Merge origin/master into codex/send-one-turn

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

@@ -0,0 +1,335 @@
+import { describe, expect, it } from 'vitest'
+import { Context, type Fiber } from 'cordis'
+import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
+import AgentLoop from '@deepseek-ai/dsh-agent-loop'
+import LlmService, { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm'
+import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm'
+import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
+import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
+import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
+import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts'
+
+interface Harness {
+  ctx: Context
+  agentsFiber: Fiber
+  loopFiber: Fiber
+}
+
+async function harness(adapter: LlmAdapter): Promise<Harness> {
+  const ctx = new Context()
+  await ctx.plugin(LlmService)
+  await ctx.plugin(SessionStore)
+  await ctx.plugin(SystemPrompt)
+  await ctx.plugin(ToolRegistry)
+  const agentsFiber = await ctx.plugin(AgentRegistry)
+  const loopFiber = await ctx.plugin(AgentLoop, { agents: [] })
+  ctx.llm.registerAdapter(['mock'], adapter)
+  return { ctx, agentsFiber, loopFiber }
+}
+
+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') {
+        dispose()
+        resolve()
+      }
+    })
+  })
+}
+
+function send(agent: Agent, text: string): void {
+  agent.send([{ type: 'text', text }])
+}
+
+/** Adapter that holds both drivers at the same awaited continuation. */
+class OverlapAdapter extends LlmAdapter {
+  private readonly bothStarted = Promise.withResolvers<boolean>()
+  private starts = 0
+  readonly observations: { sessionId: SessionId | undefined; before: Agent; after: Agent }[] = []
+
+  constructor(private readonly ctx: Context) {
+    super()
+  }
+
+  async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
+    const before = this.ctx.agents.requireInitiator()
+    this.starts += 1
+    if (this.starts === 2) this.bothStarted.resolve(true)
+    await this.bothStarted.promise
+    await Promise.resolve()
+    const after = this.ctx.agents.requireInitiator()
+    this.observations.push({ sessionId: options.sessionId, before, after })
+    yield* textResponse('done')
+  }
+}
+
+/** Test-only transport that materializes ambient identity at its request boundary. */
+class TestCapabilityTransport {
+  readonly requests: { path: string; headers: Record<string, string> }[] = []
+
+  constructor(private readonly agents: AgentRegistry) {}
+
+  async request(path: string): Promise<Record<string, string>> {
+    await Promise.resolve()
+    const headers = {
+      'X-Harness-Session-Id': this.agents.requireInitiator().session.id,
+    }
+    this.requests.push({ path, headers })
+    return headers
+  }
+}
+
+/** Adapter whose first call waits for cancellation and whose later calls complete. */
+class ReloadAdapter extends LlmAdapter {
+  readonly firstStarted = Promise.withResolvers<boolean>()
+  firstAgentDuringAbort: Agent | undefined
+  laterAgent: Agent | undefined
+  calls = 0
+  agents: AgentRegistry | undefined
+
+  async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
+    const agents = this.agents
+    if (agents === undefined) throw new Error('agent service missing')
+    this.calls += 1
+    if (this.calls === 1) {
+      this.firstStarted.resolve(true)
+      try {
+        await new Promise<void>((_resolve, reject) => {
+          const abort = (): void => { reject(new Error('aborted')) }
+          if (options.signal?.aborted === true) abort()
+          else options.signal?.addEventListener('abort', abort, { once: true })
+        })
+      } catch (error: unknown) {
+        await Promise.resolve()
+        this.firstAgentDuringAbort = agents.requireInitiator()
+        throw error
+      }
+      return
+    }
+    await Promise.resolve()
+    this.laterAgent = agents.requireInitiator()
+    yield* textResponse('reloaded')
+  }
+}
+
+describe('AgentLoop initiator scope', () => {
+  it('keeps overlapping driver continuations bound to their exact Agents', async () => {
+    const ctx = new Context()
+    const adapter = new OverlapAdapter(ctx)
+    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 a = ctx.agentLoop.create(SessionId('a'), { provider: 'mock', model: 'mock' })
+    const b = ctx.agentLoop.create(SessionId('b'), { provider: 'mock', model: 'mock' })
+    const idleA = waitForIdle(ctx, a)
+    const idleB = waitForIdle(ctx, b)
+    send(a, 'a')
+    send(b, 'b')
+    await Promise.all([idleA, idleB])
+
+    expect(adapter.observations).toHaveLength(2)
+    expect(adapter.observations).toEqual(expect.arrayContaining([
+      { sessionId: a.session.id, before: a, after: a },
+      { sessionId: b.session.id, before: b, after: b },
+    ]))
+    expect(ctx.agents.currentInitiator()).toBeUndefined()
+    await ctx.fiber.dispose()
+  })
+
+  it('keeps child setup under the parent boundary and restores the parent while the child driver remains active', async () => {
+    const adapter = new MockAdapter([
+      toolCallResponse('spawn', 'spawn-child', {}),
+      toolCallResponse('observe', 'observe-child', {}),
+      textResponse('child done'),
+      textResponse('parent done'),
+    ])
+    const { ctx } = await harness(adapter)
+    let parentDuringSetup: Agent | undefined
+    let explicitChild: Agent | undefined
+    let childDuringDriver: Agent | undefined
+    let parentWhileChildDriverActive: Agent | undefined
+    let child: Agent | undefined
+
+    ctx.tools.register(defineTool({
+      name: 'spawn-child',
+      description: 'create one child agent',
+      parameters: {},
+      execute: async (_args, exec) => {
+        if (exec.agent === undefined) throw new Error('parent agent missing')
+        const handle = await exec.agent.ctx.agents.create({
+          sessionId: SessionId('child-session'),
+          agentOptions: { provider: 'mock', model: 'mock' },
+          setup: (agentCtx) => {
+            parentDuringSetup = ctx.agents.requireInitiator()
+            explicitChild = agentCtx.agent
+            agentCtx.tools.register(defineTool({
+              name: 'observe-child',
+              description: 'observe child execution identity',
+              parameters: {},
+              execute: async () => {
+                await Promise.resolve()
+                childDuringDriver = ctx.agents.requireInitiator()
+                return [{ type: 'text', text: 'observed' }]
+              },
+            }))
+          },
+        })
+        child = handle.agent
+        parentWhileChildDriverActive = ctx.agents.requireInitiator()
+        send(handle.agent, 'run child')
+        await handle.agent.whenIdle()
+        await handle.dispose()
+        return [{ type: 'text', text: 'child completed' }]
+      },
+    }))
+
+    const parentHandle = await ctx.agents.create({
+      sessionId: SessionId('parent-session'),
+      agentOptions: { provider: 'mock', model: 'mock' },
+    })
+    const idle = waitForIdle(ctx, parentHandle.agent)
+    send(parentHandle.agent, 'spawn')
+    await idle
+
+    expect(parentDuringSetup).toBe(parentHandle.agent)
+    expect(explicitChild).toBe(child)
+    expect(childDuringDriver).toBe(child)
+    expect(parentWhileChildDriverActive).toBe(parentHandle.agent)
+    expect(ctx.agents.currentInitiator()).toBeUndefined()
+    await parentHandle.dispose()
+    await ctx.fiber.dispose()
+  })
+
+  it('keeps agentless direct tools ambient-free and builds trusted transport headers internally', async () => {
+    const adapter = new MockAdapter([
+      toolCallResponse('capability', 'capability-request', { path: '/v1/capability' }),
+      textResponse('done'),
+    ])
+    const { ctx } = await harness(adapter)
+    const transport = new TestCapabilityTransport(ctx.agents)
+    let directAmbient: Agent | undefined
+    let captured: Agent | undefined
+
+    ctx.tools.register(defineTool({
+      name: 'agentless-probe',
+      description: 'observe an agentless call',
+      parameters: {},
+      execute: async () => {
+        await Promise.resolve()
+        directAmbient = ctx.agents.currentInitiator()
+        return [{ type: 'text', text: 'ok' }]
+      },
+    }))
+    ctx.tools.register(defineTool({
+      name: 'capability-request',
+      description: 'call the test capability transport',
+      parameters: { path: { type: 'string' } },
+      execute: async (args) => {
+        captured = ctx.agents.requireInitiator()
+        const path = (args as { path: string }).path
+        const headers = await transport.request(path)
+        return [{ type: 'text', text: JSON.stringify(headers) }]
+      },
+    }))
+
+    const direct = await ctx.tools.execute({
+      callId: CallId('direct'),
+      name: 'agentless-probe',
+      arguments: {},
+    })
+    expect(direct.isError).toBe(false)
+    expect(directAmbient).toBeUndefined()
+
+    const handle = await ctx.agents.create({
+      sessionId: SessionId('transport-session'),
+      agentOptions: { provider: 'mock', model: 'mock' },
+    })
+    const idle = waitForIdle(ctx, handle.agent)
+    send(handle.agent, 'call transport')
+    await idle
+
+    expect(transport.requests).toEqual([{
+      path: '/v1/capability',
+      headers: { 'X-Harness-Session-Id': 'transport-session' },
+    }])
+    const schema = adapter.requests[0]?.tools?.find(tool => tool.name === 'capability-request')
+    expect(JSON.stringify(schema?.parameters)).not.toMatch(/session|harness/i)
+    const call = handle.agent.session.events.find(event => event.type === 'tool/call')
+    expect(call?.type === 'tool/call' ? call.data.arguments : undefined)
+      .toBe(JSON.stringify({ path: '/v1/capability' }))
+    expect(captured).toBe(handle.agent)
+
+    await handle.dispose()
+    expect(captured?.status).toBe('disposed')
+    expect(ctx.agents.currentInitiator()).toBeUndefined()
+    await ctx.fiber.dispose()
+  })
+
+  it('drains the old driver before disabling ALS during agent-service restart', async () => {
+    const adapter = new ReloadAdapter()
+    const { ctx, agentsFiber, loopFiber } = await harness(adapter)
+    const oldService = ctx.agents
+    adapter.agents = oldService
+    const oldHandle = await ctx.agents.create({
+      sessionId: SessionId('before-restart-session'),
+      agentOptions: { provider: 'mock', model: 'mock' },
+    })
+    const oldAgent = oldHandle.agent
+    send(oldAgent, 'block')
+    await adapter.firstStarted.promise
+
+    await agentsFiber.restart()
+    await loopFiber.await()
+    expect(adapter.firstAgentDuringAbort?.id).toBe(oldAgent.id)
+    expect(adapter.firstAgentDuringAbort?.session).toBe(oldAgent.session)
+    expect(oldAgent.status).toBe('disposed')
+    expect(() => oldService.currentInitiator()).toThrow('agent initiator scope is disposed')
+    expect(ctx.agents).not.toBe(oldService)
+    adapter.agents = ctx.agents
+
+    const newHandle = await ctx.agents.create({
+      sessionId: SessionId('after-restart-session'),
+      agentOptions: { provider: 'mock', model: 'mock' },
+    })
+    const newAgent = newHandle.agent
+    const idle = waitForIdle(ctx, newAgent)
+    send(newAgent, 'continue')
+    await idle
+    expect(adapter.laterAgent?.id).toBe(newAgent.id)
+    expect(adapter.laterAgent?.session).toBe(newAgent.session)
+    await ctx.fiber.dispose()
+  })
+
+  it('keeps ALS readable while root disposal drains sibling AgentLoop fibers', async () => {
+    const ctx = new Context()
+    const adapter = new ReloadAdapter()
+    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 service = ctx.agents
+    adapter.agents = service
+    const handle = await ctx.agents.create({
+      sessionId: SessionId('root-dispose-session'),
+      agentOptions: { provider: 'mock', model: 'mock' },
+    })
+    const agent = handle.agent
+    send(agent, 'block')
+    await adapter.firstStarted.promise
+
+    await ctx.fiber.dispose()
+    expect(adapter.firstAgentDuringAbort?.id).toBe(agent.id)
+    expect(adapter.firstAgentDuringAbort?.session).toBe(agent.session)
+    expect(agent.status).toBe('disposed')
+    expect(() => service.currentInitiator()).toThrow('agent initiator scope is disposed')
+  })
+})

