mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
3f83a4ee96
Review round 2 (tianyicui inline comments): - dsh-system-prompt itself registers the harness:identity (-100) and deployment:persona (0) sections — they must survive a swapped loop plugin, so they leave dsh-agent-loop; the persona text is the plugin's own validated 'persona' config. The model/cwd variables STAY on the loop: runtime facts of the agents it drives. - AgentOptions.systemPrompt is deleted with all its forwarding plumbing: the app configs' systemPrompt keys become 'persona' routed through dsh-agent-core (schema = z.intersect of the owners'), the ACP bridge and tool-subagent stop carrying persona configuration, and subagent children now render the deployment persona like every other agent. - Example personas drop transport/interface trivia (ACP, CLI) — facts irrelevant to the model. - Root CONTEXT.md removed (not idiomatic); its persona definition was wrong under the new ownership anyway. - Docs, READMEs, the prompt-variables RFC, and generated catalogs updated; new loop test pins the assemble-waterfall escape valve (an emptied assembly sends NO system field).
85 lines
3.8 KiB
TypeScript
85 lines
3.8 KiB
TypeScript
import { mkdtemp, readFile, rm } 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 { AgentId } from '@deepseek-ai/dsh-agent'
|
|
import { SessionId } from '@deepseek-ai/dsh-session'
|
|
import { fsHarness, waitForIdle } from './harness.ts'
|
|
|
|
/**
|
|
* With-key smoke for the filesystem tools: a REAL model drives the REAL
|
|
* read/write/edit tools (over the real local backend + policy gate), and we
|
|
* verify the WORLD — the file on disk — not the agent's self-report. This is the
|
|
* "green units, broken product" guard: mocks prove the plumbing, only a real
|
|
* model proves the tools actually work end-to-end. Key-gated (self-skips without
|
|
* DEEPSEEK_API_KEY).
|
|
*/
|
|
|
|
let ctx: Context | undefined
|
|
let workdir: string | undefined
|
|
|
|
afterEach(async () => {
|
|
await ctx?.fiber.dispose()
|
|
ctx = undefined
|
|
if (workdir !== undefined) await rm(workdir, { recursive: true, force: true })
|
|
workdir = undefined
|
|
})
|
|
|
|
const SYSTEM = 'You are a coding assistant. Use the write tool to create files, the read tool to inspect '
|
|
+ 'them, and the edit tool for literal replacements. Read a file before editing it. Keep replies terse.'
|
|
|
|
describe.skipIf(!process.env.DEEPSEEK_API_KEY)('fs tools with-key smoke', () => {
|
|
it('creates, reads, then edits a file — verified on disk', async () => {
|
|
workdir = await mkdtemp(join(tmpdir(), 'dsh-fs-e2e-'))
|
|
ctx = await fsHarness(workdir, SYSTEM)
|
|
// agentLoop.create prepares a session with no cwd, so the provider default
|
|
// (config.cwd = workdir) is the workspace.
|
|
const agent = ctx.agentLoop.create(AgentId('fs-e2e'), { model: 'deepseek-v4-flash' })
|
|
|
|
agent.send([{ type: 'text', text:
|
|
'Create a file named note.txt containing exactly the line: status: draft. '
|
|
+ 'Then read it back, then edit it to replace the literal word draft with final. '
|
|
+ 'Tell me when done.' }])
|
|
await waitForIdle(ctx, agent)
|
|
|
|
// Verify the WORLD: the edit landed on disk.
|
|
const content = await readFile(join(workdir, 'note.txt'), 'utf8')
|
|
expect(content).toContain('status: final')
|
|
expect(content).not.toContain('draft')
|
|
|
|
// The log records real read/write/edit tool calls (not bash).
|
|
const calls = [...agent.session.events].filter(e => e.type === 'tool/call').map(e => e.data.name)
|
|
expect(calls).toContain('write')
|
|
expect(calls).toContain('read')
|
|
expect(calls).toContain('edit')
|
|
}, 180_000)
|
|
|
|
it('resolves a relative path against the per-session cwd (factory meta.cwd)', async () => {
|
|
// config.cwd is the harness workdir, but the agent's SESSION cwd is a
|
|
// different dir; the write must land in the SESSION dir, proving the tool
|
|
// passes the per-session cwd (not the backend default).
|
|
const configDir = await mkdtemp(join(tmpdir(), 'dsh-fs-e2e-cfg-'))
|
|
workdir = configDir
|
|
const sessionDir = await mkdtemp(join(tmpdir(), 'dsh-fs-e2e-session-'))
|
|
try {
|
|
ctx = await fsHarness(configDir, SYSTEM)
|
|
const handle = ctx.agents.create({
|
|
agentId: AgentId('fs-e2e-cwd'),
|
|
sessionId: SessionId(`fs-e2e-cwd-${Date.now()}`),
|
|
meta: { cwd: sessionDir },
|
|
agentOptions: { model: 'deepseek-v4-flash' },
|
|
})
|
|
handle.agent.send([{ type: 'text', text:
|
|
'Use the write tool to create a file named where.txt containing exactly the line: here. Tell me when done.' }])
|
|
await waitForIdle(ctx, handle.agent)
|
|
|
|
// The file is in the SESSION dir, not the config dir.
|
|
expect(await readFile(join(sessionDir, 'where.txt'), 'utf8')).toContain('here')
|
|
await expect(readFile(join(configDir, 'where.txt'), 'utf8')).rejects.toMatchObject({ code: 'ENOENT' })
|
|
} finally {
|
|
await rm(sessionDir, { recursive: true, force: true })
|
|
}
|
|
}, 180_000)
|
|
})
|