Files
deepseek-harness/packages/core/agent/tests/agent.spec.ts
Tianyi Cui d6a2ab30c8 feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.

- Extract the `Branded<B>` primitive into a new standalone type-only package
  `@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
  dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
  dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
  dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
  generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
  the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
  the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
  SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
  that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
  agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
  at the config boundary and the inner create()/resume casts disappear (only the
  genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
  Map keys and public params/exports (SessionStore, AgentRegistry + factory
  options, the ACP session-id surface + ToolPresenter CallId map, the
  persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
  the Branded type-equiv at dsh-brand, fix stale param types in the session/
  agent/bash READMEs, regenerate the cordis catalog + module graph.

Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:19:59 +08:00

140 lines
5.4 KiB
TypeScript

import { describe, expect, it } from 'vitest'
import { Context } from 'cordis'
import { Session, SessionId } from '@deepseek-ai/dsh-session'
import AgentRegistry, { Agent, AgentId } from '@deepseek-ai/dsh-agent'
function stubAgent(rawId: string): Agent {
const id = AgentId(rawId)
return {
id,
options: {},
session: new Session(SessionId(`${id}-session`)),
status: 'idle',
send() {},
steer() {},
inject() {},
abort() {},
cancel() {},
whenIdle() { return Promise.resolve() },
}
}
describe('AgentRegistry', () => {
it('registers agents and emits created/disposed events', async () => {
const ctx = new Context()
await ctx.plugin(AgentRegistry)
const created: string[] = []
const disposed: string[] = []
ctx.on('agent/created', agent => void created.push(agent.id))
ctx.on('agent/disposed', agent => void disposed.push(agent.id))
const agent = stubAgent('a1')
const dispose = ctx.agents.register(agent)
expect(created).toEqual(['a1'])
expect(ctx.agents.get(AgentId('a1'))).toBe(agent)
expect(ctx.agents.list()).toEqual([agent])
dispose()
expect(disposed).toEqual(['a1'])
expect(ctx.agents.get(AgentId('a1'))).toBeUndefined()
})
it('rejects duplicate ids and unregisters on fiber dispose (HMR safety)', async () => {
const ctx = new Context()
await ctx.plugin(AgentRegistry)
ctx.agents.register(stubAgent('main'))
expect(() => ctx.agents.register(stubAgent('main'))).toThrow('already registered')
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
inner.agents.register(stubAgent('scoped'))
}, { inject: ['agents'] }))
expect(ctx.agents.list().map(a => a.id)).toEqual(['main', 'scoped'])
await fiber.dispose()
expect(ctx.agents.list().map(a => a.id)).toEqual(['main'])
})
it('rolls back the agent entry when an agent/created listener throws (P1-1)', async () => {
const ctx = new Context()
await ctx.plugin(AgentRegistry)
let threw = false
ctx.on('agent/created', () => {
if (!threw) { threw = true; throw new Error('boom created listener') }
})
// The throwing emit must roll the entry back, not leak it.
expect(() => ctx.agents.register(stubAgent('main'))).toThrow('boom created listener')
expect(ctx.agents.get(AgentId('main'))).toBeUndefined() // rolled back, not leaked
// A subsequent listener-free register of the SAME id succeeds and is
// tracked exactly once (the duplicate-id check is not wedged).
const dispose = ctx.agents.register(stubAgent('main'))
expect(ctx.agents.list().map(a => a.id)).toEqual(['main'])
dispose()
expect(ctx.agents.get(AgentId('main'))).toBeUndefined()
})
})
describe('AgentRegistry factory seam', () => {
/** A stub AgentFactory that records calls and returns a stub agent. */
function stubFactory() {
const calls: { create: unknown[]; resume: unknown[] } = { create: [], resume: [] }
const factory: import('@deepseek-ai/dsh-agent').AgentFactory = {
createAgent(options) {
calls.create.push(options)
return { agent: stubAgent(options.agentId), dispose: () => Promise.resolve() }
},
resume(options) {
calls.resume.push(options)
return Promise.resolve({ agent: stubAgent(options.agentId), dispose: () => Promise.resolve() })
},
}
return { factory, calls }
}
it('create()/resume() throw when no factory is registered', async () => {
const ctx = new Context()
await ctx.plugin(AgentRegistry)
expect(() => ctx.agents.create({ agentId: AgentId('a'), sessionId: SessionId('s') })).toThrow(/no agent factory/)
await expect(ctx.agents.resume({ agentId: AgentId('a'), resumeSessionId: SessionId('s') })).rejects.toThrow(/no agent factory/)
})
it('setFactory registers a factory; create/resume delegate to it', async () => {
const ctx = new Context()
await ctx.plugin(AgentRegistry)
const { factory, calls } = stubFactory()
ctx.agents.setFactory(factory)
const created = ctx.agents.create({ agentId: AgentId('c1'), sessionId: SessionId('sess-1'), meta: { cwd: '/w' } })
expect(created.agent.id).toBe('c1')
expect(calls.create).toEqual([{ agentId: AgentId('c1'), sessionId: SessionId('sess-1'), meta: { cwd: '/w' } }])
const resumed = await ctx.agents.resume({ agentId: AgentId('r1'), resumeSessionId: SessionId('old-sess') })
expect(resumed.agent.id).toBe('r1')
expect(calls.resume).toEqual([{ agentId: AgentId('r1'), resumeSessionId: SessionId('old-sess') }])
})
it('setFactory rejects a second factory', async () => {
const ctx = new Context()
await ctx.plugin(AgentRegistry)
ctx.agents.setFactory(stubFactory().factory)
expect(() => ctx.agents.setFactory(stubFactory().factory)).toThrow(/already registered/)
})
it('disposing the setFactory fiber clears the factory (HMR safety)', async () => {
const ctx = new Context()
await ctx.plugin(AgentRegistry)
let dispose!: () => void
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
dispose = inner.agents.setFactory(stubFactory().factory)
}, { inject: ['agents'] }))
expect(() => ctx.agents.create({ agentId: AgentId('a'), sessionId: SessionId('s') })).not.toThrow()
void dispose
await fiber.dispose()
// factory slot cleared → create throws again
expect(() => ctx.agents.create({ agentId: AgentId('a2'), sessionId: SessionId('s2') })).toThrow(/no agent factory/)
})
})