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

@@ -1,15 +1,18 @@
 import { describe, expect, it, vi } from 'vitest'
 import { Context } from 'cordis'
-import { AgentId } from '@deepseek-ai/dsh-agent'
 import LlmService from '@deepseek-ai/dsh-llm'
 import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
 import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
 import ToolRegistry from '@deepseek-ai/dsh-tools'
-import AgentRegistry from '@deepseek-ai/dsh-agent'
-import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
-import { bindReactLoopAgentContext, prepareReactLoopAgent } from '../src/agent.ts'
+import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
+import AgentLoop, { DEFAULT_MAX_PARALLEL_TOOL_CALLS } from '@deepseek-ai/dsh-agent-loop'
+import { bindReactLoopAgentContext, prepareReactLoopAgent, type ReactLoopAgent } from '../src/agent.ts'
 import { MockAdapter, textResponse } from './mock-adapter.ts'
 
+function driverDone(agent: Agent): Promise<void> {
+  return (agent as Agent & { done: Promise<void> }).done
+}
+
 async function harness(adapter: MockAdapter) {
   const ctx = new Context()
   await ctx.plugin(LlmService)
@@ -22,7 +25,7 @@ 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') {
@@ -33,7 +36,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
   })
 }
 
-function waitForStatus(ctx: Context, agent: ReactLoopAgent, expected: ReactLoopAgent['status']): Promise<void> {
+function waitForStatus(ctx: Context, agent: Agent, expected: Agent['status']): Promise<void> {
   return new Promise((resolve) => {
     const dispose = ctx.on('agent/status', (subject, status) => {
       if (subject === agent && status === expected) {
@@ -44,19 +47,23 @@ function waitForStatus(ctx: Context, agent: ReactLoopAgent, expected: ReactLoopA
   })
 }
 
-function send(agent: ReactLoopAgent, text: string) {
+function send(agent: Agent, text: string) {
   agent.send([{ type: 'text', text }])
 }
 
