mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
Add examples/coding-agent and the docs cookbook
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).
This commit is contained in:
36
examples/coding-agent/src/session-jsonl.ts
Normal file
36
examples/coding-agent/src/session-jsonl.ts
Normal file
@@ -0,0 +1,36 @@
|
||||
import { appendFile } from 'node:fs/promises'
|
||||
import { join } from 'node:path'
|
||||
import type { Context } from 'cordis'
|
||||
import type { Session, SessionEvent } from '@deepseek-ai/dsh-session'
|
||||
|
||||
export const name = 'session-jsonl'
|
||||
export const inject = ['sessions']
|
||||
|
||||
/**
|
||||
* Minimal persistence plugin: buffers session events (write-behind) and
|
||||
* drains to a JSONL file at every `session/flush` checkpoint — the pattern a
|
||||
* real JSONL/sqlite persistence plugin would follow.
|
||||
*/
|
||||
export function apply(ctx: Context) {
|
||||
const buffers = new Map<Session, SessionEvent[]>()
|
||||
const path = (session: Session) => join(import.meta.dirname, '..', `${session.id}.jsonl`)
|
||||
|
||||
ctx.on('session/event', (session, event) => {
|
||||
let buffer = buffers.get(session)
|
||||
if (!buffer) buffers.set(session, buffer = [])
|
||||
buffer.push(event)
|
||||
})
|
||||
|
||||
const flush = async (session: Session) => {
|
||||
const buffer = buffers.get(session)
|
||||
if (!buffer?.length) return
|
||||
const lines = buffer.splice(0).map(event => JSON.stringify(event) + '\n').join('')
|
||||
await appendFile(path(session), lines)
|
||||
}
|
||||
|
||||
ctx.on('session/flush', flush)
|
||||
ctx.effect(() => () => {
|
||||
// drain remaining buffers on dispose
|
||||
for (const session of buffers.keys()) void flush(session)
|
||||
}, 'session-jsonl')
|
||||
}
|
||||
119
examples/coding-agent/src/stdio-chat.ts
Normal file
119
examples/coding-agent/src/stdio-chat.ts
Normal file
@@ -0,0 +1,119 @@
|
||||
import { createInterface } from 'node:readline'
|
||||
import type { Context } from 'cordis'
|
||||
import type {} from '@deepseek-ai/dsh-agent'
|
||||
|
||||
export const name = 'stdio-chat'
|
||||
export const inject = ['agents']
|
||||
|
||||
// Copied from examples/echo-agent (welcome text + reasoning rendering
|
||||
// adjusted). Deliberately example-local rather than a shared package — two
|
||||
// examples don't justify the abstraction yet; revisit at the third.
|
||||
|
||||
/**
|
||||
* Minimal UI plugin: reads lines from stdin → agent.send(); renders the
|
||||
* agent's stream chunks and tool activity to stdout. Demonstrates that a UI
|
||||
* is "just a plugin" — it only consumes the agent/* event taxonomy.
|
||||
*/
|
||||
export function apply(ctx: Context) {
|
||||
let inReasoning = false
|
||||
ctx.on('agent/stream-chunk', (_agent, _turn, _step, chunk) => {
|
||||
if (chunk.type === 'reasoning-delta') {
|
||||
// Dim the chain-of-thought so the answer stands out.
