Tianyi Cui
e98c1c5d42
The first real agent wiring: DeepSeek V4 + the bash tool suite + stdio chat + JSONL persistence, runnable via yarn demo:coding (reads the gitignored repo-root .env through process.loadEnvFile). - examples/coding-agent: cordis.yml wiring both real plugin families (llm-deepseek with !!js env secrets; bash-local + tool-bash), a bash-only coding system prompt, a max-steps-guard plugin (bounds runaway turns via the agent/turn-continuation waterfall — abort() from step-end is a no-op by then), and a stdio UI with dimmed reasoning and exit-on-idle for piped stdin. - e2e (yarn test:e2e, key-gated): full-loop.e2e.ts runs a real model against the real bash tool; coding-task.e2e.ts is the swebench-style smoke — the model fixes a buggy add.js in a temp dir and the test re-runs node add.test.js itself rather than trusting the agent. - docs/cookbook: adding-a-package (the verified checklist), adding-a-tool (execute() contract, background pattern, seams), adding-an-llm-adapter (protocol obligations, mock-server testing, e2e policy). AGENTS.md layout/commands/secrets sections updated; architecture.md points at both examples and the cookbook. - vitest.e2e.config.ts: serialize test files + retry twice — parallel e2e files trip the shared internal key's concurrency quota. - fix: the !js YAML tag spelling in docs/JSDoc is actually !!js (js-yaml resolves custom tags under tag:yaml.org,2002:js).
87 lines
3.1 KiB
TypeScript
87 lines
3.1 KiB
TypeScript
import { spawnSync } from 'node:child_process'
|
|
import { mkdtemp, readFile, rm, writeFile } from 'node:fs/promises'
|
|
import { tmpdir } from 'node:os'
|
|
import { join } from 'node:path'
|
|
import { afterEach, describe, expect, it } from 'vitest'
|
|
import type { Context } from 'cordis'
|
|
import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts'
|
|
|
|
/**
|
|
* The swebench-style smoke test: a real model fixes a real bug in a temp
|
|
* directory using only the bash tool, and the fix is verified OUTSIDE the
|
|
* agent by re-running the test script. Key-gated.
|
|
*/
|
|
|
|
const TEST_FILE = [
|
|
"const assert = require('node:assert');",
|
|
"const { add } = require('./add.js');",
|
|
'assert.strictEqual(add(2, 3), 5);',
|
|
'assert.strictEqual(add(-1, 1), 0);',
|
|
"console.log('PASS');",
|
|
'',
|
|
].join('\n')
|
|
|
|
const BUGGY_ADD = [
|
|
'// A tiny module with an obvious bug.',
|
|
'function add(a, b) {',
|
|
' return a - b;',
|
|
'}',
|
|
'module.exports = { add };',
|
|
'',
|
|
].join('\n')
|
|
|
|
let workdir: string | undefined
|
|
let ctx: Context | undefined
|
|
|
|
afterEach(async () => {
|
|
// Dispose the harness even on failure/retry: agent-loop teardown stops the
|
|
// loop and LocalBashExecutor teardown kills anything the model left running.
|
|
await ctx?.fiber.dispose()
|
|
ctx = undefined
|
|
if (workdir !== undefined) await rm(workdir, { recursive: true, force: true })
|
|
workdir = undefined
|
|
})
|
|
|
|
describe.skipIf(!process.env.DEEPSEEK_API_KEY)('coding task: fix a failing test via bash', () => {
|
|
it('repairs add.js so node add.test.js passes', async () => {
|
|
workdir = await mkdtemp(join(tmpdir(), 'dsh-coding-task-'))
|
|
await writeFile(join(workdir, 'add.js'), BUGGY_ADD)
|
|
await writeFile(join(workdir, 'add.test.js'), TEST_FILE)
|
|
|
|
// Confirm the fixture actually fails before the agent touches it.
|
|
const before = spawnSync('node', ['add.test.js'], { cwd: workdir })
|
|
expect(before.status).not.toBe(0)
|
|
|
|
ctx = await codingHarness(workdir)
|
|
const agent = ctx.agentLoop.create('e2e-task', {
|
|
model: 'deepseek-v4-flash',
|
|
systemPrompt: SYSTEM_PROMPT,
|
|
})
|
|
|
|
agent.send([{
|
|
type: 'text',
|
|
text: 'In the current directory, `node add.test.js` fails because add.js has a bug. '
|
|
+ 'Fix add.js so the test passes, run `node add.test.js` to verify, and report the result. '
|
|
+ 'Do not modify add.test.js.',
|
|
}])
|
|
await waitForIdle(ctx, agent)
|
|
|
|
// The agent claims success…
|
|
const summary = finalText([...agent.session.events]).toLowerCase()
|
|
expect(summary.length).toBeGreaterThan(0)
|
|
|
|
// …and the world agrees: the test passes when WE run it, and the test
|
|
// file is byte-identical (an agent that neutered the test instead of
|
|
// fixing the bug fails here, not just on a keyword probe).
|
|
const untouchedTest = await readFile(join(workdir, 'add.test.js'), 'utf8')
|
|
expect(untouchedTest).toBe(TEST_FILE)
|
|
|
|
const after = spawnSync('node', ['add.test.js'], { cwd: workdir, encoding: 'utf8' })
|
|
expect(after.stdout).toContain('PASS')
|
|
expect(after.status).toBe(0)
|
|
|
|
const fixed = await readFile(join(workdir, 'add.js'), 'utf8')
|
|
expect(fixed).not.toMatch(/a\s*-\s*b/)
|
|
}, 180_000)
|
|
})
|