Merge remote-tracking branch 'origin/master' into codex/skill-system

packages/core/agent-loop/tests/cancel.spec.ts

@@ -12,7 +12,7 @@
 
 import { describe, expect, it } from 'vitest'
 import { Context } from 'cordis'
-import LlmService from '@deepseek-ai/dsh-llm'
+import LlmService, { type Message } from '@deepseek-ai/dsh-llm'
 import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session'
 import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
 import ToolRegistry from '@deepseek-ai/dsh-tools'
@@ -166,6 +166,103 @@ describe('Agent.cancel()', () => {
     expect(reasons.length).toBe(2)
   })
 
+  it('cancel from inside the agent/session-prefix waterfall drops the step (prefix-composition window)', async () => {
+    const adapter = new MockAdapter([textResponse('should not stream')])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+
+    // Prefix composition runs before the pre-step seam on the instance's first
+    // step; a cancel landing inside it must drop the about-to-start step
+    // without running the seam or the model.
+    let streamed = false
+    ctx.on('session/event', (_s, event) => { if (event.type === 'assistant/chunk') streamed = true })
+    ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next) => {
+      agent.cancel('from prefix composition')
+      return next()
+    })
+
+    const reasons: TurnEndReason[] = []
+    ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
+
+    send(agent, 'go')
+    await waitForIdle(ctx, agent)
+
+    expect(streamed).toBe(false)
+    expect(reasons).toEqual([{ kind: 'aborted', reason: 'from prefix composition' }])
+  })
+
+  it('disposal from inside the agent/session-prefix waterfall ends the turn disposed (prefix-composition window)', 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-prefix'),
+      sessionId: SessionId('dispose-prefix-session'),
+      agentOptions: { model: 'mock' },
+    })
+    const agent = handle.agent as ReactLoopAgent
+
+    let disposalDone: Promise<void> | undefined
+    let streamed = false
+    ctx.on('session/event', (_s, event) => { if (event.type === 'assistant/chunk') streamed = true })
+    ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next) => {
+      disposalDone = handle.dispose()
+      return next()
+    })
+
+    send(agent, 'go')
+    await new Promise(resolve => setTimeout(resolve, 0))
+    await disposalDone
+    await agent.done
+
+    // No step opened, no model call ran, and the turn closed disposed.
+    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' })
+  })
+
+  it('a cancel-interrupted prefix composition is discarded: the next send recomposes and ships the fresh prefix (stale-cache guard)', async () => {
+    const adapter = new MockAdapter([textResponse('reply')])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+
+    // The first composition is interrupted mid-waterfall and — like an
+    // abort-aware listener bailing on a firing signal — contributes nothing.
+    // Caching that degraded result would silently strip the prefix from every
+    // later request of this instance; the loop must discard it and recompose
+    // on the next send, and the SECOND composition's value must be what the
+    // wire and the header log carry.
+    const opener: Message = { role: 'user', content: [{ type: 'text', text: 'fresh opener' }] }
+    let compositions = 0
+    ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next): Promise<Message[]> => {
+      compositions += 1
+      if (compositions === 1) {
+        agent.cancel('mid-composition')
+        return next()
+      }
+      return [opener, ...await next()]
+    })
+
+    send(agent, 'dropped')
+    await waitForIdle(ctx, agent)
+    send(agent, 'real prompt')
+    await waitForIdle(ctx, agent)
+
+    expect(compositions).toBe(2)
+    expect(adapter.requests).toHaveLength(1)
+    expect(adapter.requests[0]?.messages[0]).toEqual(opener)
+    const headerEvent = agent.session.events.find(e => e.type === 'request/header')
+    expect(headerEvent?.type === 'request/header' && headerEvent.data.header.messagePrefix).toEqual([opener])
+  })
+
   it('cancel from a synchronous turn/start session-event listener drops the step (step-start window)', async () => {
     const adapter = new MockAdapter([textResponse('should not stream')])
     const ctx = await harness(adapter)

packages/core/agent-loop/tests/interception.spec.ts

@@ -1,6 +1,6 @@
 import { describe, expect, it } from 'vitest'
 import { Context } from 'cordis'
-import LlmService, { CallId } from '@deepseek-ai/dsh-llm'
+import LlmService, { CallId, type Message } from '@deepseek-ai/dsh-llm'
 import SessionStore, { 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'
@@ -310,6 +310,162 @@ describe('agent/session-start', () => {
   })
 })
 
