Merge remote-tracking branch 'origin/master' into worktree/agent-execution-context-rfc
# Conflicts: # docs/architecture.md # docs/config-catalog.md # docs/cordis-catalog/services.md # docs/module-graph.md # examples/coding-agent/tests/code-mode.e2e.ts # packages/context/workspace-context/tests/workspace-context.spec.ts # packages/core/README.md # packages/core/agent-loop/README.md # packages/core/agent-loop/tests/agent.spec.ts # packages/core/agent-loop/tests/cancel.spec.ts # packages/core/agent-loop/tests/config-session-id.spec.ts # packages/core/agent-loop/tests/contract-regressions.spec.ts # packages/core/agent-loop/tests/coverage-edges.spec.ts # packages/core/agent-loop/tests/interception.spec.ts # packages/core/agent-loop/tests/loop.spec.ts # packages/core/agent-loop/tests/properties.spec.ts # packages/core/agent-loop/tests/request-cache.e2e.ts # packages/core/agent-loop/tests/request-reconstruction.spec.ts # packages/core/agent-loop/tests/resume.spec.ts # packages/core/agent-loop/tests/scope-lifecycle.spec.ts # packages/core/agent-loop/tests/tool-calls.spec.ts # packages/core/agent-loop/tests/tool-order.spec.ts # packages/core/agent-loop/tests/turn-stop.spec.ts # packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts # website/zh-CN/api/harness/agent-loop.md
This commit is contained in:
Tianyi Cui
@@ -1,17 +1,12 @@
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import LlmService, { CallId, type Message } from '@deepseek-ai/dsh-llm'
|
||||
import SessionStore, { type SessionEvent, type TurnEndReason } from '@deepseek-ai/dsh-session'
|
||||
import SessionStore, { SessionId, type SessionEvent, type TurnEndReason } from '@deepseek-ai/dsh-session'
|
||||
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
||||
import ToolRegistry, { defineTool, type PostToolDecision, type PreToolDecision } from '@deepseek-ai/dsh-tools'
|
||||
import AgentRegistry, {
|
||||
AgentId,
|
||||
type ContinuationDecision,
|
||||
type PromptDecision,
|
||||
type SessionStartSource,
|
||||
} from '@deepseek-ai/dsh-agent'
|
||||
import AgentRegistry, { type Agent, type ContinuationDecision, type PromptDecision, type SessionStartSource } from '@deepseek-ai/dsh-agent'
|
||||
import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution'
|
||||
import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
|
||||
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
|
||||
import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts'
|
||||
|
||||
/**
|
||||
@@ -36,7 +31,7 @@ async function harness(adapter: MockAdapter) {
|
||||
return ctx
|
||||
}
|
||||
|
||||
function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
|
||||
function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
|
||||
return new Promise((resolve) => {
|
||||
const dispose = ctx.on('agent/status', (subject, status) => {
|
||||
if (subject === agent && status === 'idle') {
|
||||
@@ -47,11 +42,11 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
|
||||
})
|
||||
}
|
||||
|
||||
function send(agent: ReactLoopAgent, text: string) {
|
||||
function send(agent: Agent, text: string) {
|
||||
agent.send([{ type: 'text', text }])
|
||||
}
|
||||
|
||||
function events(agent: ReactLoopAgent): SessionEvent[] {
|
||||
function events(agent: Agent): SessionEvent[] {
|
||||
return [...agent.session.events]
|
||||
}
|
||||
|
||||
@@ -59,7 +54,7 @@ describe('agent/prompt-submit', () => {
|
||||
it('allow (default via next) records the user/message unchanged', async () => {
|
||||
const adapter = new MockAdapter([textResponse('ok')])
|
||||
const ctx = await harness(adapter)
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
|
||||
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
const seen: string[] = []
|
||||
ctx.on('agent/prompt-submit', async (_agent, content, _source, next) => {
|
||||
@@ -78,7 +73,7 @@ describe('agent/prompt-submit', () => {
|
||||
it('allow with content REWRITES the prompt before it is recorded', async () => {
|
||||
const adapter = new MockAdapter([textResponse('ok')])
|
||||
const ctx = await harness(adapter)
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
|
||||
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
ctx.on('agent/prompt-submit', async (): Promise<PromptDecision> =>
|
||||
({ kind: 'allow', content: [{ type: 'text', text: 'REWRITTEN' }] }))
|
||||
@@ -96,7 +91,7 @@ describe('agent/prompt-submit', () => {
|
||||
it('allow with additionalContexts injects separate context/message events into the turn', async () => {
|
||||
const adapter = new MockAdapter([textResponse('ok')])
|
||||
const ctx = await harness(adapter)
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
|
||||
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
const meta = { kind: 'prompt-context', version: 1 }
|
||||
ctx.on('agent/prompt-submit', async (): Promise<PromptDecision> =>
|
||||
@@ -131,7 +126,7 @@ describe('agent/prompt-submit', () => {
|
||||
// compaction listener measures the current surface before the single derive.
