Pine/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases 1 Wiki Activity

Merge origin/master into skill system branch

Browse Source 
Resolve documentation split, tool presentation, and generated catalog changes from master while preserving the skill system integration.
This commit is contained in:
Yichen Jiang
2026-07-05 16:50:29 +08:00
parent 5870bc2e1a 57fd914f95
commit 83dfc3887e
454 changed files with 29524 additions and 4598 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/core/agent-loop/tests/loop.spec.ts
+59 -29
View File
@@ -46,15 +46,20 @@ describe('agent loop', () => {
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
// All boundaries — turn and step — are durable session events on the
// session/event feed (no agent/* mirror). Record them in fire order to
// assert the full boundary nesting.
const order: string[] = []
for (const name of ['agent/turn-start', 'agent/step-start', 'agent/step-end', 'agent/turn-end'] as const) {
ctx.on(name, () => void order.push(name))
}
ctx.on('session/event', (_session, event) => {
if (event.type === 'turn/start' || event.type === 'step/start' || event.type === 'step/end' || event.type === 'turn/end') {
order.push(event.type)
}
})
send(agent, 'hi')
await waitForIdle(ctx, agent)
expect(order).toEqual(['agent/turn-start', 'agent/step-start', 'agent/step-end', 'agent/turn-end'])
expect(order).toEqual(['turn/start', 'step/start', 'step/end', 'turn/end'])
const types = agent.session.events.map(e => e.type)
// turn/start opens the turn, THEN the queued user message is recorded inside
@@ -110,6 +115,32 @@ describe('agent loop', () => {
expect(types).toContain('tool/result')
})
it('threads a tool-attached meta (execute object return) onto the tool/result event', async () => {
const adapter = new MockAdapter([
toolCallResponse('c1', 'writer', { path: 'a.txt' }, 'writing'),
textResponse('done'),
])
const ctx = await harness(adapter)
// A tool that returns the { content, meta } object form: the loop must
// persist `meta` on the tool/result event so a UI reproduces the card on replay.
ctx.tools.register(defineTool({
name: 'writer',
description: 'writes a file',
parameters: { path: { type: 'string' } },
async execute() {
return { content: [{ type: 'text', text: 'ok' }], meta: { diffs: [{ path: 'a.txt', oldText: null, newText: 'x' }] } }
},
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
send(agent, 'use the tool')
await waitForIdle(ctx, agent)
const toolResult = agent.session.events.find(e => e.type === 'tool/result')
expect(toolResult?.type === 'tool/result' && toolResult.data.meta)
.toEqual({ diffs: [{ path: 'a.txt', oldText: null, newText: 'x' }] })
})
it('passes assembled system prompt and tool schemas into the request', async () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
@@ -132,21 +163,17 @@ describe('agent loop', () => {
expect(request!.tools?.map(t => t.name)).toEqual(['noop'])
})
it('records raw chunks for replay and emits agent/stream-chunk', async () => {
it('records raw chunks for replay as assistant/chunk session events', async () => {
const adapter = new MockAdapter([textResponse('abc')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
const streamed: StreamChunk[] = []
ctx.on('agent/stream-chunk', (_agent, _turn, _step, chunk) => void streamed.push(chunk))
send(agent, 'hi')
await waitForIdle(ctx, agent)
const chunkEvents = agent.session.events.filter(e => e.type === 'assistant/chunk')
// textResponse('abc') = block-start + 3 deltas + block-end + usage + finish = 7
expect(chunkEvents).toHaveLength(7)
expect(streamed).toHaveLength(7)
// replay: chunk events alone re-assemble to the recorded assistant message
const deltaText = chunkEvents
.flatMap(e => e.type === 'assistant/chunk' ? [e.data.chunk] : [])
@@ -269,9 +296,9 @@ describe('agent loop', () => {
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
let steps = 0
ctx.on('agent/step-end', () => void steps++)
ctx.on('session/event', (_session, event) => { if (event.type === 'step/end') steps++ })
ctx.on('agent/turn-continuation', async (_agent, _turn, _defaultDecision, next) => {
if (steps < 3) return true
if (steps < 3) return { action: 'continue' as const }
return next()
})
@@ -294,7 +321,7 @@ describe('agent loop', () => {
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
ctx.on('agent/turn-continuation', async () => false as const)
ctx.on('agent/turn-continuation', async () => ({ action: 'stop' }) as const)
send(agent, 'go')
await waitForIdle(ctx, agent)
@@ -430,7 +457,7 @@ describe('agent loop', () => {
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
const reasons: TurnEndReason[] = []
ctx.on('agent/turn-end', (_agent, _turn, reason) => void reasons.push(reason))
ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
send(agent, 'go')
// wait until the stream is hanging, then cancel
@@ -450,7 +477,7 @@ describe('agent loop', () => {
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
const reasons: TurnEndReason[] = []
ctx.on('agent/turn-end', (_agent, _turn, reason) => void reasons.push(reason))
ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
send(agent, 'go')
await waitForIdle(ctx, agent)
@@ -475,16 +502,16 @@ describe('agent loop', () => {
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
let steps = 0
ctx.on('agent/step-end', () => void steps++)
ctx.on('session/event', (_session, event) => { if (event.type === 'step/end') steps++ })
// Force exactly one continuation (step 1 → step 2), then defer to default
// (step 2 is a plain stop with no tool calls → stops).