+describe('agent/session-prefix', () => {
+  it('composes once per loop instance and fronts every request; the header records it; history stays untouched', async () => {
+    const adapter = new MockAdapter([
+      toolCallResponse('c1', 'echo', { text: 'ping' }),
+      textResponse('done'),
+      textResponse('again'),
+    ])
+    const ctx = await harness(adapter)
+    ctx.tools.register(defineTool({
+      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'), { model: 'mock' })
+
+    const reminder: Message = { role: 'user', content: [{ type: 'text', text: '<system-reminder>catalog</system-reminder>' }] }
+    let composed = 0
+    ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next): Promise<Message[]> => {
+      composed += 1
+      return [...await next(), reminder]
+    })
+
+    send(agent, 'go')
+    await waitForIdle(ctx, agent)
+    send(agent, 'next turn')
+    await waitForIdle(ctx, agent)
+
+    // Three requests (two turns), ONE composition: the frozen product is
+    // reused verbatim, so the prefix cannot drift mid-session.
+    expect(adapter.requests).toHaveLength(3)
+    expect(composed).toBe(1)
+    for (const request of adapter.requests) {
+      expect(request.messages[0]).toEqual(reminder)
+    }
+    // The anchoring snapshot is the prefix's durable record — and the ONLY
+    // header event: reuse means no request/header-delta ever.
+    const headerEvents = events(agent).filter(e => e.type === 'request/header' || e.type === 'request/header-delta')
+    expect(headerEvents).toHaveLength(1)
+    expect(headerEvents[0]?.type === 'request/header' && headerEvents[0].data.header.messagePrefix).toEqual([reminder])
+    // Never session history: the derivation starts at the real user prompt.
+    expect(agent.session.deriveMessages()[0]).toEqual({ role: 'user', content: [{ type: 'text', text: 'go' }] })
+  })
+
+  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'), { model: 'mock' })
+
+    const reminder: Message = { role: 'user', content: [{ type: 'text', text: 'opener' }] }
+    const order: string[] = []
+    ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next): Promise<Message[]> => {
+      order.push('compose')
+      return [reminder, ...await next()]
+    })
+    const seen: (readonly Message[])[] = []
+    ctx.on('agent/pre-step', (_agent, _turn, _step, _system, sessionPrefix) => {
+      order.push('pre-step')
+      seen.push(sessionPrefix)
+    })
+
+    send(agent, 'hi')
+    await waitForIdle(ctx, agent)
+
+    // Composition precedes the pre-step seam, and the seam receives THIS
+    // instance's composed prefix — a token-pressure gate (compaction) counts
+    // what the request will actually carry, never a stale logged prefix.
+    expect(order).toEqual(['compose', 'pre-step'])
+    expect(seen[0]).toEqual([reminder])
+  })
+
+  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'), { model: 'mock' })
+
+    // Both listeners use the canonical `[mine, ...await next()]` prepend: the
+    // waterfall unwinds innermost-first (the second listener's array is built
+    // first), so prepending puts the FIRST-registered contribution first.
+    ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next): Promise<Message[]> => {
+      return [{ role: 'user', content: [{ type: 'text', text: 'first' }] }, ...await next()]
+    })
+    ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next): Promise<Message[]> => {
+      return [{ role: 'user', content: [{ type: 'text', text: 'second' }] }, ...await next()]
+    })
+
+    send(agent, 'hi')
+    await waitForIdle(ctx, agent)
+
+    const texts = adapter.requests[0]!.messages.map(m => m.content[0]?.type === 'text' ? m.content[0].text : '')
+    expect(texts).toEqual(['first', 'second', 'hi'])
+  })
+
+  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'), { model: 'mock' })
+
+    // A listener that delegates without contributing — the canonical no-op.
+    ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next) => next())
+
+    send(agent, 'hi')
+    await waitForIdle(ctx, agent)
+
+    const headerEvent = events(agent).find(e => e.type === 'request/header')
+    expect(headerEvent?.type === 'request/header' && 'messagePrefix' in headerEvent.data.header).toBe(false)
+    expect(adapter.requests[0]!.messages).toEqual([{ role: 'user', content: [{ type: 'text', text: 'hi' }] }])
+  })
+
+  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'), { model: 'mock' })
+
+    let mutationError: unknown
+    ctx.on('agent/session-prefix', async (_agent, prefix, _signal, next): Promise<Message[]> => {
+      try {
+        prefix.push({ role: 'user', content: [{ type: 'text', text: 'smuggled' }] })
+      } catch (error: unknown) {
+        mutationError = error
+      }
+      return next()
+    })
+
+    send(agent, 'hi')
+    await waitForIdle(ctx, agent)
+
+    expect(mutationError).toBeInstanceOf(TypeError)
+    expect(adapter.requests[0]!.messages).toEqual([{ role: 'user', content: [{ type: 'text', text: 'hi' }] }])
+  })
+
+  it('mutating a listener-held reference after composition cannot alter later requests (the cache is a frozen clone)', async () => {
+    const adapter = new MockAdapter([
+      toolCallResponse('c1', 'echo', { text: 'ping' }),
+      textResponse('done'),
+    ])
+    const ctx = await harness(adapter)
+    ctx.tools.register(defineTool({
+      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'), { 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])
+
+    send(agent, 'go')
+    await waitForIdle(ctx, agent)
+
+    // The listener mutates the object it contributed AFTER composition; the
+    // cached prefix is a deep-frozen clone, so step 2's request is unchanged.
+    held.content = [{ type: 'text', text: 'v2' }]
+    expect(adapter.requests[1]!.messages[0]).toEqual({ role: 'user', content: [{ type: 'text', text: 'v1' }] })
+    expect(events(agent).filter(e => e.type === 'request/header-delta')).toHaveLength(0)
+  })
+})
+
+
 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')])

