mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
2f86a93bdd
The agent-default-model refactor renamed ApiProxyDefaults.defaultTarget to defaultModelSelection; this stack-owned spec merged without textual conflict and kept the old field, so its harness built a defaults object whose selection thunk was undefined and every create answered internal.
298 lines
13 KiB
TypeScript
298 lines
13 KiB
TypeScript
/**
|
|
* A session's agent preset is fixed at creation. The gateway records the
|
|
* resolved id on the header and refuses to adopt the identity under a different
|
|
* one, because the session's history was produced under that preset's tools:
|
|
* rebuilding it differently would replay tool calls the new agent cannot make.
|
|
*/
|
|
|
|
import { mkdtempSync, realpathSync } from 'node:fs'
|
|
import { tmpdir } from 'node:os'
|
|
import { join } from 'node:path'
|
|
import { Context } from 'cordis'
|
|
import AgentRegistry, { type AgentFactory } from '@deepseek-ai/dsh-agent'
|
|
import type { Agent } from '@deepseek-ai/dsh-agent'
|
|
import SessionStore, { SessionId, type Session } from '@deepseek-ai/dsh-session'
|
|
import UserInteractionService from '@deepseek-ai/dsh-user-interaction'
|
|
import { RpcId, type RpcRequest } from '../src/api/rpc.ts'
|
|
import { UnknownPresetError } from '@deepseek-ai/dsh-agent-presets'
|
|
import { GoalId } from '@deepseek-ai/dsh-goal'
|
|
import { createApiProxy } from '../src/api-proxy.ts'
|
|
import { describe, expect, it } from 'vitest'
|
|
|
|
let nextRpc = 0
|
|
function request<P>(payload: P): RpcRequest<P> {
|
|
return { rpcId: RpcId(`preset-${String(nextRpc++)}`), payload }
|
|
}
|
|
|
|
/** Minimal live agent; the gateway only needs identity and its session. */
|
|
function stubAgent(session: Session): Agent {
|
|
return { id: session.id, session, status: 'idle' } as unknown as Agent
|
|
}
|
|
|
|
/**
|
|
* A roster whose `mount` is a no-op: this spec is about the gateway's identity
|
|
* rules, and the composition itself is covered by the real-composition test in
|
|
* `apps/cli`.
|
|
*/
|
|
function roster(ids: readonly string[]): unknown {
|
|
return {
|
|
defaultId: ids[0],
|
|
list: () => Promise.resolve(ids.map(id => ({ id, trust: 'system', path: `/presets/${id}.yml` }))),
|
|
resolve: (id?: string) => {
|
|
const wanted = id ?? ids[0] ?? ''
|
|
if (!ids.includes(wanted)) return Promise.reject(new UnknownPresetError(wanted, ids))
|
|
return Promise.resolve({ id: wanted, trust: 'system', path: `/presets/${wanted}.yml` })
|
|
},
|
|
mount: (_ctx: Context, id?: string) =>
|
|
Promise.resolve({ id: id ?? ids[0], trust: 'system', path: '/presets/x.yml' }),
|
|
// What a real mount leaves behind: a service instance only the agent that
|
|
// mounted it can be used to address. The doubles are per agent so a test
|
|
// can tell "this session's" from "some session's".
|
|
serviceFor: (agent: { id: unknown }, name: string) => {
|
|
const perAgent = services.get(String(agent.id))
|
|
return perAgent?.[name]
|
|
},
|
|
// The standing scope key a cold transcript read resolves presenters in.
