refactor: share loader smoke harness
This commit is contained in:
Tianyi Cui
@@ -13,7 +13,7 @@ Each example must have **both** kinds of end-to-end smoke, because they catch di
|
||||
|
||||
**Exception — keyless-by-nature examples.** An example whose model is itself a mock/deterministic stand-in (no real provider) has no meaningful with-key smoke; the keyless smoke is the complete requirement. State the exception inline in the test.
|
||||
|
||||
A keyless smoke that spawns the example from a temp cwd must set `TSX_TSCONFIG_PATH` to the repo-root tsconfig (the unbuilt `paths` map is found by searching UP from cwd), and pass `--expose-internals` when the `cordis.yml` loads the HMR plugin (mirror the `demo:*` script).
|
||||
A keyless stdio smoke uses `@deepseek-ai/dsh-loader-smoke`, which owns the isolated cwd and DSH homes, repo tsconfig pin, `--expose-internals`, subprocess deadline, EOF, captured diagnostics, forced kill, and cleanup. The example test supplies only its absolute bin/config/tsconfig paths, environment overrides, stdin lines, and output assertions.
|
||||
|
||||
## Current state
|
||||
|
||||
|
||||
@@ -1,99 +1,27 @@
|
||||
import { spawn, type ChildProcessWithoutNullStreams } from 'node:child_process'
|
||||
import { mkdtemp, rm } from 'node:fs/promises'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { join } from 'node:path'
|
||||
import { fileURLToPath } from 'node:url'
|
||||
import { afterEach, describe, expect, it } from 'vitest'
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { LOADER_SMOKE_TEST_TIMEOUT_MS, runLoaderSmoke } from '@deepseek-ai/dsh-loader-smoke'
|
||||
|
||||
/**
|
||||
* Keyless Loader-path smoke for the Code Mode overlay: boot the REAL
|
||||
* example through the `@deepseek-ai/dsh-stdio-agent` bin against
|
||||
* `code-mode.cordis.yml` (the cordis Loader, `unwrapExports`, the include
|
||||
* patches over ./cordis.yml, the worker-thread code runtime, and the
|
||||
* registry in `mode: code`), then close stdin with no prompt and assert
|
||||
* the Code Mode banner + a clean exit.
|
||||
*
|
||||
* No prompt is ever sent, so the model is NEVER called and no `run_code`
|
||||
* turn happens — a dummy key lets `llm-deepseek`'s key-PRESENT check boot
|
||||
* the tree. This is the export-shape guard (postmortem 0001) for the Code
|
||||
* Mode composition; the with-key proof lives in `code-mode.e2e.ts`.
|
||||
* Keyless Loader-path smoke for the Code Mode overlay: boot the real include
|
||||
* tree through stdio-agent and `code-mode.cordis.yml`, then close stdin without
|
||||
* a prompt and assert the banner. No model or `run_code` turn runs.
|
||||
*/
|
||||
|
||||
const binScript = fileURLToPath(new URL('../../../packages/ui/stdio-agent/src/bin.ts', import.meta.url))
|
||||
const configPath = fileURLToPath(new URL('../code-mode.cordis.yml', import.meta.url))
|
||||
const tsxLoader = fileURLToPath(import.meta.resolve('tsx'))
|
||||
// Dev/test run UNBUILT: resolve `@deepseek-ai/dsh-*` through the root tsconfig
|
||||
// `paths` map; tsx searches UP from cwd, and we spawn from a temp dir outside
|
||||
// the repo, so point it at the repo tsconfig.
|
||||
const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
|
||||
// The real-API workflow runs up to 14 e2e files at once. Cold tsx/Loader
|
||||
// startup can therefore outlive a tight smoke-test deadline before the child
|
||||
// emits any output; 30s still detects a wedged process without confusing
|
||||
// bounded CI contention with a lifecycle failure.