-describe('ReactLoopAgent', () => {
+describe('Agent', () => {
   it('rejects access before context binding and a second driver for one session', async () => {
     const ctx = new Context()
     await ctx.plugin(SessionStore)
     const session = ctx.sessions.create(SessionId('exclusive-driver'))
-    const prepared = prepareReactLoopAgent(ctx, AgentId('first-driver'), { model: 'mock' }, session)
+    const prepared = prepareReactLoopAgent(
+      ctx, SessionId('first-driver'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
+    )
 
     expect(() => prepared.agent.ctx).toThrow('context is not bound')
-    expect(() => prepareReactLoopAgent(ctx, AgentId('second-driver'), { model: 'mock' }, session))
+    expect(() => prepareReactLoopAgent(
+      ctx, SessionId('second-driver'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
+    ))
       .toThrow('already has a concrete agent driver')
 
     await prepared.dispose()
@@ -65,13 +72,13 @@ describe('ReactLoopAgent', () => {
 
   it('borrows caller options and binds its scoped context exactly once', async () => {
     const ctx = await harness(new MockAdapter([textResponse('unused')]))
-    const options = { model: 'mock' }
-    const agent = ctx.agentLoop.create(AgentId('owned-bindings'), options)
+    const options = { provider: 'mock', model: 'mock' }
+    const agent = ctx.agentLoop.create(SessionId('owned-bindings'), options)
 
     expect(agent.options).toBe(options)
     expect(agent.id).toBe('owned-bindings')
-    expect(agent.session.id).toMatch(/^owned-bindings-session-/)
-    expect(() => { bindReactLoopAgentContext(agent, new Context()) }).toThrow(/context is already bound/)
+    expect(agent.session.id).toBe(agent.id)
+    expect(() => { bindReactLoopAgentContext(agent as ReactLoopAgent, new Context()) }).toThrow(/context is already bound/)
 
     await ctx.fiber.dispose()
   })
@@ -79,14 +86,14 @@ describe('ReactLoopAgent', () => {
   it('send() throws after disposal', async () => {
     const adapter = new MockAdapter(['hang'])
     const ctx = await harness(adapter)
-    let agent!: ReactLoopAgent
+    let agent!: Agent
     const fiber = await ctx.plugin(Object.assign((inner: Context) => {
-      agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' })
+      agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', model: 'mock' })
     }, { inject: ['agentLoop'] }))
     send(agent, 'go')
     await new Promise(r => setTimeout(r, 30))
     await fiber.dispose()
-    await agent.done
+    await driverDone(agent)
 
     expect(() => { agent.send([{ type: 'text', text: 'too late' }]) }).toThrow('disposed')
   })
@@ -94,14 +101,14 @@ describe('ReactLoopAgent', () => {
   it('steer() throws after disposal', async () => {
     const adapter = new MockAdapter(['hang'])
     const ctx = await harness(adapter)
-    let agent!: ReactLoopAgent
+    let agent!: Agent
     const fiber = await ctx.plugin(Object.assign((inner: Context) => {
-      agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' })
+      agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', model: 'mock' })
     }, { inject: ['agentLoop'] }))
     send(agent, 'go')
     await new Promise(r => setTimeout(r, 30))
     await fiber.dispose()
-    await agent.done
+    await driverDone(agent)
 
     expect(() => { agent.steer([{ type: 'text', text: 'too late' }]) }).toThrow('disposed')
   })
@@ -109,14 +116,14 @@ describe('ReactLoopAgent', () => {
   it('inject() throws after disposal', async () => {
     const adapter = new MockAdapter(['hang'])
     const ctx = await harness(adapter)
-    let agent!: ReactLoopAgent
+    let agent!: Agent
     const fiber = await ctx.plugin(Object.assign((inner: Context) => {
-      agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' })
+      agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', model: 'mock' })
     }, { inject: ['agentLoop'] }))
     send(agent, 'go')
     await new Promise(r => setTimeout(r, 30))
     await fiber.dispose()
-    await agent.done
+    await driverDone(agent)
 
     expect(() => { agent.inject([{ type: 'text', text: 'too late' }]) }).toThrow('disposed')
   })
@@ -124,7 +131,7 @@ describe('ReactLoopAgent', () => {
   it('inject() decides enclosure from the LOG (open turn), not agent status', async () => {
     const adapter = new MockAdapter([textResponse('ok')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     // Simulate an OPEN turn in the log while the agent is idle (status is not a
     // reliable open-turn signal). inject must append into that open turn, NOT
@@ -150,7 +157,7 @@ describe('ReactLoopAgent', () => {
     // A persistence-like listener whose flush rejects.
     ctx.on('session/flush', () => { throw new Error('disk gone') })
     const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     // inject() is synchronous and fires a fire-and-forget flush; a rejecting
     // flush must be contained (logged), never thrown into the caller.
@@ -163,12 +170,14 @@ describe('ReactLoopAgent', () => {
   it('idle inject() closes its one-shot turn AND still checkpoints even if the append throws', async () => {
     const adapter = new MockAdapter([textResponse('ok')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
     let flushes = 0
     ctx.on('session/flush', () => { flushes += 1 })
 
-    // Invalid injected content throws after turn/start. `finally` must still append turn/end and
-    // flush the balanced in-memory turn so a crash cannot lose it before the next checkpoint.
+    // Non-serializable injected content makes Session.append throw AFTER
+    // turn/start was recorded. The turn/end must still be appended (finally),
+    // AND the durability checkpoint must still fire — the balanced turn is in
+    // memory and a crash before the next turn/dispose would otherwise lose it.
     expect(() => {
       agent.inject([{ type: 'text', text: 'x', bad: 1n } as never], { source: { kind: 'plugin', plugin: 'p' } })
     }).toThrow(/non-JSON-serializable/)
@@ -181,7 +190,7 @@ describe('ReactLoopAgent', () => {
   it('idle inject() still checkpoints when a listener throws on the synthetic turn/end', async () => {
     const adapter = new MockAdapter([textResponse('ok')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
     let flushes = 0
     ctx.on('session/flush', () => { flushes += 1 })
     // Session contains a throwing post-commit turn/end observer. The accepted
@@ -204,7 +213,7 @@ describe('ReactLoopAgent', () => {
     // A non-Error rejection exercises the String() normalization branch.
     ctx.on('session/flush', () => { throw 'disk gone' })
     const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
     const errors: { turn: number; step: number; message: string }[] = []
     ctx.on('agent/error', (_a, turn, step, error) => void errors.push({ turn, step, message: error.message }))
 
@@ -223,7 +232,7 @@ describe('ReactLoopAgent', () => {
   it('idle inject() with a non-serializable source opens no turn (nothing to close)', async () => {
     const adapter = new MockAdapter([textResponse('ok')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     // A non-serializable source makes the turn/start append throw BEFORE the
     // event is pushed (Session.append validates before push), so NO turn opens.
@@ -238,7 +247,7 @@ describe('ReactLoopAgent', () => {
   it('steer() when idle falls through to send() and starts a turn', async () => {
     const adapter = new MockAdapter([textResponse('ok')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     // steer while idle delegates to send
     agent.steer([{ type: 'text', text: 'steer idle' }], { source: { kind: 'plugin', plugin: 'test' } })
@@ -250,20 +259,29 @@ describe('ReactLoopAgent', () => {
   })
 
   it('disposer is idempotent (double-stop)', async () => {
-    // The internal start seam exposes one idle driver's disposer for repeated invocation.
+    // Create a bare Agent and start it through the package-internal
+    // test seam. Then call its disposer twice — the second call hits the
+    // early-return branch.
     const ctx = new Context()
     await ctx.plugin(SessionStore)
+    await ctx.plugin(AgentRegistry)
     const session = ctx.sessions.create(SessionId('test'))
-    const prepared = prepareReactLoopAgent(ctx, AgentId('bare'), { model: 'mock' }, session)
+    const prepared = prepareReactLoopAgent(
+      ctx, SessionId('bare'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
+    )
     const { agent } = prepared
 
+    // Start the loop to get the disposer; the agent waits for messages
+    // (idle, never-resolving cancel), so it will stay idle.
     prepared.markPublished()
     const dispose = prepared.startDriver()
 
+    // First dispose
     const firstDisposal = dispose()
     expect(agent.status).toBe('disposed')
     await firstDisposal
 