packages/core/agent-loop/tests/tool-order.spec.ts

@@ -0,0 +1,117 @@
+/**
+ * Loop-level tool-order determinism: the request/header event — and therefore
+ * the frozen request the adapter receives — carries the assembly's canonical
+ * tool order (system-prompt's `toolOrder` config, or lexicographic name
+ * order), regardless of the order tool plugins happened to register in.
+ * Registration order is a plugin-load artifact (concurrent dynamic imports
+ * race), so nothing downstream of the registry may depend on it.
+ */
+
+import { describe, expect, it } from 'vitest'
+import { Context } from 'cordis'
+import LlmService from '@deepseek-ai/dsh-llm'
+import SessionStore, { foldRequestHeader } from '@deepseek-ai/dsh-session'
+import SystemPrompt, { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt'
+import type { Config as SystemPromptConfig } from '@deepseek-ai/dsh-system-prompt'
+import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
+import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
+import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
+import { MockAdapter, textResponse } from './mock-adapter.ts'
+
+async function harness(adapter: MockAdapter, toolOrder?: SystemPromptConfig['toolOrder']) {
+  const ctx = new Context()
+  await ctx.plugin(LlmService)
+  await ctx.plugin(SessionStore)
+  await ctx.plugin(SystemPrompt, { persona: 'stable base', ...toolOrder !== undefined ? { toolOrder } : {} })
+  await ctx.plugin(ToolRegistry)
+  await ctx.plugin(AgentRegistry)
+  await ctx.plugin(AgentLoop, { agents: [] })
+  ctx.llm.registerAdapter(['mock'], adapter)
+  return ctx
+}
+
+function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
+  return new Promise((resolve) => {
+    const dispose = ctx.on('agent/status', (subject, status) => {
+      if (subject === agent && status === 'idle') {
+        dispose()
+        resolve()
+      }
+    })
+  })
+}
+
+function registerNamed(ctx: Context, name: string) {
+  ctx.tools.register(defineTool({
+    name,
+    description: `the ${name} tool`,
+    parameters: {},
+    async execute() {
+      return [{ type: 'text', text: name }]
+    },
+  }))
+}
+
+/** Run one text-only turn and return the harness context + agent. */
+async function runTurn(registrationOrder: string[], toolOrder?: SystemPromptConfig['toolOrder']) {
+  const adapter = new MockAdapter([textResponse('done')])
+  const ctx = await harness(adapter, toolOrder)
+  for (const name of registrationOrder) registerNamed(ctx, name)
+  const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+  agent.send([{ type: 'text', text: 'go' }])
+  await waitForIdle(ctx, agent)
+  return { ctx, agent, adapter }
+}
+
+describe('loop-level canonical tool order', () => {
+  it('logs the request/header with tools in canonical order, not registration order', async () => {
+    const { agent, adapter } = await runTurn(['zulu', 'alpha', 'mike'])