|
||||
const PROCESS_TIMEOUT_MS = 30_000
|
||||
// Leave enough room for the process-owned timeout to report captured output
|
||||
// before Vitest aborts the test itself.
|
||||
const TEST_TIMEOUT_MS = PROCESS_TIMEOUT_MS + 15_000
|
||||
|
||||
let child: ChildProcessWithoutNullStreams | undefined
|
||||
let workdir: string | undefined
|
||||
|
||||
afterEach(async () => {
|
||||
if (child !== undefined && child.exitCode === null) child.kill('SIGKILL')
|
||||
child = undefined
|
||||
if (workdir !== undefined) await rm(workdir, { recursive: true, force: true })
|
||||
workdir = undefined
|
||||
})
|
||||
|
||||
async function bootAndEof(): Promise<{ stdout: string; code: number }> {
|
||||
workdir = await mkdtemp(join(tmpdir(), 'code-mode-smoke-'))
|
||||
const cwd = workdir
|
||||
return new Promise((resolve, reject) => {
|
||||
const proc = spawn(
|
||||
process.execPath,
|
||||
// --expose-internals: the included cordis.yml loads the HMR plugin (mirrors demo:code-mode).
|
||||
['--expose-internals', '--import', tsxLoader, binScript, configPath],
|
||||
{
|
||||
cwd,
|
||||
env: {
|
||||
...process.env,
|
||||
TSX_TSCONFIG_PATH: repoTsconfig,
|
||||
// A dummy key so llm-deepseek's apply() (key-PRESENT check only) boots.
|
||||
// No prompt is sent, so the adapter never streams — no network call.
|
||||
DEEPSEEK_API_KEY: 'keyless-smoke-no-call',
|
||||
},
|
||||
stdio: ['pipe', 'pipe', 'pipe'],
|
||||
},
|
||||
)
|
||||
child = proc
|
||||
let stdout = ''
|
||||
let stderr = ''
|
||||
proc.stdout.setEncoding('utf8')
|
||||
proc.stdout.on('data', (chunk: string) => { stdout += chunk })
|
||||
proc.stderr.setEncoding('utf8')
|
||||
proc.stderr.on('data', (chunk: string) => { stderr += chunk })
|
||||
|
||||
const timer = setTimeout(() => {
|
||||
proc.kill('SIGKILL')
|
||||
reject(new Error(`code-mode overlay did not exit within ${PROCESS_TIMEOUT_MS / 1_000}s. stdout:\n${stdout}\nstderr:\n${stderr}`))
|
||||
}, PROCESS_TIMEOUT_MS)
|
||||
|
||||
proc.on('exit', (code) => {
|
||||
clearTimeout(timer)
|
||||
if (code === 0) resolve({ stdout, code })
|
||||
else reject(new Error(`code-mode overlay exited ${code}. stderr:\n${stderr}`))
|
||||
})
|
||||
proc.on('error', (err) => { clearTimeout(timer); reject(err) })
|
||||
|
||||
// No prompt — just EOF, so the stdio UI exits without ever running a turn.
|
||||
proc.stdin.end()
|
||||
})
|
||||
}
|
||||
const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
|
||||
|
||||
describe('code-mode overlay keyless smoke (real code-mode.cordis.yml via the Loader)', () => {
|
||||
it('boots the Code Mode plugin tree, prints its banner, and exits cleanly on EOF', async () => {
|
||||
const { stdout, code } = await bootAndEof()
|
||||
expect(code).toBe(0)
|
||||
const { stdout } = await runLoaderSmoke({
|
||||
label: 'code-mode overlay',
|
||||
tempDirPrefix: 'code-mode-smoke-',
|
||||
binScript,
|
||||
configPath,
|
||||
tsconfigPath,
|
||||
env: { DEEPSEEK_API_KEY: 'keyless-smoke-no-call' },
|
||||
})
|
||||
expect(stdout).toContain('code-mode agent ready.')