+    // Second dispose — idempotent, no throw
     await expect(dispose()).resolves.toBeUndefined()
     expect(agent.status).toBe('disposed')
   })
@@ -272,7 +290,9 @@ describe('ReactLoopAgent', () => {
     const ctx = new Context()
     await ctx.plugin(SessionStore)
     const session = ctx.sessions.create(SessionId('pre-start-dispose'))
-    const prepared = prepareReactLoopAgent(ctx, AgentId('pre-start-dispose'), { model: 'mock' }, session)
+    const prepared = prepareReactLoopAgent(
+      ctx, SessionId('pre-start-dispose'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
+    )
 
     await prepared.dispose()
     expect(prepared.agent.status).toBe('disposed')
@@ -286,7 +306,7 @@ describe('ReactLoopAgent', () => {
   it('setting the same status does not emit agent/status again', async () => {
     const adapter = new MockAdapter([textResponse('ok')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     const statuses: string[] = []
     ctx.on('agent/status', (subject, status) => {
@@ -305,7 +325,7 @@ describe('ReactLoopAgent', () => {
   it('whenIdle() resolves immediately when the agent is not running', async () => {
     const adapter = new MockAdapter([textResponse('ok')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     // Fresh agent is idle — whenIdle() takes the not-running fast path and
     // resolves without subscribing. await must not hang.
@@ -316,7 +336,7 @@ describe('ReactLoopAgent', () => {
   it('whenIdle() waits for queued work that has not flipped status yet', async () => {
     const adapter = new MockAdapter(['hang'])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     send(agent, 'queued')
     let settled = false
@@ -334,8 +354,8 @@ describe('ReactLoopAgent', () => {
   it('whenIdle() awaits the running→idle transition, ignoring other subjects/running events', async () => {
     const adapter = new MockAdapter([textResponse('ok'), textResponse('ok')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
-    const other = ctx.agentLoop.create(AgentId('a2'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
+    const other = ctx.agentLoop.create(SessionId('a2'), { provider: 'mock', model: 'mock' })
 
     // Drive `agent` into `running`, then await whenIdle() — it subscribes to
     // agent/status and resolves on the first transition out of running.
@@ -358,8 +378,10 @@ describe('ReactLoopAgent', () => {
   })
 
   it('whenIdle() subscribed while running resolves via done when the agent is then disposed', async () => {
-    // Queue the internal waiter while running, then dispose the bare driver. Its disposed branch
-    // must chain the loop's `done` promise rather than resolve before exit.
+    // Covers the waiter's disposed arm: whenIdle() queues an internal waiter
+    // while running (not the fast path), then the disposer settles it and chains
+    // `done` (loop exit), not an eager resolve. A bare Agent + direct
+    // internal driver disposer keeps the emit synchronous.
     const ctx = new Context()
     await ctx.plugin(LlmService)
     await ctx.plugin(SessionStore)
@@ -369,7 +391,9 @@ describe('ReactLoopAgent', () => {
     const adapter = new MockAdapter(['hang'])
     ctx.llm.registerAdapter(['mock'], adapter)
     const session = ctx.sessions.create(SessionId('bare'))
-    const prepared = prepareReactLoopAgent(ctx, AgentId('bare'), { model: 'mock' }, session)
+    const prepared = prepareReactLoopAgent(
+      ctx, SessionId('bare'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
+    )
     const { agent } = prepared
     prepared.markPublished()
     const dispose = prepared.startDriver()
@@ -385,13 +409,15 @@ describe('ReactLoopAgent', () => {
   })
 
   it('whenIdle() subscribed while running survives a FIBER dispose (no hung promise)', async () => {
-    // The waiter is agent-owned state, not an effect-scoped listener that owner disposal would
-    // remove before the disposed transition. Fiber teardown must still settle it.
+    // The waiter is internal agent state, NOT an effect-scoped ctx.on listener:
+    // disposing the OWNING fiber runs the agent's listener disposers, which would
+    // have dropped a ctx.on-based waiter before the 'disposed' transition and
+    // hung the promise. With internal waiters, the fiber disposer still settles it.
     const adapter = new MockAdapter(['hang'])
     const ctx = await harness(adapter)
-    let agent!: ReactLoopAgent
+    let agent!: Agent
     const fiber = await ctx.plugin(Object.assign((inner: Context) => {
-      agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' })
+      agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', model: 'mock' })
     }, { inject: ['agentLoop'] }))
     send(agent, 'go')
     await new Promise(r => setTimeout(r, 30))
@@ -404,19 +430,21 @@ describe('ReactLoopAgent', () => {
   })
 
   it('whenIdle() on a disposed agent awaits the loop exit (done), not just the status flip', async () => {
-    // Disposed status is emitted before the driver unwinds. `whenIdle()` must chain `done` so it
-    // resolves only after true loop exit.
+    // The disposer emits agent/status('disposed') BEFORE the driver loop
+    // unwinds, so whenIdle() must chain `done` (true quiescence) on the
+    // disposed path. Dispose a running agent, then assert whenIdle() resolves
+    // only after `done` — i.e. the loop has actually exited.
     const adapter = new MockAdapter(['hang'])
     const ctx = await harness(adapter)
-    let agent!: ReactLoopAgent
+    let agent!: Agent
     const fiber = await ctx.plugin(Object.assign((inner: Context) => {
-      agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' })
+      agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', model: 'mock' })
     }, { inject: ['agentLoop'] }))
     send(agent, 'go')
     await new Promise(r => setTimeout(r, 30))
 
     let doneResolved = false
-    void agent.done.then(() => { doneResolved = true })
+    void driverDone(agent).then(() => { doneResolved = true })
     await fiber.dispose() // sets status disposed, aborts, drains the loop
     expect(agent.status).toBe('disposed')
 
@@ -431,7 +459,7 @@ describe('ReactLoopAgent', () => {
     const adapter = new MockAdapter([textResponse('ok')])
     const ctx = await harness(adapter)
     const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
     ctx.on('agent/status', (_subject, status) => {
       if (status === 'running') throw new Error('bad running listener')
     })
@@ -449,7 +477,7 @@ describe('ReactLoopAgent', () => {
     const adapter = new MockAdapter([textResponse('ok')])
     const ctx = await harness(adapter)
     const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
     ctx.on('agent/status', (_subject, status) => {
       if (status === 'idle') throw new Error('bad idle listener')
     })

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

@@ -12,10 +12,14 @@ import { Context } from 'cordis'
 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'
-import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
-import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
-import { MockAdapter, textResponse } from './mock-adapter.ts'
+import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
+import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
+import AgentLoop from '@deepseek-ai/dsh-agent-loop'
+import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts'
+
+function driverDone(agent: Agent): Promise<void> {
+  return (agent as Agent & { done: Promise<void> }).done
+}
 
 async function harness(adapter: MockAdapter) {
   const ctx = new Context()
@@ -29,12 +33,12 @@ async function harness(adapter: MockAdapter) {
   return ctx
 }
 
-function send(agent: ReactLoopAgent, text: string) {
+function send(agent: Agent, text: string) {
   agent.send([{ type: 'text', text }])
 }
 
 /** Resolve on the agent's next idle transition (event-based, not status poll). */
-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') { dispose(); resolve() }
@@ -43,7 +47,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
 }
 
