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

Merge origin/master into skill system branch

Browse Source 
Use the new filesystem seam for skill file reads and system skill writes when ctx.fs is available, and include the skill tool in the generated tool catalog.
This commit is contained in:
Yichen Jiang
2026-07-03 12:26:58 +08:00
parent cce3c2a43b d8ea99756d
commit 5870bc2e1a
138 changed files with 11548 additions and 248 deletions
Download Patch File Download Diff File Expand all files Collapse all files

69
packages/core/agent-loop/tests/cancel.spec.ts
View File

@@ -13,7 +13,7 @@
import { describe, expect, it } from 'vitest'
import { Context } from 'cordis'
import LlmService from '@deepseek-ai/dsh-llm'
import SessionStore, { TurnEndReason } from '@deepseek-ai/dsh-session'
import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry from '@deepseek-ai/dsh-tools'
import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
@@ -194,6 +194,73 @@ describe('Agent.cancel()', () => {
expect(reasons).toEqual([{ kind: 'aborted', reason: 'from turn-start' }])
})
it('cancel from a synchronous agent/step-start listener drops the step (post-step-start window)', async () => {
const adapter = new MockAdapter([textResponse('should not stream')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
// A step-start listener fires AFTER step/start is appended (and after the
// pre-step seam), so cancelling there lands in the SECOND cancel check (the
// one that must closeStep() to balance the already-open step) — distinct
// from a turn-start cancel, which is caught before the step opens.
let streamed = false
ctx.on('agent/stream-chunk', () => { streamed = true })
const dispose = ctx.on('agent/step-start', (subject) => {
if (subject === agent) agent.cancel('from step-start')
})
const reasons: TurnEndReason[] = []
ctx.on('agent/turn-end', (_a, _t, reason) => void reasons.push(reason))
send(agent, 'go')
await waitForIdle(ctx, agent)
dispose()
// No step streamed, the turn ended aborted with the caller's reason, and the
// log is balanced (the open step was closed by the cancel branch).
expect(streamed).toBe(false)
expect(reasons).toEqual([{ kind: 'aborted', reason: 'from step-start' }])
const types = agent.session.events.map(e => e.type)
expect(types.filter(t => t === 'step/start').length).toBe(types.filter(t => t === 'step/end').length)
})
it('disposal from a synchronous agent/step-start listener closes the open step as disposed', async () => {
const adapter = new MockAdapter([textResponse('should not stream')])
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
const handle = ctx.agents.create({
agentId: AgentId('a-dispose-step-start'),
sessionId: SessionId('dispose-step-start-session'),
agentOptions: { model: 'mock' },
})
const agent = handle.agent as ReactLoopAgent
let disposalDone: Promise<void> | undefined
let streamed = false
ctx.on('agent/stream-chunk', () => { streamed = true })
ctx.on('agent/step-start', (subject) => {
if (subject === agent) disposalDone = handle.dispose()
})
send(agent, 'go')
await disposalDone
await agent.done
expect(streamed).toBe(false)
expect(adapter.requests).toHaveLength(0)
const turnEnd = agent.session.events.findLast(e => e.type === 'turn/end')
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toEqual({ kind: 'disposed' })
const types = agent.session.events.map(e => e.type)
expect(types.filter(t => t === 'step/start').length).toBe(types.filter(t => t === 'step/end').length)
})
it('cancel during the continuation window ends the turn aborted and runs no further step', async () => {
// A continuation-waterfall listener cancels DURING the continuation decision
// (the finished step's AbortController is already cleared), and votes to