|
||||
}, TEST_TIMEOUT_MS)
|
||||
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
|
||||
})
|
||||
|
||||
@@ -1,112 +1,28 @@
|
||||
import { spawn, type ChildProcessWithoutNullStreams } from 'node:child_process'
|
||||
import { mkdtemp, rm } from 'node:fs/promises'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { join } from 'node:path'
|
||||
import { fileURLToPath } from 'node:url'
|
||||
import { afterEach, describe, expect, it } from 'vitest'
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { LOADER_SMOKE_TEST_TIMEOUT_MS, runLoaderSmoke } from '@deepseek-ai/dsh-loader-smoke'
|
||||
|
||||
/**
|
||||
* Keyless Loader-path smoke for examples/coding-agent: boot the REAL example
|
||||
* through the `@deepseek-ai/dsh-stdio-agent` bin against its `cordis.yml` (the
|
||||
* cordis Loader, `unwrapExports`, the full plugin tree incl. the
|
||||
* `@deepseek-ai/dsh-agent-core` bundle and the app's in-package readline UI
|
||||
* module), then close stdin with no prompt and assert the
|
||||
* ready banner + a clean exit.
|
||||
*
|
||||
* No prompt is ever sent, so the model is NEVER called — this is why it runs
|
||||
* without a real key. coding-agent's `cordis.yml` loads `llm-deepseek`, whose
|
||||
* `apply()` only requires a key to be PRESENT (it does not validate it and only
|
||||
* uses it when a stream actually starts), so a dummy key lets the tree boot
|
||||
* while the absence of any prompt guarantees no network call. The value is the
|
||||
* real-Loader-path guard that the composed tree boots (see postmortem 0001;
|
||||
* the app carries no `inject`, so its export SHAPE is pinned by the stdio-agent
|
||||
* unit suite's unwrap assertion, not by a crash here),
|
||||
* complementing coding-agent's with-key e2e suites which prove the real
|
||||
* product.
|
||||
* Keyless Loader-path smoke for examples/coding-agent: boot the real example
|
||||
* through the stdio-agent bin and its `cordis.yml`, then close stdin without a
|
||||
* prompt and assert the banner. The dummy key satisfies adapter construction;
|
||||
* immediate EOF guarantees there is no model call.
|
||||
*/
|
||||
|
||||
// TODO(loader-smoke-harness): extract the shared spawn/tempdir/timeout/EOF
|
||||
// harness used here, code-mode-keyless-smoke, and cordis-agent's keyless smoke.
|
||||
// The dsh-stdio-agent bin (the demo:repl entry) and this example's cordis.yml.
|
||||
// The bin resolves its config-path arg from CWD; the test spawns from a temp
|
||||
// cwd, so we pass the example config's ABSOLUTE path.
|
||||
const binScript = fileURLToPath(new URL('../../../packages/ui/stdio-agent/src/bin.ts', import.meta.url))
|
||||
const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url))
|
||||
const tsxLoader = fileURLToPath(import.meta.resolve('tsx'))
|
||||
// Dev/test run UNBUILT: resolve `@deepseek-ai/dsh-*` through the root tsconfig
|
||||
// `paths` map; tsx searches UP from cwd, and we spawn from a temp dir outside
|
||||
// the repo, so point it at the repo tsconfig (root is four levels up).
|
||||
const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
|
||||
// The real-API workflow runs up to 14 e2e files at once. Cold tsx/Loader
|
||||
// startup can therefore outlive a tight smoke-test deadline before the child
|
||||
// emits any output; 30s still detects a wedged process without confusing
|
||||
// bounded CI contention with a lifecycle failure.
|
||||
const PROCESS_TIMEOUT_MS = 30_000
|
||||
// Leave enough room for the process-owned timeout to report captured output
|
||||
// before Vitest aborts the test itself.