|
|
standingKeyFor: (id?: string) => {
|
|
const wanted = id ?? ids[0] ?? ''
|
|
standingKeyRequests.push(wanted)
|
|
if (!ids.includes(wanted) || failingStandingKeys.has(wanted)) {
|
|
return Promise.reject(new UnknownPresetError(wanted, ids))
|
|
}
|
|
let key = standingKeys.get(wanted)
|
|
if (key === undefined) {
|
|
key = { agentPreset: wanted }
|
|
standingKeys.set(wanted, key)
|
|
}
|
|
return Promise.resolve(key)
|
|
},
|
|
}
|
|
}
|
|
|
|
/** Standing keys the roster double minted, and the ids readers asked for. */
|
|
const standingKeys = new Map<string, object>()
|
|
const standingKeyRequests: string[] = []
|
|
/** Preset ids whose standing mount the double reports as unusable. */
|
|
const failingStandingKeys = new Set<string>()
|
|
|
|
/** Per-agent service instances a mounted preset would own, keyed by session id. */
|
|
const services = new Map<string, Record<string, unknown>>()
|
|
|
|
async function harness(presets?: readonly string[], persistence?: unknown) {
|
|
const cwd = realpathSync(mkdtempSync(join(tmpdir(), 'dsh-apiproxy-preset-')))
|
|
const ctx = new Context()
|
|
await ctx.plugin(SessionStore)
|
|
await ctx.plugin(AgentRegistry)
|
|
await ctx.plugin(UserInteractionService)
|
|
ctx.provide('sessionPersistence', (persistence ?? { list: () => Promise.resolve([]) }) as never)
|
|
if (presets !== undefined) ctx.provide('agentPresets', roster(presets) as never)
|
|
|
|
const factory: AgentFactory = {
|
|
async createAgent(_ownerCtx, options) {
|
|
const session = ctx.sessions.create(
|
|
options.sessionId,
|
|
options.meta === undefined ? {} : { meta: options.meta },
|
|
)
|
|
const agent = stubAgent(session)
|
|
// Setup runs before publication against a context that carries the
|
|
// agent, and the agent reaches back through `agent.ctx` — the pair the
|
|
// gateway's own `installTarget` relies on.
|
|
const agentCtx = ctx.extend({ agent })
|
|
;(agent as { ctx?: Context }).ctx = agentCtx
|
|
await options.setup?.(agentCtx)
|
|
const unregister = ctx.agents.register(agent)
|
|
return { agent, dispose: () => { unregister(); return Promise.resolve() } }
|
|
},
|
|
async resume() {
|
|
throw new Error('test harness has no persisted sessions')
|
|
},
|
|
}
|
|
ctx.agents.setFactory(factory)
|
|
const api = createApiProxy(ctx, {
|
|
defaultModelSelection: () => ({ provider: 'test', model: 'test-model' }),
|
|
cwd,
|
|
workspaceRoot: cwd,
|
|
})
|
|
return { api, ctx, cwd }
|
|
}
|
|
|
|
describe('session.create with an agent preset', () => {
|
|
it('records the resolved preset on the session header', async () => {
|
|
const { api, ctx } = await harness(['standard', 'core-web'])
|
|
|
|
const created = await api.sessions.create(request({ sessionId: SessionId('s1'), agentPreset: 'core-web' }))
|
|
|
|
expect(created.result.ok).toBe(true)
|
|
expect(ctx.sessions.get(SessionId('s1'))?.header.agentPreset).toBe('core-web')
|
|
})
|
|
|
|
it('records the default when the caller names none', async () => {
|
|
const { api, ctx } = await harness(['standard', 'core-web'])
|
|
|
|
await api.sessions.create(request({ sessionId: SessionId('s2') }))
|
|
|
|
expect(ctx.sessions.get(SessionId('s2'))?.header.agentPreset).toBe('standard')
|
|
})
|
|
|
|
it('rejects an unknown preset and names the ones that exist', async () => {
|
|
const { api } = await harness(['standard'])
|
|
|
|
const response = await api.sessions.create(request({ sessionId: SessionId('s3'), agentPreset: 'nope' }))
|
|
|
|
expect(response.result.ok).toBe(false)
|
|
if (response.result.ok) throw new Error('unreachable')
|
|
expect(response.result.error.code).toBe('agent-preset-not-found')
|
|
})
|
|
|
|