+    const header = foldRequestHeader(agent.session.events)
+    expect(header?.tools?.map(tool => tool.name)).toEqual(['alpha', 'mike', 'zulu'])
+    // The dispatched request is built FROM the logged header (whose tools the
+    // assembly already canonicalized) and reaches the adapter deep-frozen —
+    // the marker the reconstruction invariant keys on.
+    expect(adapter.requests[0]?.tools?.map(tool => tool.name)).toEqual(['alpha', 'mike', 'zulu'])
+    expect(Object.isFrozen(adapter.requests[0])).toBe(true)
+    expect(adapter.requests[0]?.sessionId).toBe(agent.session.id)
+  })
+
+  it('produces the same header order for any registration order', async () => {
+    const first = await runTurn(['alpha', 'mike', 'zulu'])
+    const second = await runTurn(['zulu', 'mike', 'alpha'])
+    const names = (run: typeof first) => foldRequestHeader(run.agent.session.events)?.tools?.map(tool => tool.name)
+    expect(names(first)).toEqual(['alpha', 'mike', 'zulu'])
+    expect(names(second)).toEqual(names(first))
+  })
+
+  it('honors a configured toolOrder in the logged header and the dispatched request', async () => {
+    const { agent, adapter } = await runTurn(['alpha', 'zulu', 'mike'], ['zulu', TOOL_ORDER_REST])
+    const header = foldRequestHeader(agent.session.events)
+    expect(header?.tools?.map(tool => tool.name)).toEqual(['zulu', 'alpha', 'mike'])
+    expect(adapter.requests[0]?.tools?.map(tool => tool.name)).toEqual(['zulu', 'alpha', 'mike'])
+    expect(Object.isFrozen(adapter.requests[0])).toBe(true)
+  })
+
+  it('fails the turn — no model request — when toolOrder names an unregistered tool', async () => {
+    // The assemble rejection escapes to runTurn's outer catch: the open turn
+    // closes with an `error` reason (agent/error mirrors it), no step opens,
+    // no request/header is logged, the adapter never sees a request, and the
+    // agent returns to idle — a misconfigured deployment fails every turn
+    // deterministically instead of silently reordering nothing.
+    const adapter = new MockAdapter([textResponse('never sent')])
+    const ctx = await harness(adapter, ['ghost', TOOL_ORDER_REST])
+    registerNamed(ctx, 'alpha')
+    const errors: Error[] = []
+    ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+    expect(adapter.requests).toHaveLength(0)
+    expect(errors.map(e => e.message)).toEqual(['toolOrder lists unregistered tool "ghost"; registered tools: alpha'])
+    expect(foldRequestHeader(agent.session.events)).toBeUndefined()
+    const end = agent.session.events.find(e => e.type === 'turn/end')
+    expect(end?.type === 'turn/end' && end.data.reason).toMatchObject({ kind: 'error', step: 1 })
+    // The turn is balanced (turn/start → turn/end) with no step events inside.
+    expect(agent.session.events.some(e => e.type === 'step/start')).toBe(false)
+  })
+})