|
||||
const TEST_TIMEOUT_MS = PROCESS_TIMEOUT_MS + 15_000
|
||||
|
||||
let child: ChildProcessWithoutNullStreams | undefined
|
||||
let workdir: string | undefined
|
||||
|
||||
afterEach(async () => {
|
||||
if (child !== undefined && child.exitCode === null) child.kill('SIGKILL')
|
||||
child = undefined
|
||||
if (workdir !== undefined) await rm(workdir, { recursive: true, force: true })
|
||||
workdir = undefined
|
||||
})
|
||||
|
||||
async function bootAndEof(): Promise<{ stdout: string; code: number }> {
|
||||
workdir = await mkdtemp(join(tmpdir(), 'coding-smoke-'))
|
||||
const cwd = workdir
|
||||
return new Promise((resolve, reject) => {
|
||||
const proc = spawn(
|
||||
process.execPath,
|
||||
// --expose-internals: cordis.yml loads the HMR plugin (mirrors demo:repl).
|
||||
['--expose-internals', '--import', tsxLoader, binScript, configPath],
|
||||
{
|
||||
cwd,
|
||||
env: {
|
||||
...process.env,
|
||||
TSX_TSCONFIG_PATH: repoTsconfig,
|
||||
// A dummy key so llm-deepseek's apply() (key-PRESENT check only) boots.
|
||||
// No prompt is sent, so the adapter never streams — no network call.
|
||||
DEEPSEEK_API_KEY: 'keyless-smoke-no-call',
|
||||
DSH_HOME: join(cwd, '.dsh'),
|
||||
DSH_AGENTS_HOME: join(cwd, '.agents'),
|
||||
},
|
||||
stdio: ['pipe', 'pipe', 'pipe'],
|
||||
},
|
||||
)
|
||||
child = proc
|
||||
let stdout = ''
|
||||
let stderr = ''
|
||||
proc.stdout.setEncoding('utf8')
|
||||
proc.stdout.on('data', (chunk: string) => { stdout += chunk })
|
||||
proc.stderr.setEncoding('utf8')
|
||||
proc.stderr.on('data', (chunk: string) => { stderr += chunk })
|
||||
|
||||
const timer = setTimeout(() => {
|
||||
proc.kill('SIGKILL')
|
||||
reject(new Error(`coding-agent did not exit within ${PROCESS_TIMEOUT_MS / 1_000}s. stdout:\n${stdout}\nstderr:\n${stderr}`))
|
||||
}, PROCESS_TIMEOUT_MS)
|
||||
|
||||
proc.on('exit', (code) => {
|
||||
clearTimeout(timer)
|
||||
if (code === 0) resolve({ stdout, code })
|
||||
else reject(new Error(`coding-agent exited ${code}. stderr:\n${stderr}`))
|
||||
})
|
||||
proc.on('error', (err) => { clearTimeout(timer); reject(err) })
|
||||
|
||||
// No prompt — just EOF, so the stdio UI exits without ever running a turn.
|
||||
proc.stdin.end()
|
||||
})
|
||||
}
|
||||
const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
|
||||
|
||||
describe('coding-agent keyless smoke (real cordis.yml via the Loader)', () => {
|
||||
it('boots the full plugin tree, prints its banner, and exits cleanly on EOF', async () => {
|
||||
const { stdout, code } = await bootAndEof()
|
||||
expect(code).toBe(0)
|
||||
const { stdout } = await runLoaderSmoke({
|
||||
label: 'coding-agent',
|
||||
tempDirPrefix: 'coding-smoke-',
|
||||
binScript,
|
||||
configPath,
|
||||
tsconfigPath,
|
||||
env: { DEEPSEEK_API_KEY: 'keyless-smoke-no-call' },
|
||||
})
|
||||
expect(stdout).toContain('agent REPL ready.')