 /** All user-message texts recorded in the log (to assert what actually ran). */
-function userTexts(agent: ReactLoopAgent): string[] {
+function userTexts(agent: Agent): string[] {
   return agent.session.events
     .filter(e => e.type === 'user/message')
     .flatMap(e => e.type === 'user/message' ? e.data.content : [])
@@ -54,7 +58,7 @@ describe('Agent.cancel()', () => {
   it('cancel() on an idle agent with nothing queued is a no-op; the next prompt runs (F2 leak guard)', async () => {
     const adapter = new MockAdapter([textResponse('reply')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     // The loop is parked at the idle wait with nothing queued. A cancel here must
     // NOT arm the marker — otherwise the next legitimate prompt would be dropped.
@@ -71,7 +75,7 @@ describe('Agent.cancel()', () => {
   it('pre-step cancel drops the about-to-start turn (no turn is opened)', async () => {
     const adapter = new MockAdapter([textResponse('should not run')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     // send() queues synchronously (status still idle, loop microtask not yet
     // resumed). Cancel in that pre-step window: the queued turn must not run.
@@ -92,11 +96,10 @@ describe('Agent.cancel()', () => {
     const adapter = new MockAdapter([textResponse('should not run')])
     const ctx = await harness(adapter)
     const handle = await ctx.agents.create({
-      agentId: AgentId('a-dispose-running'),
       sessionId: SessionId('dispose-running-session'),
-      agentOptions: { model: 'mock' },
+      agentOptions: { provider: 'mock', model: 'mock' },
     })
-    const agent = handle.agent as ReactLoopAgent
+    const agent = handle.agent
 
     const running = Promise.withResolvers<undefined>()
     let disposalDone: Promise<void> | undefined
@@ -110,7 +113,7 @@ describe('Agent.cancel()', () => {
     await running.promise
     if (disposalDone === undefined) throw new Error('running listener did not start disposal')
     await disposalDone
-    await agent.done
+    await driverDone(agent)
 
     expect(agent.status).toBe('disposed')
     expect(agent.session.events.some(event => event.type === 'turn/start')).toBe(false)
@@ -121,7 +124,7 @@ describe('Agent.cancel()', () => {
   it('a whenIdle() waiter registered BEFORE a pre-step cancel resolves (F1 hang guard)', async () => {
     const adapter = new MockAdapter([textResponse('x')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     // This waiter cannot rely on a running→idle transition because cancellation
     // drops the turn before it runs; the skip path must settle it directly.
@@ -140,7 +143,7 @@ describe('Agent.cancel()', () => {
   it('cancel() mid-step aborts the active turn and drops every queued tail item', async () => {
     const adapter = new MockAdapter(['hang'])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     const reasons: TurnEndReason[] = []
     ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
@@ -161,7 +164,7 @@ describe('Agent.cancel()', () => {
   it('cancel() with no reason defaults to "cancelled" when aborting an in-flight step', async () => {
     const adapter = new MockAdapter(['hang'])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     const reasons: TurnEndReason[] = []
     ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
@@ -174,10 +177,63 @@ describe('Agent.cancel()', () => {
     expect(reasons).toEqual([{ kind: 'aborted', reason: 'cancelled' }])
   })
 
+  it('cancel from an assistant/message observer skips execution but balances replay', async () => {
+    const adapter = new MockAdapter([
+      toolCallResponse('c1', 'danger', {}),
+      textResponse('recovered after cancellation'),
+    ])
+    const ctx = await harness(adapter)
+    let executions = 0
+    ctx.tools.register(defineTool({
+      name: 'danger',
+      description: 'must not run after cancellation',
+      parameters: {},
+      async execute() {
+        executions += 1
+        return [{ type: 'text', text: 'ran' }]
+      },
+    }))
+    const agent = ctx.agentLoop.create(SessionId('cancel-after-assistant-message'), { provider: 'mock', model: 'mock' })
+    const dispose = ctx.on('session/event', (session, event) => {
+      if (session === agent.session && event.type === 'assistant/message') {
+        agent.cancel('cancelled after assistant message')
+      }
+    })
+
+    const reasons: TurnEndReason[] = []
+    ctx.on('session/event', (_session, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
+
+    send(agent, 'go')
+    await waitForIdle(ctx, agent)
+    dispose()
+
+    expect(executions).toBe(0)
+    expect(reasons).toEqual([{ kind: 'aborted', reason: 'cancelled after assistant message' }])
+    const call = agent.session.events.find(event => event.type === 'tool/call')
+    const result = agent.session.events.find(event => event.type === 'tool/result')
+    expect(call?.type === 'tool/call' ? call.data.callId : undefined).toBe('c1')
+    expect(result?.type === 'tool/result' ? result.data : undefined).toMatchObject({
+      callId: 'c1',
+      isError: true,
+      error: { name: 'AbortError', code: 'ABORTED' },
+    })
+
+    send(agent, 'continue safely')
+    await waitForIdle(ctx, agent)
+    const replayedResult = adapter.requests[1]!.messages
+      .flatMap(message => message.content)
+      .find(block => block.type === 'tool-result')
+    expect(replayedResult).toMatchObject({ toolCallId: 'c1', isError: true })
+    expect(reasons).toEqual([
+      { kind: 'aborted', reason: 'cancelled after assistant message' },
+      { kind: 'completed' },
+    ])
+  })
+
   it('a prompt sent AFTER a cancelled turn settles runs normally (marker reset)', async () => {
     const adapter = new MockAdapter(['hang', textResponse('second reply')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     // First turn hangs; cancel it mid-step.
     send(agent, 'first')
@@ -199,7 +255,7 @@ describe('Agent.cancel()', () => {
   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' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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
@@ -233,11 +289,10 @@ describe('Agent.cancel()', () => {
     ctx.llm.registerAdapter(['mock'], adapter)
 
     const handle = await ctx.agents.create({
-      agentId: AgentId('a-dispose-prefix'),
       sessionId: SessionId('dispose-prefix-session'),
-      agentOptions: { model: 'mock' },
+      agentOptions: { provider: 'mock', model: 'mock' },
     })
-    const agent = handle.agent as ReactLoopAgent
+    const agent = handle.agent
 
     let disposalDone: Promise<void> | undefined
     let streamed = false
@@ -250,7 +305,7 @@ describe('Agent.cancel()', () => {
     send(agent, 'go')
     await new Promise(resolve => setTimeout(resolve, 0))
     await disposalDone
-    await agent.done
+    await driverDone(agent)
 
     // No step opened, no model call ran, and the turn closed disposed.
     expect(streamed).toBe(false)
@@ -262,7 +317,7 @@ describe('Agent.cancel()', () => {
   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' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     // The interrupted first composition must not cache its degraded empty value;
     // the next prompt recomposes and logs/sends the fresh prefix.
@@ -292,7 +347,7 @@ describe('Agent.cancel()', () => {
   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)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     // A turn/start listener fires before a step controller exists, so the
     // turn-scoped marker—not step abort—must drop the pending step.
@@ -319,7 +374,7 @@ describe('Agent.cancel()', () => {
   it('cancel from a synchronous step/start session-event 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' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     // A step/start session-event listener fires AFTER step/start is appended
     // (and after the pre-step seam), so cancelling there lands in the SECOND
@@ -358,11 +413,10 @@ describe('Agent.cancel()', () => {
     ctx.llm.registerAdapter(['mock'], adapter)
 
     const handle = await ctx.agents.create({
-      agentId: AgentId('a-dispose-step-start'),
       sessionId: SessionId('dispose-step-start-session'),
-      agentOptions: { model: 'mock' },
+      agentOptions: { provider: 'mock', model: 'mock' },
     })
-    const agent = handle.agent as ReactLoopAgent
+    const agent = handle.agent
 
     let disposalDone: Promise<void> | undefined
     let streamed = false
@@ -373,7 +427,7 @@ describe('Agent.cancel()', () => {
 
     send(agent, 'go')
     await disposalDone
-    await agent.done
+    await driverDone(agent)
 