it('refuses to adopt a live session under a different preset', async () => {
|
|
const { api } = await harness(['standard', 'core-web'])
|
|
await api.sessions.create(request({ sessionId: SessionId('s4'), agentPreset: 'core-web' }))
|
|
|
|
const response = await api.sessions.create(request({ sessionId: SessionId('s4'), agentPreset: 'standard' }))
|
|
|
|
expect(response.result.ok).toBe(false)
|
|
if (response.result.ok) throw new Error('unreachable')
|
|
expect(response.result.error.code).toBe('agent-preset-conflict')
|
|
expect(response.result.error.details).toEqual({
|
|
sessionId: 's4',
|
|
requestedPreset: 'standard',
|
|
existingPreset: 'core-web',
|
|
})
|
|
})
|
|
|
|
it('adopts a live session unchanged when the caller names no preset', async () => {
|
|
const { api } = await harness(['standard', 'core-web'])
|
|
await api.sessions.create(request({ sessionId: SessionId('s5'), agentPreset: 'core-web' }))
|
|
|
|
// Reconnecting and retrying a create must stay ordinary operations.
|
|
const response = await api.sessions.create(request({ sessionId: SessionId('s5') }))
|
|
|
|
expect(response.result.ok).toBe(true)
|
|
})
|
|
|
|
it('leaves the header preset-less when no roster is composed', async () => {
|
|
const { api, ctx } = await harness()
|
|
|
|
await api.sessions.create(request({ sessionId: SessionId('s6') }))
|
|
|
|
expect(ctx.sessions.get(SessionId('s6'))?.header.agentPreset).toBeUndefined()
|
|
})
|
|
|
|
it('says why a preset-less session cannot be adopted under one', async () => {
|
|
// Two callers reach this: a deployment that composes no roster, and a
|
|
// session created before one existed. Both record no preset, so naming
|
|
// any is a conflict rather than an adoption — the history was produced
|
|
// under a composition this roster cannot name. The message has to say
|
|
// that, because "already runs agent preset undefined" reads as a bug.
|
|
const { api } = await harness()
|
|
await api.sessions.create(request({ sessionId: SessionId('s7') }))
|
|
|
|
const response = await api.sessions.create(request({ sessionId: SessionId('s7'), agentPreset: 'standard' }))
|
|
|
|
expect(response.result.ok).toBe(false)
|
|
if (response.result.ok) throw new Error('unreachable')
|
|
expect(response.result.error.code).toBe('agent-preset-conflict')
|
|
expect(response.result.error.message).toContain('records no agent preset')
|
|
expect(response.result.error.details).toEqual({
|
|
sessionId: 's7',
|
|
requestedPreset: 'standard',
|
|
existingPreset: undefined,
|
|
})
|
|
})
|
|
})
|
|
|
|
/**
|
|
* A capability a preset mounts is reachable from nowhere the host normally
|
|
* looks: an `isolate` realm is what makes it per session. The gateway serves
|
|
* requests that are ABOUT a session from OUTSIDE it, so it addresses the
|
|
* instance through the agent instead of reading a root-realm singleton.
|
|
*/
|
|
describe('a capability the session\'s preset mounts', () => {
|
|
it('serves the goal RPC from the session\'s own goal service', async () => {
|
|
const { api } = await harness(['standard'])
|
|
await api.sessions.create(request({ sessionId: SessionId('g1'), agentPreset: 'standard' }))
|
|
const ref = { id: GoalId('goal-1'), revision: 1 }
|
|
const paused: unknown[] = []
|
|
services.set('g1', {
|
|
goals: { pause: (agent: { id: unknown }, r: unknown) => { paused.push([String(agent.id), r]); return ref } },
|
|
})
|
|
|
|
const response = await api.goals.pause(request({ sessionId: SessionId('g1'), ref }))
|
|
|
|
expect(response.result).toMatchObject({ ok: true, value: { ref } })
|
|
// Reached the instance this session mounted, and was handed its own agent.