|
||||
}, TEST_TIMEOUT_MS)
|
||||
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
|
||||
})
|
||||
|
||||
@@ -1,102 +1,27 @@
|
||||
import { spawn, type ChildProcessWithoutNullStreams } from 'node:child_process'
|
||||
import { mkdtemp, rm } from 'node:fs/promises'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { join } from 'node:path'
|
||||
import { fileURLToPath } from 'node:url'
|
||||
import { afterEach, describe, expect, it } from 'vitest'
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { LOADER_SMOKE_TEST_TIMEOUT_MS, runLoaderSmoke } from '@deepseek-ai/dsh-loader-smoke'
|
||||
|
||||
/**
|
||||
* Keyless Loader-path smoke for examples/cordis-agent: boot the REAL example
|
||||
* through the `@deepseek-ai/dsh-stdio-agent` bin against its `cordis.yml` —
|
||||
* the cordis Loader, `unwrapExports`, the full plugin tree INCLUDING the
|
||||
* `@deepseek-ai/dsh-tool-cordis` package resolved by name (whose `inject`
|
||||
* would crash a collapsed export shape at load, see docs/postmortem/0001) —
|
||||
* then close stdin with no prompt and assert the ready banner + a clean exit.
|
||||
*
|
||||
* No prompt is ever sent, so the model is NEVER called — that is why it runs
|
||||
* without a real key: `llm-deepseek`'s apply() only requires a key to be
|
||||
* PRESENT, and the absence of any prompt guarantees no network call. The
|
||||
* with-key product proof lives in cordis-tools.e2e.ts.
|
||||
* Keyless Loader-path smoke for examples/cordis-agent: boot the real tree,
|
||||
* including tool-cordis resolved by package name, then close stdin without a
|
||||
* prompt and assert the banner. The dummy key never reaches a model call.
|
||||
*/
|
||||
|
||||
// The dsh-stdio-agent bin (the demo:cordis entry) and this example's cordis.yml.
|
||||
// The bin resolves its config-path arg from CWD; the test spawns from a temp
|
||||
// cwd, so we pass the example config's ABSOLUTE path.
|
||||
const binScript = fileURLToPath(new URL('../../../packages/ui/stdio-agent/src/bin.ts', import.meta.url))
|
||||
const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url))
|
||||
const tsxLoader = fileURLToPath(import.meta.resolve('tsx'))
|
||||
// Dev/test run UNBUILT: resolve `@deepseek-ai/dsh-*` through the root tsconfig
|
||||
// `paths` map; tsx searches UP from cwd, and we spawn from a temp dir outside
|
||||
// the repo, so point it at the repo tsconfig (root is three levels up).
|
||||
const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
|
||||
// The real-API workflow runs up to 14 e2e files at once. Cold tsx/Loader
|
||||
// startup can therefore outlive a tight smoke-test deadline before the child
|
||||
// emits any output; 30s still detects a wedged process without confusing
|
||||
// bounded CI contention with a lifecycle failure.
|
||||
const PROCESS_TIMEOUT_MS = 30_000
|
||||
// Leave enough room for the process-owned timeout to report captured output
|
||||
// before Vitest aborts the test itself.
|
||||
const TEST_TIMEOUT_MS = PROCESS_TIMEOUT_MS + 15_000
|
||||
|
||||
let child: ChildProcessWithoutNullStreams | undefined
|
||||
let workdir: string | undefined
|
||||
|
||||
afterEach(async () => {
|
||||
if (child !== undefined && child.exitCode === null) child.kill('SIGKILL')
|
||||
child = undefined
|
||||
if (workdir !== undefined) await rm(workdir, { recursive: true, force: true })
|
||||
workdir = undefined
|
||||
})
|
||||
|
||||
async function bootAndEof(): Promise<{ stdout: string; code: number }> {
|
||||
workdir = await mkdtemp(join(tmpdir(), 'cordis-smoke-'))
|
||||
const cwd = workdir
|
||||
return new Promise((resolve, reject) => {
|
||||
const proc = spawn(
|
||||
process.execPath,
|
||||
// --expose-internals: cordis.yml loads the HMR plugin (mirrors demo:cordis).
