has(pkg.name)) continue
const pkgRel = join(groupRel, pkg.name)
if (!existsSync(join(packagesRoot, group.name, pkg.name, 'package.json'))) {
errors.push(`${pkgRel}: expected a package here (no package.json found) — the hierarchy is exactly packages/<group>/<pkg>, no deeper nesting`)
}
}
}
return errors
}
function checkRepositoryVersion(): string[] {
if (repositoryVersion && /^\d+\.\d+\.\d+$/.test(repositoryVersion)) return []
return ['package.json: version must be stable X.Y.Z']
}
const errors = [
...checkRepositoryVersion(),
...workspaceManifests().flatMap(checkWorkspace),
...checkHierarchyShape(),
]
2026-06-16 14:55:37 +08:00
if (errors.length > 0) {
console.error(errors.join('\n'))
process.exitCode = 1
}