     expect(streamed).toBe(false)
     expect(adapter.requests).toHaveLength(0)
@@ -390,7 +444,7 @@ describe('Agent.cancel()', () => {
     // `aborted` and run NO second step.
     const adapter = new MockAdapter([textResponse('one'), textResponse('two')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     let steps = 0
     const reasons: TurnEndReason[] = []
@@ -422,7 +476,7 @@ describe('Agent.cancel()', () => {
   it('cancel from a synchronous agent/status(running) listener drops the turn (window 2)', async () => {
     const adapter = new MockAdapter([textResponse('should not run')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     // `agent/status` is synchronous, so cancellation can land after the first
     // pre-step check; the second check must drop the now-empty turn.
@@ -446,7 +500,7 @@ describe('Agent.cancel()', () => {
     // Cancellation must not settle idle while replacement work remains queued.
     const adapter = new MockAdapter([textResponse('A reply'), textResponse('B reply')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     let replaced = false
     const dispose = ctx.on('agent/status', (subject, status) => {
@@ -473,7 +527,7 @@ describe('Agent.cancel()', () => {
     // prompt B is queued before the loop resumes from the idle wait.
     const adapter = new MockAdapter([textResponse('A reply'), textResponse('B reply')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     send(agent, 'A')           // queues A (status still idle, loop microtask pending)
     const idle = agent.whenIdle() // registers a waiter (idle + hasQueued → no fast path)
@@ -492,7 +546,7 @@ describe('Agent.cancel()', () => {
   it("cancel clears the turn's steering — it is not re-enqueued as a fresh turn", async () => {
     const adapter = new MockAdapter(['hang'])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     send(agent, 'go')
     await new Promise(r => setTimeout(r, 30))

packages/core/agent-loop/tests/config-session-id.spec.ts

@@ -7,15 +7,16 @@ import LlmService from '@deepseek-ai/dsh-llm'
 import SessionStore, { SessionId } 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'
+import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
+
 import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
-import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
+import AgentLoop from '@deepseek-ai/dsh-agent-loop'
 import { MockAdapter, textResponse } from './mock-adapter.ts'
 
 const dirs: string[] = []
 afterEach(async () => { for (const d of dirs.splice(0)) await rm(d, { recursive: true, force: true }) })
 
-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') { dispose(); resolve() }
@@ -23,7 +24,281 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
   })
 }
 