104
packages/core/agent-loop/tests/loop.spec.ts
View File

@@ -320,6 +320,110 @@ describe('agent loop', () => {
expect(adapter.requests[0]!.model).toBe('other-model')
})
it('agent/pre-step fires once per step before the step is opened', async () => {
// Two steps (a tool call, then a final text turn) → two model calls → two
// pre-step fires, each carrying the assembled full system prompt, BEFORE
// the step is opened and its request is derived (the request the adapter
// sees reflects any surface state at fire time).
const adapter = new MockAdapter([
toolCallResponse('c1', 'echo', {}, 'calling echo'),
textResponse('done'),
])
const ctx = await harness(adapter)
ctx.tools.register(defineTool({
name: 'echo', description: 'echo', parameters: {},
async execute() { return [{ type: 'text', text: 'echoed' }] },
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
const fires: { turn: number; step: number; fullSystemPrompt: string }[] = []
ctx.on('agent/pre-step', (subject, turn, step, fullSystemPrompt) => {
if (subject === agent) fires.push({ turn, step, fullSystemPrompt })
})
send(agent, 'go')
await waitForIdle(ctx, agent)
// One fire per step, in order, each with the assembled system prompt.
expect(fires).toEqual([
{ turn: 1, step: 1, fullSystemPrompt: '' },
{ turn: 1, step: 2, fullSystemPrompt: '' },
])
})
it('agent/pre-step fires BEFORE the step it precedes opens (events land outside the step)', async () => {
// A listener appending a surface node in pre-step lands it BEFORE step/start
// in the log — proving the seam fires outside the step. The node is still in
// the derived request for that step (derive happens after step/start).
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
let injected = false
ctx.on('agent/pre-step', (subject) => {
if (subject === agent && !injected) {
injected = true
subject.session.append('context/message', {
content: [{ type: 'text', text: 'INJECTED-IN-PRE-STEP' }],
source: { kind: 'plugin', plugin: 'test' },
}, { surfaceOp: 'append' })
}
})
send(agent, 'go')
await waitForIdle(ctx, agent)
// The adapter's request includes the node injected during pre-step (derive
// reflects it).
const text = JSON.stringify(adapter.requests[0]!.messages)
expect(text).toContain('INJECTED-IN-PRE-STEP')
// And the injected event sits BEFORE the first step/start in the log —
// the seam fired outside the step.
const events = agent.session.events
const injectedSeq = events.find(e => e.type === 'context/message')!.seq
const firstStepStartSeq = events.find(e => e.type === 'step/start')!.seq
expect(injectedSeq).toBeLessThan(firstStepStartSeq)
})
it('a throwing agent/pre-step listener ends the turn (error), not the loop', async () => {
// The seam fires before step/start, so a throw escapes to runTurn's outer
// catch: the not-yet-open step closes as a no-op, the failure surfaces via
// agent/error, and the turn ends `error` (recorded on the durable turn/end).
// The loop survives and a follow-up prompt still runs.
const adapter = new MockAdapter([textResponse('second turn ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
let throwOnce = true
ctx.on('agent/pre-step', () => {
if (throwOnce) { throwOnce = false; throw new Error('boom in pre-step') }
})
const errors: Error[] = []
ctx.on('agent/error', (_a, _t, _s, error) => void errors.push(error))
send(agent, 'first')
await waitForIdle(ctx, agent)
// The first turn failed at step 1 (no model call happened), surfaced via
// agent/error, with the durable failure on turn/end.reason.
expect(errors).toHaveLength(1)
expect(errors[0]!.message).toContain('boom in pre-step')
expect(adapter.requests.length).toBe(0)
const firstTurnEnd = agent.session.events.find(e => e.type === 'turn/end')
expect(firstTurnEnd?.type === 'turn/end' && firstTurnEnd.data.reason).toMatchObject({ kind: 'error', step: 1 })
// The step opened-and-closed count stays balanced even though it never ran.
const types = agent.session.events.map(e => e.type)
expect(types.filter(t => t === 'step/start').length).toBe(types.filter(t => t === 'step/end').length)
// The loop survived: a second prompt runs a normal completed turn.
send(agent, 'second')
await waitForIdle(ctx, agent)
expect(adapter.requests.length).toBe(1)
const lastTurnEnd = agent.session.events.findLast(e => e.type === 'turn/end')
expect(lastTurnEnd?.type === 'turn/end' && lastTurnEnd.data.reason).toEqual({ kind: 'completed' })
})
it('cancel() mid-stream ends the turn with reason aborted', async () => {
const adapter = new MockAdapter(['hang'])
const ctx = await harness(adapter)