|
||||
const adapter = new MockAdapter([textResponse('ok')])
|
||||
const ctx = await harness(adapter)
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
|
||||
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
ctx.on('agent/prompt-submit', async (): Promise<PromptDecision> =>
|
||||
({
|
||||
@@ -161,7 +156,7 @@ describe('agent/prompt-submit', () => {
|
||||
it('block drops the (only) prompt → zero-step turn ends rejected, model never called', async () => {
|
||||
const adapter = new MockAdapter([textResponse('should not run')])
|
||||
const ctx = await harness(adapter)
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
|
||||
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
ctx.on('agent/prompt-submit', async (): Promise<PromptDecision> =>
|
||||
({ kind: 'block', reason: 'blocked by policy' }))
|
||||
@@ -197,7 +192,7 @@ describe('agent/prompt-submit', () => {
|
||||
// the allowed prompt keeps the turn from ending rejected.
|
||||
const adapter = new MockAdapter([textResponse('ran once')])
|
||||
const ctx = await harness(adapter)
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
|
||||
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
ctx.on('agent/prompt-submit', async (_agent, content, _source, next): Promise<PromptDecision> => {
|
||||
const text = content.map(b => (b.type === 'text' ? b.text : '')).join('')
|
||||
@@ -233,7 +228,7 @@ describe('agent/prompt-submit', () => {
|
||||
it('a throwing prompt-submit listener ends the turn balanced (error), loop survives', async () => {
|
||||
const adapter = new MockAdapter([textResponse('after')])
|
||||
const ctx = await harness(adapter)
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
|
||||
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
let threw = false
|
||||
ctx.on('agent/prompt-submit', async () => {
|
||||
@@ -266,7 +261,7 @@ describe('agent/session-start', () => {
|
||||
const sources: SessionStartSource[] = []
|
||||
ctx.on('agent/session-start', (_agent, source) => void sources.push(source))
|
||||
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
|
||||
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
|
||||
// fires synchronously at create, before any turn
|
||||
expect(sources).toEqual(['startup'])
|
||||
expect(events(agent).some(e => e.type === 'turn/start')).toBe(false)
|
||||
@@ -285,7 +280,7 @@ describe('agent/session-start', () => {
|
||||
agent.inject([{ type: 'text', text: 'session preamble' }], { source: { kind: 'plugin', plugin: 'test' } })
|
||||
})
|
||||
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
|
||||
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
|
||||
send(agent, 'go')
|
||||
await waitForIdle(ctx, agent)
|
||||
|
||||
@@ -303,8 +298,8 @@ describe('agent/session-start', () => {
|
||||
ctx.on('agent/session-start', () => { throw new Error('session-start hook broke') })
|
||||
|
||||
// create must not throw — the listener error is contained/logged
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
|
||||
expect(agent.id).toBe(AgentId('a1'))
|
||||
