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).
44 lines
1.7 KiB
TypeScript
44 lines
1.7 KiB
TypeScript
import { afterEach, describe, expect, it } from 'vitest'
|
|
import type { Context } from 'cordis'
|
|
import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts'
|
|
|
|
/**
|
|
* The first place a REAL model meets the REAL bash tool: the cheap canary
|
|
* before the coding-task e2e. Key-gated (see vitest.e2e.config.ts).
|
|
*/
|
|
|
|
let ctx: Context | undefined
|
|
|
|
afterEach(async () => {
|
|
// Always dispose the harness, even on failure/retry/timeout: agent-loop
|
|
// teardown stops the loop and LocalBashExecutor teardown kills any
|
|
// process the model left behind.
|
|
await ctx?.fiber.dispose()
|
|
ctx = undefined
|
|
})
|
|
|
|
describe.skipIf(!process.env.DEEPSEEK_API_KEY)('full loop: real model + real bash tool', () => {
|
|
it('runs a bash command on request and reports its output', async () => {
|
|
ctx = await codingHarness(process.cwd())
|
|
const agent = ctx.agentLoop.create('e2e-loop', {
|
|
model: 'deepseek-v4-flash',
|
|
systemPrompt: SYSTEM_PROMPT,
|
|
})
|
|
|
|
agent.send([{ type: 'text', text: 'Run `echo e2e-ok` with the bash tool and tell me its exact output.' }])
|
|
await waitForIdle(ctx, agent)
|
|
|
|
const events = [...agent.session.events]
|
|
const calls = events.filter(event => event.type === 'tool/call')
|
|
expect(calls.length).toBeGreaterThan(0)
|
|
expect(calls.some(event => event.data.name === 'bash')).toBe(true)
|
|
|
|
const results = events.filter(event => event.type === 'tool/result')
|
|
const resultTexts = results.flatMap(event =>
|
|
event.data.content.filter(block => block.type === 'text').map(block => block.text))
|
|
expect(resultTexts.some(text => text.includes('e2e-ok'))).toBe(true)
|
|
|
|
expect(finalText(events)).toContain('e2e-ok')
|
|
}, 120_000)
|
|
})
|