|
||||
['--expose-internals', '--import', tsxLoader, binScript, configPath],
|
||||
{
|
||||
cwd,
|
||||
env: {
|
||||
...process.env,
|
||||
TSX_TSCONFIG_PATH: repoTsconfig,
|
||||
// A dummy key so llm-deepseek's apply() (key-PRESENT check only) boots.
|
||||
// No prompt is sent, so the adapter never streams — no network call.
|
||||
DEEPSEEK_API_KEY: 'keyless-smoke-no-call',
|
||||
},
|
||||
stdio: ['pipe', 'pipe', 'pipe'],
|
||||
},
|
||||
)
|
||||
child = proc
|
||||
let stdout = ''
|
||||
let stderr = ''
|
||||
proc.stdout.setEncoding('utf8')
|
||||
proc.stdout.on('data', (chunk: string) => { stdout += chunk })
|
||||
proc.stderr.setEncoding('utf8')
|
||||
proc.stderr.on('data', (chunk: string) => { stderr += chunk })
|
||||
|
||||
const timer = setTimeout(() => {
|
||||
proc.kill('SIGKILL')
|
||||
reject(new Error(`cordis-agent did not exit within ${PROCESS_TIMEOUT_MS / 1_000}s. stdout:\n${stdout}\nstderr:\n${stderr}`))
|
||||
}, PROCESS_TIMEOUT_MS)
|
||||
|
||||
proc.on('exit', (code) => {
|
||||
clearTimeout(timer)
|
||||
if (code === 0) resolve({ stdout, code })
|
||||
else reject(new Error(`cordis-agent exited ${code}. stderr:\n${stderr}`))
|
||||
})
|
||||
proc.on('error', (err) => { clearTimeout(timer); reject(err) })
|
||||
|
||||
// No prompt — just EOF, so the stdio UI exits without ever running a turn.
|
||||
proc.stdin.end()
|
||||
})
|
||||
}
|
||||
const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
|
||||
|
||||
describe('cordis-agent keyless smoke (real cordis.yml via the Loader)', () => {
|
||||
it('boots the full plugin tree incl. tool-cordis, prints its banner, and exits cleanly on EOF', async () => {
|
||||
const { stdout, code } = await bootAndEof()
|
||||
expect(code).toBe(0)
|
||||
const { stdout } = await runLoaderSmoke({
|
||||
label: 'cordis-agent',
|
||||
tempDirPrefix: 'cordis-smoke-',
|
||||
binScript,
|
||||
configPath,
|
||||
tsconfigPath,
|
||||
env: { DEEPSEEK_API_KEY: 'keyless-smoke-no-call' },
|
||||
})
|
||||
expect(stdout).toContain('cordis-agent ready.')
|
||||
}, TEST_TIMEOUT_MS)
|
||||
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
|
||||
})
|
||||
|
||||
@@ -1,131 +1,43 @@
|
||||
import { spawn, type ChildProcessWithoutNullStreams } from 'node:child_process'
|
||||
import { mkdtemp, rm } from 'node:fs/promises'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { join } from 'node:path'
|
||||
import { fileURLToPath } from 'node:url'
|
||||
import { afterEach, describe, expect, it } from 'vitest'
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { LOADER_SMOKE_TEST_TIMEOUT_MS, runLoaderSmoke } from '@deepseek-ai/dsh-loader-smoke'
|
||||
|
||||
/**
|
||||
* Keyless Loader-path smoke for examples/echo-agent: boot the REAL example
|
||||
* through the `@deepseek-ai/dsh-stdio-agent` bin against this example's
|
||||
* `cordis.yml` (the cordis Loader, `unwrapExports`, the whole plugin tree),
|
||||
* pipe a script of stdin lines, and assert the rendered stdout.