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
|
||||
expect(agent.id).toBe(SessionId('a1'))
|
||||
|
||||
// and the agent still runs
|
||||
send(agent, 'go')
|
||||
@@ -317,8 +312,8 @@ describe('agent/session-prefix', () => {
|
||||
it('dispatches to global and matching agent-scope listeners only', async () => {
|
||||
const adapter = new MockAdapter([textResponse('a done'), textResponse('b done')])
|
||||
const ctx = await harness(adapter)
|
||||
const agentA = ctx.agentLoop.create(AgentId('prefix-a'), { provider: 'mock', model: 'mock' })
|
||||
const agentB = ctx.agentLoop.create(AgentId('prefix-b'), { provider: 'mock', model: 'mock' })
|
||||
const agentA = ctx.agentLoop.create(SessionId('prefix-a'), { provider: 'mock', model: 'mock' })
|
||||
const agentB = ctx.agentLoop.create(SessionId('prefix-b'), { provider: 'mock', model: 'mock' })
|
||||
const seen: string[] = []
|
||||
ctx.on('agent/session-prefix', async (agent, _prefix, _signal, next) => {
|
||||
seen.push(`global:${agent.id}`)
|
||||
@@ -355,7 +350,7 @@ describe('agent/session-prefix', () => {
|
||||
name: 'echo', description: 'echo', parameters: { text: { type: 'string' } },
|
||||
async execute(args) { return [{ type: 'text', text: String(args.text) }] },
|
||||
}))
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
|
||||
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
const reminder: Message = { role: 'user', content: [{ type: 'text', text: '<system-reminder>catalog</system-reminder>' }] }
|
||||
let composed = 0
|
||||
@@ -388,7 +383,7 @@ describe('agent/session-prefix', () => {
|
||||
it('composes before the first pre-step and hands the prefix to the seam (pressure gates see the real value)', async () => {
|
||||
const adapter = new MockAdapter([textResponse('ok')])
|
||||
const ctx = await harness(adapter)
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
|
||||
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
const reminder: Message = { role: 'user', content: [{ type: 'text', text: 'opener' }] }
|
||||
const order: string[] = []
|
||||
@@ -415,7 +410,7 @@ describe('agent/session-prefix', () => {
|
||||
it('the canonical prepend pattern composes contributions in registration order', async () => {
|
||||
const adapter = new MockAdapter([textResponse('ok')])
|
||||
const ctx = await harness(adapter)
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
|
||||
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
// Both listeners use the canonical `[mine, ...await next()]` prepend: the
|
||||
// waterfall unwinds innermost-first (the second listener's array is built
|
||||
@@ -437,7 +432,7 @@ describe('agent/session-prefix', () => {
|
||||
it('with no contributions the header omits messagePrefix and the request is the bare derivation', async () => {
|
||||
const adapter = new MockAdapter([textResponse('ok')])
|
||||
const ctx = await harness(adapter)
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
|
||||
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
// A listener that delegates without contributing — the canonical no-op.