+async function makeCoreContext(): Promise<Context> {
+  const ctx = new Context()
+  await ctx.plugin(LlmService)
+  await ctx.plugin(SessionStore)
+  await ctx.plugin(SystemPrompt)
+  await ctx.plugin(ToolRegistry)
+  await ctx.plugin(AgentRegistry)
+  return ctx
+}
+
 describe('config-driven session id', () => {
+  it('rejects an empty exact id before publishing an agent', async () => {
+    const ctx = await makeCoreContext()
+    await expect(ctx.plugin(AgentLoop, {
+      agents: [{ id: 'main', sessionId: SessionId(''), model: 'mock' }],
+    })).rejects.toThrow('expected string length >= 1')
+    expect(ctx.agents.get(SessionId(''))).toBeUndefined()
+    await ctx.fiber.dispose()
+  })
+
+  it('accepts one exact fresh id and rejects it alongside a resume id', async () => {
+    const exact = await makeCoreContext()
+    await exact.plugin(AgentLoop, {
+      agents: [{ id: 'main', sessionId: SessionId('stdio-exact'), model: 'mock' }],
+    })
+    expect(exact.agents.get(SessionId('stdio-exact'))?.session.id).toBe('stdio-exact')
+    await exact.fiber.dispose()
+
+    const conflicting = await makeCoreContext()
+    await expect(conflicting.plugin(AgentLoop, {
+      agents: [{
+        id: 'main',
+        sessionId: SessionId('fresh'),
+        resumeSessionId: SessionId('persisted'),
+        model: 'mock',
+      }],
+    })).rejects.toThrow('sessionId and resumeSessionId are mutually exclusive')
+    await conflicting.fiber.dispose()
+  })
+
+  it('rejects duplicate exact ids before asynchronous configured startup', async () => {
+    const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-duplicate-'))
+    dirs.push(root)
+    const ctx = await makeCoreContext()
+    await ctx.plugin(SessionPersistenceJsonl, { root })
+
+    const outcome = await ctx.plugin(AgentLoop, {
+      agents: [
+        { id: 'first', sessionId: SessionId('shared'), model: 'mock' },
+        { id: 'second', sessionId: SessionId('shared'), model: 'mock' },
+      ],
+    }).then(() => undefined, (error: unknown) => error)
+    const published = ctx.agents.get(SessionId('shared'))
+    await ctx.fiber.dispose()
+
+    expect(outcome).toEqual(new Error('agents "first" and "second" use duplicate exact session identity "shared"'))
+    expect(published).toBeUndefined()
+  })
+
+  it('restores a materialized exact id across an AgentLoop-only reload', async () => {
+    const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-reload-'))
+    dirs.push(root)
+    const ctx = await makeCoreContext()
+    await ctx.plugin(SessionPersistenceJsonl, { root })
+    ctx.llm.registerAdapter(['mock'], new MockAdapter([textResponse('first'), textResponse('second')]))
+    const config = { agents: [{ id: 'main', sessionId: SessionId('stdio-exact-reload'), model: 'mock' }] }
+
+    const firstLoop = await ctx.plugin(AgentLoop, config)
+    let first: Agent | undefined
+    for (let i = 0; i < 50 && first === undefined; i++) {
+      await new Promise(resolve => setTimeout(resolve, 5))
+      first = ctx.agents.get(SessionId('stdio-exact-reload'))
+    }
+    expect(first).toBeDefined()
+    first!.send([{ type: 'text', text: 'remember me' }], { source: { kind: 'user' } })
+    await waitForIdle(ctx, first!)
+    await firstLoop.dispose()
+
+    const secondLoop = await ctx.plugin(AgentLoop, config)
+    let second: Agent | undefined
+    for (let i = 0; i < 50 && second === undefined; i++) {
+      await new Promise(resolve => setTimeout(resolve, 5))
+      second = ctx.agents.get(SessionId('stdio-exact-reload'))
+    }
+    expect(second).toBeDefined()
+    expect(JSON.stringify(second!.session.deriveMessages())).toContain('remember me')
+    second!.send([{ type: 'text', text: 'continue' }], { source: { kind: 'user' } })
+    await waitForIdle(ctx, second!)
+    await ctx.sessions.flush(second!.session)
+    const loaded = await ctx.sessionPersistence.load(SessionId('stdio-exact-reload'))
+    expect(loaded.events.filter(event => event.type === 'turn/start')).toHaveLength(2)
+
+    await secondLoop.dispose()
+    await ctx.fiber.dispose()
+  })
+
+  it('waits for a draining exact-id lifecycle during an overlapping reload', async () => {
+    const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-overlap-'))
+    dirs.push(root)
+    const ctx = await makeCoreContext()
+    await ctx.plugin(SessionPersistenceJsonl, { root })
+    const sessionId = SessionId('stdio-exact-overlap')
+    const config = { agents: [{ id: 'main', sessionId, model: 'mock' }] }
+    const firstLoop = await ctx.plugin(AgentLoop, config)
+    await expect.poll(() => ctx.agents.get(sessionId)).toBeDefined()
+    const first = ctx.agents.get(sessionId) as Agent
+
+    const flushGate = Promise.withResolvers<undefined>()
+    let flushStarted = false
+    ctx.on('session/flush', (session) => {
+      if (session !== first.session) return
+      flushStarted = true
+      return flushGate.promise
+    })
+    first.inject([{ type: 'text', text: 'persist before replacement' }], {
+      source: { kind: 'plugin', plugin: 'test' },
+    })
+    expect(flushStarted).toBe(true)
+
+    const firstDisposal = firstLoop.dispose()
+    await expect.poll(() => first.status).toBe('disposed')
+    const failures: unknown[] = []
+    ctx.on('agent-loop/config-start-failed', (_id, error) => { failures.push(error) })
+    const secondLoop = await ctx.plugin(AgentLoop, config)
+    await new Promise(resolve => setTimeout(resolve, 0))
+    expect(ctx.agents.get(sessionId)).toBe(first)
+    expect(failures).toEqual([])
+
+    flushGate.resolve(undefined)
+    await firstDisposal
+    await expect.poll(() => ctx.agents.get(sessionId)).toBeDefined()
+    const second = ctx.agents.get(sessionId) as Agent
+    expect(second).not.toBe(first)
+    expect(JSON.stringify(second.session.deriveMessages())).toContain('persist before replacement')
+    expect(failures).toEqual([])
+
+    await secondLoop.dispose()
+    await ctx.fiber.dispose()
+  })
+
+  it('cancels an exact-id reload while the prior lifecycle is still draining', async () => {
+    const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-cancel-'))
+    dirs.push(root)
+    const ctx = await makeCoreContext()
+    await ctx.plugin(SessionPersistenceJsonl, { root })
+    const sessionId = SessionId('stdio-exact-cancel')
+    const config = { agents: [{ id: 'main', sessionId, model: 'mock' }] }
+    const firstLoop = await ctx.plugin(AgentLoop, config)
+    await expect.poll(() => ctx.agents.get(sessionId)).toBeDefined()
+    const first = ctx.agents.get(sessionId) as Agent
+
+    const flushGate = Promise.withResolvers<undefined>()
+    ctx.on('session/flush', (session) => {
+      if (session === first.session) return flushGate.promise
+    })
+    first.inject([{ type: 'text', text: 'persist before cancellation' }], {
+      source: { kind: 'plugin', plugin: 'test' },
+    })
+
+    const firstDisposal = firstLoop.dispose()
+    await expect.poll(() => first.status).toBe('disposed')
+    const secondLoop = await ctx.plugin(AgentLoop, config)
+    await secondLoop.dispose()
+    expect(ctx.agents.get(sessionId)).toBe(first)
+
+    flushGate.resolve(undefined)
+    await firstDisposal
+    expect(ctx.agents.get(sessionId)).toBeUndefined()
+    await ctx.fiber.dispose()
+  })
+
+  it('contains an exact-id persistence lookup failure', async () => {
+    const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-failure-'))
+    dirs.push(root)
+    const ctx = await makeCoreContext()
+    await ctx.plugin(SessionPersistenceJsonl, { root })
+    const failure = new Error('persistence index failed')
+    const listenerFailure = new Error('failure observer failed')
+    const asyncListenerFailure = new Error('async failure observer failed')
+    const failures: { sessionId: SessionId; error: unknown }[] = []
+    ctx.on('agent-loop/config-start-failed', () => { throw listenerFailure })
+    ctx.on('agent-loop/config-start-failed', () => Promise.reject(asyncListenerFailure) as never)
+    ctx.on('agent-loop/config-start-failed', (sessionId, error) => {
+      failures.push({ sessionId, error })
+    })
+    vi.spyOn(ctx.sessionPersistence, 'list').mockRejectedValue(failure)
+    const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined)
+
+    await ctx.plugin(AgentLoop, {
+      agents: [{ id: 'main', sessionId: SessionId('stdio-exact-failure'), model: 'mock' }],
+    })
+
+    await expect.poll(() => warn).toHaveBeenCalledWith(expect.stringContaining(
+      'config-driven restore of "stdio-exact-failure" failed: Error: persistence index failed',
+    ))
+    expect(failures).toEqual([{ sessionId: SessionId('stdio-exact-failure'), error: failure }])
+    expect(warn).toHaveBeenCalledWith(
+      'agent "main": config-start-failed listener threw: Error: failure observer failed',
+    )
+    await expect.poll(() => warn).toHaveBeenCalledWith(
+      'agent "main": config-start-failed listener rejected: Error: async failure observer failed',
+    )
+    expect(ctx.agents.get(SessionId('stdio-exact-failure'))).toBeUndefined()
+    warn.mockRestore()
+    await ctx.fiber.dispose()
+  })
+
+  it('contains startup and observer failures whose string coercion throws', async () => {
+    const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-unrenderable-'))
+    dirs.push(root)
+    const ctx = await makeCoreContext()
+    await ctx.plugin(SessionPersistenceJsonl, { root })
+    const unrenderable = {
+      [Symbol.toPrimitive](): never {
+        throw new Error('coercion escaped')
+      },
+    }
+    const failures: unknown[] = []
+    ctx.on('agent-loop/config-start-failed', () => { throw unrenderable })
+    // Deliberately violate the normal Error-only rejection rule to exercise the unknown boundary.
+    // eslint-disable-next-line @typescript-eslint/prefer-promise-reject-errors
+    ctx.on('agent-loop/config-start-failed', () => Promise.reject(unrenderable) as never)
+    ctx.on('agent-loop/config-start-failed', (_sessionId, error) => { failures.push(error) })
+    vi.spyOn(ctx.sessionPersistence, 'list').mockRejectedValue(unrenderable)
+    const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined)
+
+    await ctx.plugin(AgentLoop, {
+      agents: [{ id: 'main', sessionId: SessionId('stdio-exact-unrenderable'), model: 'mock' }],
+    })
+
+    await expect.poll(() => failures).toEqual([unrenderable])
+    expect(warn).toHaveBeenCalledWith(
+      'agent "main": config-driven restore of "stdio-exact-unrenderable" failed: <unrenderable thrown value>',
+    )
+    expect(warn).toHaveBeenCalledWith(
+      'agent "main": config-start-failed listener threw: <unrenderable thrown value>',
+    )
+    await expect.poll(() => warn).toHaveBeenCalledWith(
+      'agent "main": config-start-failed listener rejected: <unrenderable thrown value>',
+    )
+    await ctx.fiber.dispose()
+  })
+
+  it.each(['resolve', 'reject'] as const)(
+    'joins an exact-id persistence lookup that will %s before AgentLoop disposal completes',
+    async (outcome) => {
+      const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-dispose-'))
+      dirs.push(root)
+      const ctx = await makeCoreContext()
+      await ctx.plugin(SessionPersistenceJsonl, { root })
+      const listing = Promise.withResolvers<Awaited<ReturnType<typeof ctx.sessionPersistence.list>>>()
+      vi.spyOn(ctx.sessionPersistence, 'list').mockReturnValue(listing.promise)
+      const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined)
+      const failures: unknown[] = []
+      ctx.on('agent-loop/config-start-failed', (_sessionId, error) => { failures.push(error) })
+
+      const loop = await ctx.plugin(AgentLoop, {
+        agents: [{ id: 'main', sessionId: SessionId('stdio-exact-dispose'), model: 'mock' }],
+      })
+      let disposed = false
+      const disposal = loop.dispose().then(() => { disposed = true })
+      await Promise.resolve()
+      expect(disposed).toBe(false)
+
+      if (outcome === 'resolve') listing.resolve([])
+      else listing.reject(new Error('startup cancelled by teardown'))
+      await disposal
+      expect(ctx.agents.get(SessionId('stdio-exact-dispose'))).toBeUndefined()
+      expect(failures).toEqual([])
+      expect(warn).not.toHaveBeenCalled()
+      warn.mockRestore()
+      await ctx.fiber.dispose()
+    },
+  )
+
   it('identity-nests the deferred resume fiber under its labeled owner effect', async () => {
     const ctx = new Context()
     await ctx.plugin(LlmService)
@@ -32,7 +307,7 @@ describe('config-driven session id', () => {
     await ctx.plugin(ToolRegistry)
     await ctx.plugin(AgentRegistry)
     const loopFiber = await ctx.plugin(AgentLoop, {
-      agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('deferred') }],
+      agents: [{ id: SessionId('main'), provider: 'mock', model: 'mock', resumeSessionId: SessionId('deferred') }],
     })
 