|
||||
*
|
||||
* This is the guard the per-file unit suite structurally cannot be: it drives
|
||||
* the `@deepseek-ai/dsh-stdio-agent` app plugin, the `@deepseek-ai/dsh-agent-core`
|
||||
* bundle it loads, the app's in-package readline UI module, AND the
|
||||
* example-local `mock-llm.ts` / `echo-tool.ts` through their REAL load path
|
||||
* (see docs/postmortem/0001). The app itself carries no `inject`, so a stray
|
||||
* `export default` would boot rather than crash here — the export SHAPE is
|
||||
* pinned by the explicit unwrap assertion in the stdio-agent unit suite; this
|
||||
* smoke proves the composed tree actually runs. It needs no API key — the
|
||||
* `mock-echo` adapter never touches the network — so it runs in the default e2e
|
||||
* gate.
|
||||
*
|
||||
* Both branches of mock-llm.ts are exercised: an `echo …` line (the tool
|
||||
* round-trip → `ECHO: …`) and a plain line (the direct canned reply).
|
||||
* Keyless-by-nature Loader-path coverage for examples/echo-agent. The real
|
||||
* tree uses its deterministic mock model, so this suite is both the boot smoke
|
||||
* and the complete behavior proof for the example.
|
||||
*/
|
||||
|
||||
// The dsh-stdio-agent bin (the demo:echo entry) and this example's cordis.yml.
|
||||
// The bin resolves its config-path arg from CWD; the test spawns from a temp
|
||||
// cwd, so we pass the example config's ABSOLUTE path.
|
||||
const binScript = fileURLToPath(new URL('../../../packages/ui/stdio-agent/src/bin.ts', import.meta.url))
|
||||
const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url))
|
||||
const tsxLoader = fileURLToPath(import.meta.resolve('tsx'))
|
||||
// Dev/test run UNBUILT: `@deepseek-ai/dsh-*` imports resolve through the root
|
||||
// tsconfig `paths` map, which tsx finds by searching UP from cwd. We spawn from
|
||||
// a temp cwd OUTSIDE the repo, so point tsx at the repo tsconfig explicitly
|
||||
// (repo root is four levels up from examples/echo-agent/tests).
|
||||
const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
|
||||
// The real-API workflow runs up to 14 e2e files at once. Cold tsx/Loader
|
||||
// startup can therefore outlive a tight smoke-test deadline before the child
|
||||
// emits any output; 30s still detects a wedged process without confusing
|
||||
// bounded CI contention with a lifecycle failure.
|
||||
const PROCESS_TIMEOUT_MS = 30_000
|
||||
// Leave enough room for the process-owned timeout to report captured output
|
||||
// before Vitest aborts the test itself.
|
||||
const TEST_TIMEOUT_MS = PROCESS_TIMEOUT_MS + 15_000
|
||||
const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
|
||||
|
||||
let child: ChildProcessWithoutNullStreams | undefined
|
||||
let workdir: string | undefined
|
||||
|
||||
afterEach(async () => {
|
||||
if (child !== undefined && child.exitCode === null) child.kill('SIGKILL')
|
||||
child = undefined
|
||||
if (workdir !== undefined) await rm(workdir, { recursive: true, force: true })
|
||||
workdir = undefined
|
||||
})
|
||||
|
||||
/**
|
||||
* Boot echo-agent, write `lines` to its stdin, close stdin, and resolve with
|
||||
* the full stdout once the process exits (the stdio UI exits on EOF after the
|
||||
* agent settles). Rejects on a non-zero exit or the process deadline.
|
||||
*/
|
||||
async function runEcho(lines: string[]): Promise<{ stdout: string; code: number }> {
|
||||
workdir = await mkdtemp(join(tmpdir(), 'echo-smoke-'))
|
||||
const cwd = workdir
|
||||
return new Promise((resolve, reject) => {
|
||||
const proc = spawn(
|
||||
process.execPath,
|
||||
// --expose-internals: the example's cordis.yml loads the HMR plugin, which
|
||||
// requires it (mirrors the `demo:echo` script). The whole point is to boot
|
||||
// the example EXACTLY as it really runs, through the bin + Loader.