|
||||
if (!inReasoning) process.stdout.write('\x1B[2m')
|
||||
inReasoning = true
|
||||
process.stdout.write(chunk.text)
|
||||
} else if (chunk.type === 'text-delta') {
|
||||
if (inReasoning) process.stdout.write('\x1B[0m\n')
|
||||
inReasoning = false
|
||||
process.stdout.write(chunk.text)
|
||||
}
|
||||
})
|
||||
|
||||
ctx.on('agent/turn-start', (agent, turn) => {
|
||||
process.stdout.write(`\n[${agent.id} turn ${turn}] `)
|
||||
})
|
||||
|
||||
ctx.on('agent/turn-end', () => {
|
||||
if (inReasoning) process.stdout.write('\x1B[0m')
|
||||
inReasoning = false
|
||||
process.stdout.write('\n> ')
|
||||
})
|
||||
|
||||
ctx.on('session/event', (_session, event) => {
|
||||
if (event.type === 'tool/call') {
|
||||
const { name: toolName, arguments: args } = event.data
|
||||
if (inReasoning) process.stdout.write('\x1B[0m')
|
||||
inReasoning = false
|
||||
process.stdout.write(`\n [tool call] ${toolName}(${args})`)
|
||||
} else if (event.type === 'tool/result') {
|
||||
const { content } = event.data
|
||||
const text = content.filter(b => b.type === 'text').map(b => b.text).join('')
|
||||
process.stdout.write(`\n [tool result] ${text}\n `)
|
||||
}
|
||||
})
|
||||
|
||||
ctx.effect(() => {
|
||||
const reader = createInterface({ input: process.stdin })
|
||||
// Piped-input exit, once stdin reaches EOF:
|
||||
// - If no line ever submitted work (empty stdin, blank-only lines), exit
|
||||
// immediately — no turn will ever start, so there is nothing to wait
|
||||
// for. (Gating on an observed 'running' here would hang forever.)
|
||||
// - If work WAS submitted, exit the next time the agent settles to idle
|
||||
// AFTER having run. Two subtleties this handles: the loop batches
|
||||
// several queued messages into ONE turn (one idle), so we don't count
|
||||
// sends; and agent.send() does NOT synchronously flip status to
|
||||
// 'running', so requiring an observed 'running' first (`sawRunning`)
|
||||
// avoids exiting in the gap before the turn starts and dropping work.
|
||||
let stdinClosed = false
|
||||
let disposed = false
|
||||
let submittedWork = false
|
||||
let sawRunning = false
|
||||
|
||||
const maybeExit = (): void => {
|
||||
if (disposed || !stdinClosed) return
|
||||
// No work submitted: nothing will ever run, exit straight away.
|
||||
// Work submitted: wait until a turn has run and the agent is idle.
|
||||
if (submittedWork) {
|
||||
if (!sawRunning) return
|
||||
const agent = ctx.agents.get('main')
|
||||
if (agent && agent.status !== 'idle') return // a turn is still running
|
||||
}
|
||||
// Let any final output flush, then exit.
|
||||
setTimeout(() => process.exit(0), 200)
|
||||
}
|
||||
|
||||
const disposeStatusListener = ctx.on('agent/status', (subject, status) => {
|
||||
if (subject.id !== 'main') return
|
||||
if (status === 'running') sawRunning = true
|
||||
if (status === 'idle') maybeExit()
|
||||
})
|
||||
|
||||
reader.on('line', (line) => {
|
||||
const text = line.trim()
|
||||
if (!text) return
|
||||
const agent = ctx.agents.get('main')
|
||||
if (!agent) {
|
||||
console.error('agent "main" is not running')
|
||||
return
|
||||
}
|
||||
submittedWork = true
|
||||
if (agent.status === 'running') {
|
||||
agent.steer([{ type: 'text', text }])
|
||||
} else {
|
||||
agent.send([{ type: 'text', text }])
|
||||
}
|
||||
})
|
||||
reader.on('close', () => {
|
||||
// Fires for BOTH stdin EOF and plugin disposal (reader.close() below);
|
||||
// `disposed` guards teardown so HMR/dispose never exits the process.
|
||||
stdinClosed = true
|
||||
maybeExit()
|
||||
})
|
||||
process.stdout.write('coding-agent ready. Give it a coding task (bash is its only tool).\n> ')
|
||||
return () => {
|
||||
disposed = true
|
||||
disposeStatusListener()
|
||||
reader.close()
|
||||
}
|
||||
}, 'stdio-chat')
|
||||
}
|
||||
Reference in New Issue
Block a user