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).
56 lines
2.1 KiB
TypeScript
56 lines
2.1 KiB
TypeScript
import { Context } from 'cordis'
|
|
import LlmService from '@deepseek-ai/dsh-llm'
|
|
import SessionStore from '@deepseek-ai/dsh-session'
|
|
import type { SessionEvent } from '@deepseek-ai/dsh-session'
|
|
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
|
import ToolRegistry from '@deepseek-ai/dsh-tools'
|
|
import AgentRegistry from '@deepseek-ai/dsh-agent'
|
|
import AgentLoop, { LoopAgent } from '@deepseek-ai/dsh-agent-loop'
|
|
import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
|
|
import * as ToolBash from '@deepseek-ai/dsh-tool-bash'
|
|
import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
|
|
|
|
/**
|
|
* Shared harness for the coding-agent e2e suites: the full plugin stack
|
|
* with the real DeepSeek adapter and the real bash tool. Lives outside the
|
|
* *.e2e.ts pattern so importing it never re-registers another file's tests.
|
|
*/
|
|
|
|
export const SYSTEM_PROMPT = 'You are a coding agent. Your only tool is bash; '
|
|
+ 'do file operations with cat/grep/heredocs, check [exit code: N] markers, '
|
|
+ 'and report results briefly.'
|
|
|
|
export async function codingHarness(workdir: string): Promise<Context> {
|
|
const ctx = new Context()
|
|
await ctx.plugin(LlmService)
|
|
await ctx.plugin(SessionStore)
|
|
await ctx.plugin(SystemPrompt)
|
|
await ctx.plugin(ToolRegistry)
|
|
await ctx.plugin(AgentRegistry)
|
|
await ctx.plugin(AgentLoop, { agents: [] })
|
|
await ctx.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] })
|
|
await ctx.plugin(LocalBashExecutor, { cwd: workdir, timeoutMs: 30_000 })
|
|
await ctx.plugin(ToolBash)
|
|
return ctx
|
|
}
|
|
|
|
export function waitForIdle(ctx: Context, agent: LoopAgent): Promise<void> {
|
|
return new Promise((resolve) => {
|
|
const dispose = ctx.on('agent/status', (subject, status) => {
|
|
if (subject === agent && status === 'idle') {
|
|
dispose()
|
|
resolve()
|
|
}
|
|
})
|
|
})
|
|
}
|
|
|
|
export function finalText(events: SessionEvent[]): string {
|
|
const message = events.findLast(event => event.type === 'assistant/message')
|
|
if (message?.type !== 'assistant/message') return ''
|
|
return message.data.content
|
|
.filter(block => block.type === 'text')
|
|
.map(block => block.text)
|
|
.join('')
|
|
}
|