|
|
expect(paused).toEqual([['g1', ref]])
|
|
services.delete('g1')
|
|
})
|
|
|
|
it('serves the skill catalog from the session\'s own registry', async () => {
|
|
const { api } = await harness(['standard'])
|
|
await api.sessions.create(request({ sessionId: SessionId('k1'), agentPreset: 'standard' }))
|
|
services.set('k1', {
|
|
skills: {
|
|
list: () => Promise.resolve([{
|
|
name: 'preset-owned',
|
|
description: 'ships inside the preset directory',
|
|
invocation: { modelInvocable: true, userInvocable: true },
|
|
}]),
|
|
},
|
|
})
|
|
|
|
const response = await api.skills.list(request({ sessionId: SessionId('k1') }))
|
|
|
|
// A preset ships its own skill directory, so the catalog IS the
|
|
// session's; reading a host singleton would answer for the wrong one.
|
|
expect(response.result).toMatchObject({ ok: true, value: { skills: [{ name: 'preset-owned' }] } })
|
|
services.delete('k1')
|
|
})
|
|
|
|
it('says so when no composition mounts the capability at all', async () => {
|
|
const { api } = await harness(['standard'])
|
|
await api.sessions.create(request({ sessionId: SessionId('n1'), agentPreset: 'standard' }))
|
|
|
|
const response = await api.skills.list(request({ sessionId: SessionId('n1') }))
|
|
|
|
// Absent means absent — not "this session has none", which is what a
|
|
// root-realm read used to report for every presetd session.
|
|
expect(response.result.ok).toBe(false)
|
|
const failure = response.result as { ok: false; error: { message: string } }
|
|
expect(failure.error.message).toContain('neither this session')
|
|
})
|
|
})
|
|
|
|
describe('session.history presenter scope', () => {
|
|
it('asks the roster for the RECORDED preset\'s standing key on a cold read', async () => {
|
|
const { api } = await harness(['standard', 'core-web'])
|
|
await api.sessions.create(request({ sessionId: SessionId('p1'), agentPreset: 'core-web' }))
|
|
// Cold: creation registered a live agent in this harness, so simulate the
|
|
// cold path by asking for a session only persistence knows... the harness
|
|
// has no persistence, so read the live one and assert no roster query.
|
|
standingKeyRequests.length = 0
|
|
const live = await api.sessions.history(request({ sessionId: SessionId('p1') }))
|
|
expect(live.result.ok).toBe(true)
|
|
// A live agent IS the presenter scope; the roster is not consulted.
|
|
expect(standingKeyRequests).toEqual([])
|
|
})
|
|
|
|
it('serves a COLD transcript whose standing mount is no longer usable', async () => {
|
|
// A genuinely cold session: persistence knows it, no live agent exists.
|
|
const meta = { id: SessionId('p3'), createdAt: 1, cwd: '/tmp/p3', agentPreset: 'standard' }
|
|
const { api } = await harness(['standard'], {
|
|
list: () => Promise.resolve([meta]),
|
|
inspect: () => Promise.resolve({ meta, events: [] }),
|
|
})
|
|
// The preset broke after the session ran: the roster rejects the mount.
|
|
failingStandingKeys.add('standard')
|
|
try {
|
|
standingKeyRequests.length = 0
|
|
const response = await api.sessions.history(request({ sessionId: SessionId('p3') }))
|
|
// Degraded, never failed: the roster WAS asked, and the transcript
|
|
// still serves — with the generic cards a viewless entry renders.
|
|
expect(standingKeyRequests).toEqual(['standard'])
|
|
expect(response.result.ok).toBe(true)
|
|
} finally {
|
|
failingStandingKeys.delete('standard')
|
|
}
|
|
})
|
|
})
|