272
packages/core/agent-loop/tests/review-fixes.spec.ts
View File

@@ -1047,3 +1047,275 @@ describe('surface: assistant/message omits sourceEventSeqs when no chunks stream
expect(JSON.stringify(agent.session.deriveMessages())).toContain('injected')
})
})
describe('disposal/cancel honored during pre-step assembly (P1-1)', () => {
it('disposal during system-prompt assembly drops the about-to-start step as disposed', { timeout: 30000 }, async () => {
// Block `system-prompt/assemble` on a promise. Start disposal (which
// calls stop() synchronously, setting status=disposed), then release the
// block. The loop must check isDisposed() after assembly and end the turn
// `disposed` — no LLM call. Don't await fiber.dispose() before releasing
// the blocker: the dispose chain awaits agent.done, which hangs until the
// loop unblocks.
const adapter = new MockAdapter(['hang'])
let releaseAssemble!: () => void
const blocked = new Promise<void>(r => void (releaseAssemble = r))
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(Invariants, { freeze: false })
ctx.llm.registerAdapter(['mock'], adapter)
// Blocking listener on the parent context (survives fiber disposal).
const unlisten = ctx.on('system-prompt/assemble', async function (_assembly, next) {
await blocked
return next()
})
let agent!: ReactLoopAgent
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
agent = inner.agentLoop.create(AgentId('a-dispose-assemble'), { model: 'mock' })
}, { inject: ['agentLoop'] }))
const reasons: TurnEndReason[] = []
ctx.on('agent/turn-end', (_a, _t, reason) => void reasons.push(reason))
send(agent, 'go')
// Give the loop time to enter the step and reach assemble().
await new Promise(r => setTimeout(r, 50))
// Start disposal — stop() sets status=disposed synchronously, then the
// disposer's await agent.done hangs because the loop is blocked in the
// waterfall. Do NOT await yet; release the blocker first.
const disposalDone = fiber.dispose()
// Now release the blocked waterfall — the loop unblocks, checks
// isDisposed(), and exits, which resolves agent.done and disposalDone.
releaseAssemble()
await disposalDone
await agent.done
unlisten()
const e = [...agent.session.events]
expect(e.filter(x => x.type === 'turn/start')).toHaveLength(1)
expect(e.filter(x => x.type === 'turn/end')).toHaveLength(1)
const turnEnd = e.findLast(x => x.type === 'turn/end')
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toEqual({ kind: 'disposed' })
// No step was opened, no LLM call was made.
expect(e.some(x => x.type === 'step/start')).toBe(false)
expect(e.some(x => x.type === 'assistant/chunk')).toBe(false)
// agent/turn-end may not fire when disposal happens during assembly: the
// fiber's disposer (stop→status=disposed) runs before closeTurn(true)'s
// emit, and the LIFO chain disposes effects in reverse registration order.
// The turn/end durable record is the one that matters.
})
it('cancel during system-prompt assembly drops the about-to-start step as aborted', { timeout: 30000 }, async () => {
const adapter = new MockAdapter([textResponse('should not appear')])
let releaseAssemble!: () => void
const blocker = new Promise<void>(r => void (releaseAssemble = r))
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(Invariants, { freeze: false })
ctx.llm.registerAdapter(['mock'], adapter)
const unlisten = ctx.on('system-prompt/assemble', async function (_assembly, next) {
await blocker
return next()
})
let agent!: ReactLoopAgent
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
agent = inner.agentLoop.create(AgentId('a-cancel-assemble'), { model: 'mock' })
}, { inject: ['agentLoop'] }))
const reasons: TurnEndReason[] = []
ctx.on('agent/turn-end', (_a, _t, reason) => void reasons.push(reason))
send(agent, 'go')
await new Promise(r => setTimeout(r, 50))
agent.cancel('user cancelled during assembly')
releaseAssemble()
await waitForIdle(ctx, agent)
await fiber.dispose()
await agent.done
unlisten()
const e = [...agent.session.events]
expect(e.filter(x => x.type === 'turn/start')).toHaveLength(1)
expect(e.filter(x => x.type === 'turn/end')).toHaveLength(1)
const turnEnd = e.findLast(x => x.type === 'turn/end')
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toEqual({
kind: 'aborted',
reason: 'user cancelled during assembly',
})
expect(e.some(x => x.type === 'step/start')).toBe(false)
expect(e.some(x => x.type === 'assistant/chunk')).toBe(false)
expect(e.some(x => x.type === 'assistant/message')).toBe(false)
expect(adapter.requests).toHaveLength(0)
expect(reasons).toEqual([{ kind: 'aborted', reason: 'user cancelled during assembly' }])
})
it('disposal during agent/pre-step seam ends the turn disposed', { timeout: 15000 }, async () => {
// Block the `agent/pre-step` serial seam on a promise we control, then
// dispose the agent's fiber. When the block releases, the loop must see
// isDisposed() at the post-seam check and end the turn disposed.