ctx.on('agent/turn-continuation', async (_agent, _turn, _defaultDecision, next) => {
if (steps < 2) return true
if (steps < 2) return { action: 'continue' as const }
return next()
})
const reasons: TurnEndReason[] = []
ctx.on('agent/turn-end', (_agent, _turn, reason) => void reasons.push(reason))
ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
send(agent, 'go')
await waitForIdle(ctx, agent)
@@ -506,7 +533,7 @@ describe('agent loop', () => {
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
const reasons: TurnEndReason[] = []
ctx.on('agent/turn-end', (_agent, _turn, reason) => void reasons.push(reason))
ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
send(agent, 'first')
await waitForIdle(ctx, agent)
@@ -539,7 +566,7 @@ describe('agent loop', () => {
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
const reasons: TurnEndReason[] = []
ctx.on('agent/turn-end', (_agent, _turn, reason) => void reasons.push(reason))
ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
send(agent, 'go')
await waitForIdle(ctx, agent)
@@ -581,7 +608,7 @@ describe('agent loop', () => {
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
const reasons: TurnEndReason[] = []
ctx.on('agent/turn-end', (_agent, _turn, reason) => void reasons.push(reason))
ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
send(agent, 'go')
await waitForIdle(ctx, agent)
@@ -600,7 +627,7 @@ describe('agent loop', () => {
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
const reasons: TurnEndReason[] = []
ctx.on('agent/turn-end', (_agent, _turn, reason) => void reasons.push(reason))
ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
send(agent, 'go')
await waitForIdle(ctx, agent)
@@ -640,7 +667,7 @@ describe('agent loop', () => {
])
})
it('stops the turn when agent/step-end listener failure has recorded an error', async () => {
it('stops the turn when a step/end session-event listener failure has recorded an error', async () => {
const adapter = new MockAdapter([
toolCallResponse('c1', 'echo', { text: 'x' }),
textResponse('should not run'),
@@ -656,8 +683,11 @@ describe('agent loop', () => {
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
let threw = false
ctx.on('agent/step-end', () => {
if (!threw) { threw = true; throw new Error('bad step-end listener') }
// A throwing step/end session-event listener is the surviving boundary-listener
// failure path (step boundaries have no agent/* mirror): closeStep contains it
// and surfaces it as a turn error rather than stranding the turn open.
ctx.on('session/event', (_session, event) => {
if (event.type === 'step/end' && !threw) { threw = true; throw new Error('bad step/end listener') }
})
send(agent, 'go')
@@ -674,13 +704,13 @@ describe('agent loop', () => {
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
const turns: number[] = []
ctx.on('agent/turn-start', (_agent, turn) => void turns.push(turn))
ctx.on('session/event', (_s, event) => { if (event.type === 'turn/start') turns.push(event.data.turn) })
// queue two messages while idle — first starts turn 1 immediately;
// queue the second during turn 1 via a stream-chunk hook
// queue the second during turn 1 when the first assistant chunk streams
let queued = false
ctx.on('agent/stream-chunk', () => {
if (!queued) {
ctx.on('session/event', (_s, event) => {
if (event.type === 'assistant/chunk' && !queued) {
queued = true
send(agent, 'second message')
}
@@ -721,7 +751,7 @@ describe('agent loop', () => {
const errors: Error[] = []
const reasons: TurnEndReason[] = []
ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error))
ctx.on('agent/turn-end', (_agent, _turn, reason) => void reasons.push(reason))
ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
send(agent, 'hi')
await waitForIdle(ctx, agent)