|
||||
ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next) => next())
|
||||
@@ -453,7 +448,7 @@ describe('agent/session-prefix', () => {
|
||||
it('the frozen seed rejects in-place mutation — a contribution is a returned extension', async () => {
|
||||
const adapter = new MockAdapter([textResponse('ok')])
|
||||
const ctx = await harness(adapter)
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
|
||||
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
let mutationError: unknown
|
||||
ctx.on('agent/session-prefix', async (_agent, prefix, _signal, next): Promise<Message[]> => {
|
||||
@@ -482,7 +477,7 @@ describe('agent/session-prefix', () => {
|
||||
name: 'echo', description: 'echo', parameters: { text: { type: 'string' } },
|
||||
async execute(args) { return [{ type: 'text', text: String(args.text) }] },
|
||||
}))
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
|
||||
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
const held: Message = { role: 'user', content: [{ type: 'text', text: 'v1' }] }
|
||||
ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next): Promise<Message[]> => [...await next(), held])
|
||||
@@ -503,7 +498,7 @@ describe('agent/turn-continuation (ContinuationDecision)', () => {
|
||||
it('a continue decision with a reason records next-step steering in the same turn', async () => {
|
||||
const adapter = new MockAdapter([textResponse('step 1 no tools'), textResponse('step 2')])
|
||||
const ctx = await harness(adapter)
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
|
||||
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
let forced = false
|
||||
ctx.on('agent/turn-continuation', async (_agent, _turn, _default, next): Promise<ContinuationDecision> => {
|
||||
@@ -535,7 +530,7 @@ describe('agent/turn-continuation (ContinuationDecision)', () => {
|
||||
name: 'echo', description: 'echo', parameters: { text: { type: 'string' } },
|
||||
async execute(args) { return [{ type: 'text', text: String(args.text) }] },
|
||||
}))
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
|
||||
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
ctx.on('agent/turn-continuation', async (): Promise<ContinuationDecision> => ({ action: 'stop' }))
|
||||
|
||||
@@ -565,7 +560,7 @@ describe('tool additionalContexts buffering across a step', () => {
|
||||
name: 'echo', description: 'echo', parameters: { text: { type: 'string' } },
|
||||
async execute(args) { return [{ type: 'text', text: String(args.text) }] },
|
||||
}))
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
|
||||
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
// Each call attaches one context naming itself.
|
||||
ctx.on('tools/post-execute', async (exec, _result): Promise<PostToolDecision> =>
|
||||
@@ -613,7 +608,7 @@ describe('tool additionalContexts buffering across a step', () => {
|
||||
return [{ type: 'text', text: 'outer result' }]
|
||||
},
|
||||
}))
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
|
||||
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
send(agent, 'go')
|
||||
await waitForIdle(ctx, agent)
|
||||
@@ -640,7 +635,7 @@ describe('tools/pre-execute gate (native-plugin permission pattern, end-to-end t
|
||||
name: 'danger', description: 'danger', parameters: {},
|
||||
async execute() { ran = true; return [{ type: 'text', text: 'should not run' }] },
|
||||
}))
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
|
||||
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
ctx.on('tools/pre-execute', async (exec, next): Promise<PreToolDecision> => {
|
||||
if (exec.name === 'danger') return { kind: 'deny', reason: 'blocked dangerous tool' }
|
||||
@@ -702,7 +697,7 @@ describe('worked example: a native hook plugin is just a cordis plugin on the se
|
||||
name: 'echo', description: 'echo', parameters: { text: { type: 'string' } },
|
||||
async execute(args) { return [{ type: 'text', text: String(args.text) }] },
|
||||
}))
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
|
||||
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
send(agent, 'please echo hi')
|
||||
await waitForIdle(ctx, agent)
|
||||
@@ -725,7 +720,7 @@ describe('worked example: a native hook plugin is just a cordis plugin on the se
|
||||
const adapter = new MockAdapter([textResponse('should not run')])
|
||||
const ctx = await harness(adapter)
|
||||
await ctx.plugin(NativeGuard)
|
||||
const agent = ctx.agentLoop.create(AgentId('a2'), { provider: 'mock', model: 'mock' })
|
||||
const agent = ctx.agentLoop.create(SessionId('a2'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
const reasons: TurnEndReason[] = []
|
||||
ctx.on('session/event', (_s, event: SessionEvent) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
|
||||
@@ -744,7 +739,7 @@ describe('worked example: a native hook plugin is just a cordis plugin on the se
|
||||
await fiber.dispose()
|
||||
|
||||
// After disposal, a destructive prompt is NOT blocked (the listener is gone).
|
||||
const agent = ctx.agentLoop.create(AgentId('a3'), { provider: 'mock', model: 'mock' })
|
||||
const agent = ctx.agentLoop.create(SessionId('a3'), { provider: 'mock', model: 'mock' })
|
||||
send(agent, 'run rm -rf /')
|
||||
await waitForIdle(ctx, agent)
|
||||
// the prompt ran (not rejected) — proving the prompt-submit listener was disposed
|
||||
|
||||
Reference in New Issue
Block a user