const adapter = new MockAdapter(['hang'])
let releasePreStep!: () => void
const blocker = new Promise<void>(r => void (releasePreStep = r))
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(Invariants, { freeze: false })
ctx.llm.registerAdapter(['mock'], adapter)
ctx.on('agent/pre-step', async () => {
await blocker
})
let agent!: ReactLoopAgent
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
agent = inner.agentLoop.create(AgentId('a-dispose-prestep'), { model: 'mock' })
}, { inject: ['agentLoop'] }))
const reasons: TurnEndReason[] = []
ctx.on('agent/turn-end', (_a, _t, reason) => void reasons.push(reason))
send(agent, 'go')
await new Promise(r => setTimeout(r, 50))
// Start disposal, then release the block, then await disposal.
const disposalDone = fiber.dispose()
releasePreStep()
await disposalDone
await agent.done
// After the pre-step seam finishes, the post-seam cancel/dispose check
// catches disposal. The step was never opened, no LLM call was made.
const e = [...agent.session.events]
expect(e.filter(x => x.type === 'turn/start')).toHaveLength(1)
expect(e.filter(x => x.type === 'turn/end')).toHaveLength(1)
const turnEnd = e.findLast(x => x.type === 'turn/end')
// Disposal wins the post-seam check — reason is `disposed`.
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toEqual({ kind: 'disposed' })
expect(e.some(x => x.type === 'step/start')).toBe(false)
expect(e.some(x => x.type === 'assistant/chunk')).toBe(false)
// agent/turn-end may not fire when disposal happens during pre-step: the
// fiber's disposer runs before closeTurn(true)'s emit. The durable turn/end
// is the authoritative record.
})
it('cancel during agent/pre-step seam ends the turn aborted', { timeout: 15000 }, async () => {
// Block `agent/pre-step`, then cancel() the agent. When the block releases,
// the post-seam check catches cancellation and ends the turn aborted.
const adapter = new MockAdapter(['hang'])
let releasePreStep!: () => void
const blocker = new Promise<void>(r => void (releasePreStep = r))
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(Invariants, { freeze: false })
ctx.llm.registerAdapter(['mock'], adapter)
ctx.on('agent/pre-step', async () => {
await blocker
})
let agent!: ReactLoopAgent
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
agent = inner.agentLoop.create(AgentId('a-cancel-prestep'), { model: 'mock' })
}, { inject: ['agentLoop'] }))
const reasons: TurnEndReason[] = []
ctx.on('agent/turn-end', (_a, _t, reason) => void reasons.push(reason))
send(agent, 'go')
await new Promise(r => setTimeout(r, 30))
agent.cancel('user cancelled')
releasePreStep()
await waitForIdle(ctx, agent)
await fiber.dispose()
await agent.done
const e = [...agent.session.events]
expect(e.filter(x => x.type === 'turn/start')).toHaveLength(1)
expect(e.filter(x => x.type === 'turn/end')).toHaveLength(1)
const turnEnd = e.findLast(x => x.type === 'turn/end')
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toEqual({ kind: 'aborted', reason: 'user cancelled' })
expect(e.some(x => x.type === 'step/start')).toBe(false)
expect(e.some(x => x.type === 'assistant/chunk')).toBe(false)
expect(reasons).toEqual([{ kind: 'aborted', reason: 'user cancelled' }])
})
it('disposal during assembly does not leak an LLM call or append assistant/chunk', { timeout: 15000 }, async () => {
// The key assertion from the original bug report: after disposal, no
// assistant/chunk or assistant/message appears — the turn ends disposed
// before any model interaction.
const adapter = new MockAdapter([textResponse('should not appear')])
let releaseAssemble!: () => void
const blocker = new Promise<void>(r => void (releaseAssemble = r))
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(Invariants, { freeze: false })
ctx.llm.registerAdapter(['mock'], adapter)
ctx.on('system-prompt/assemble', async function (_assembly, next) {
await blocker
return next()
})
let agent!: ReactLoopAgent
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
agent = inner.agentLoop.create(AgentId('a-dispose-no-leak'), { model: 'mock' })
}, { inject: ['agentLoop'] }))
send(agent, 'go')
await new Promise(r => setTimeout(r, 50))
const disposalDone = fiber.dispose()
releaseAssemble()
await disposalDone
await agent.done
const e = [...agent.session.events]
expect(e.filter(x => x.type === 'turn/start')).toHaveLength(1)
expect(e.filter(x => x.type === 'turn/end')).toHaveLength(1)
// The critical assertions: after disposal, the turn has no assistant
// artifacts — the turn ended disposed before the model was invoked.
expect(e.some(x => x.type === 'assistant/chunk')).toBe(false)
expect(e.some(x => x.type === 'assistant/message')).toBe(false)
expect(adapter.requests).toHaveLength(0)
// The durable turn/end reason is the authoritative record; agent/turn-end
// may not fire when disposal interleaves with closeTurn(true)'s emit.
})
})