|
||||
['--expose-internals', '--import', tsxLoader, binScript, configPath],
|
||||
{
|
||||
cwd,
|
||||
env: {
|
||||
...process.env,
|
||||
TSX_TSCONFIG_PATH: repoTsconfig,
|
||||
DSH_HOME: join(cwd, '.dsh'),
|
||||
DSH_AGENTS_HOME: join(cwd, '.agents'),
|
||||
},
|
||||
stdio: ['pipe', 'pipe', 'pipe'],
|
||||
},
|
||||
)
|
||||
child = proc
|
||||
let stdout = ''
|
||||
let stderr = ''
|
||||
proc.stdout.setEncoding('utf8')
|
||||
proc.stdout.on('data', (chunk: string) => { stdout += chunk })
|
||||
proc.stderr.setEncoding('utf8')
|
||||
proc.stderr.on('data', (chunk: string) => { stderr += chunk })
|
||||
|
||||
const timer = setTimeout(() => {
|
||||
proc.kill('SIGKILL')
|
||||
reject(new Error(`echo-agent did not exit within ${PROCESS_TIMEOUT_MS / 1_000}s. stdout:\n${stdout}\nstderr:\n${stderr}`))
|
||||
}, PROCESS_TIMEOUT_MS)
|
||||
|
||||
proc.on('exit', (code) => {
|
||||
clearTimeout(timer)
|
||||
if (code === 0) resolve({ stdout, code })
|
||||
else reject(new Error(`echo-agent exited ${code}. stderr:\n${stderr}`))
|
||||
})
|
||||
proc.on('error', (err) => { clearTimeout(timer); reject(err) })
|
||||
|
||||
// Feed the script, then EOF so the stdio UI exits after the agent settles.
|
||||
for (const line of lines) proc.stdin.write(`${line}\n`)
|
||||
proc.stdin.end()
|
||||
async function runEcho(stdinLines: readonly string[]): Promise<string> {
|
||||
const { stdout } = await runLoaderSmoke({
|
||||
label: 'echo-agent',
|
||||
tempDirPrefix: 'echo-smoke-',
|
||||
binScript,
|
||||
configPath,
|
||||
tsconfigPath,
|
||||
stdinLines,
|
||||
})
|
||||
return stdout
|
||||
}
|
||||
|
||||
describe('echo-agent keyless smoke (real cordis.yml via the Loader)', () => {
|
||||
it('boots, prints its welcome banner, and exits cleanly on stdin EOF', async () => {
|
||||
const { stdout, code } = await runEcho([])
|
||||
expect(code).toBe(0)
|
||||
expect(stdout).toContain('echo-agent ready.')
|
||||
}, TEST_TIMEOUT_MS)
|
||||
expect(await runEcho([])).toContain('echo-agent ready.')
|
||||
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
|
||||
|
||||
it('runs the echo tool round-trip for an "echo …" line', async () => {
|
||||
const { stdout } = await runEcho(['echo hello world'])
|
||||
// mock-llm.ts emits a tool-call for the echo tool; echo-tool.ts uppercases.
|
||||
const stdout = await runEcho(['echo hello world'])
|
||||
expect(stdout).toContain('[tool call] echo')
|
||||
expect(stdout).toContain('[tool result] ECHO: HELLO WORLD')
|
||||
}, TEST_TIMEOUT_MS)
|
||||
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
|
||||
|
||||
it('streams a direct canned reply for a non-echo line', async () => {
|
||||
const { stdout } = await runEcho(['just chatting'])
|
||||
// The direct-response branch of mock-llm.ts quotes the input back.
|
||||
const stdout = await runEcho(['just chatting'])
|
||||
expect(stdout).toContain('just chatting')
|
||||
expect(stdout).not.toContain('[tool call]')
|
||||
}, TEST_TIMEOUT_MS)
|
||||
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
|
||||
})
|
||||
|
||||
Reference in New Issue
Block a user