     const resumeEffect = loopFiber.getEffects().find(effect => effect.label === 'agentLoop.resume(main)')
@@ -53,11 +328,13 @@ describe('config-driven session id', () => {
     await ctx1.plugin(SystemPrompt)
     await ctx1.plugin(ToolRegistry)
     await ctx1.plugin(AgentRegistry)
-    await ctx1.plugin(AgentLoop, { agents: [{ id: AgentId('cfg'), model: 'mock' }] })
+    await ctx1.plugin(AgentLoop, { agents: [{ id: SessionId('cfg'), provider: 'mock', model: 'mock' }] })
     await ctx1.plugin(SessionPersistenceJsonl, { root })
     ctx1.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg')]))
-    const a1 = ctx1.agents.get(AgentId('cfg')) as ReactLoopAgent
+    const a1 = ctx1.agents.list()[0] as Agent
+    expect(a1.id).toBe(a1.session.id)
     expect(a1.session.id).toMatch(idPattern)
+    expect(ctx1.agents.get(SessionId('cfg'))).toBeUndefined()
     a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } })
     await waitForIdle(ctx1, a1)
     await ctx1.fiber.dispose()
@@ -70,10 +347,11 @@ describe('config-driven session id', () => {
     await ctx2.plugin(SystemPrompt)
     await ctx2.plugin(ToolRegistry)
     await ctx2.plugin(AgentRegistry)
-    await ctx2.plugin(AgentLoop, { agents: [{ id: AgentId('cfg'), model: 'mock' }] })
+    await ctx2.plugin(AgentLoop, { agents: [{ id: SessionId('cfg'), provider: 'mock', model: 'mock' }] })
     await ctx2.plugin(SessionPersistenceJsonl, { root })
     ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg2')]))
-    const a2 = ctx2.agents.get(AgentId('cfg')) as ReactLoopAgent
+    const a2 = ctx2.agents.list()[0] as Agent
+    expect(a2.id).toBe(a2.session.id)
     expect(a2.session.id).toMatch(idPattern)
     expect(a2.session.id).not.toBe(a1.session.id)
     a2.send([{ type: 'text', text: 'q2' }], { source: { kind: 'user' } })
@@ -96,7 +374,7 @@ describe('config-driven session id', () => {
     await ctx1.plugin(AgentLoop, { agents: [] })
     await ctx1.plugin(SessionPersistenceJsonl, { root })
     ctx1.llm.registerAdapter(['mock'], new MockAdapter([textResponse('first')]))
-    const a1 = (await ctx1.agents.create({ agentId: AgentId('main'), sessionId: SessionId('sticky-1') })).agent as ReactLoopAgent
+    const a1 = (await ctx1.agents.create({ sessionId: SessionId('sticky-1') })).agent
     a1.send([{ type: 'text', text: 'remember me' }], { source: { kind: 'user' } })
     await waitForIdle(ctx1, a1)
     await ctx1.fiber.dispose()
@@ -109,19 +387,20 @@ describe('config-driven session id', () => {
     await ctx2.plugin(SystemPrompt)
     await ctx2.plugin(ToolRegistry)
     await ctx2.plugin(AgentRegistry)
-    await ctx2.plugin(AgentLoop, { agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('sticky-1') }] })
+    await ctx2.plugin(AgentLoop, { agents: [{ id: SessionId('main'), provider: 'mock', model: 'mock', resumeSessionId: SessionId('sticky-1') }] })
     await ctx2.plugin(SessionPersistenceJsonl, { root })
     ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('second')]))
 
     // The deferred resume runs on a microtask after the backend is available.
-    let resumed: ReactLoopAgent | undefined
+    let resumed: Agent | undefined
     for (let i = 0; i < 50 && !resumed; i++) {
       await new Promise(r => setTimeout(r, 5))
-      resumed = ctx2.agents.get(AgentId('main')) as ReactLoopAgent | undefined
+      resumed = ctx2.agents.get(SessionId('sticky-1'))
     }
     expect(resumed).toBeDefined()
     // The live session id IS the resumed id (NOT a fresh ${id}-session-<uuid>),
     // and the prior turn's user message is in the derived history.
+    expect(resumed!.id).toBe(SessionId('sticky-1'))
     expect(resumed!.session.id).toBe('sticky-1')
     const derived = resumed!.session.deriveMessages()
     expect(JSON.stringify(derived)).toContain('remember me')
@@ -137,16 +416,16 @@ describe('config-driven session id', () => {
     await ctx.plugin(SystemPrompt)
     await ctx.plugin(ToolRegistry)
     await ctx.plugin(AgentRegistry)
-    await ctx.plugin(AgentLoop, { agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('does-not-exist') }] })
+    await ctx.plugin(AgentLoop, { agents: [{ id: SessionId('main'), provider: 'mock', model: 'mock', resumeSessionId: SessionId('does-not-exist') }] })
     const warn = vi.spyOn((ctx.agentLoop as unknown as { ctx: { logger: { warn: (...a: unknown[]) => void } } }).ctx.logger, 'warn')
       .mockImplementation(() => undefined)
     await ctx.plugin(SessionPersistenceJsonl, { root })
     ctx.llm.registerAdapter(['mock'], new MockAdapter([textResponse('x')]))
 
     // The deferred resume fails (no such session on disk). It must be contained:
-    // a warning is logged, no 'main' agent is registered, and the app stays up.
+    // a warning is logged, no agent is registered, and the app stays up.
     await new Promise(r => setTimeout(r, 200))
-    expect(ctx.agents.get(AgentId('main'))).toBeUndefined()
+    expect(ctx.agents.list()).toEqual([])
     expect(warn).toHaveBeenCalledWith(expect.stringContaining('config-driven resume of "does-not-exist" failed'))
     warn.mockRestore()
     await ctx.fiber.dispose()

packages/core/agent-loop/tests/contract-regressions.spec.ts

@@ -3,12 +3,16 @@ import { Context } from 'cordis'
 import LlmService, { CallId, ContentBlock, MessageSource, StreamChunk } from '@deepseek-ai/dsh-llm'
 import SessionStore, { Session, SessionEvent, SessionId, TurnEndReason } from '@deepseek-ai/dsh-session'
 import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
-import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
-import AgentRegistry, { AgentId, type ContinuationDecision } from '@deepseek-ai/dsh-agent'
-import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
+import ToolRegistry, { defineTool, type PostToolDecision } from '@deepseek-ai/dsh-tools'
+import AgentRegistry, { type Agent, type ContinuationDecision } from '@deepseek-ai/dsh-agent'
+import AgentLoop, { DEFAULT_MAX_PARALLEL_TOOL_CALLS } from '@deepseek-ai/dsh-agent-loop'
 import { prepareReactLoopAgent } from '../src/agent.ts'
 import * as Invariants from '@deepseek-ai/dsh-invariants'
-import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts'
+import { maxTokensResponse, MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts'
+
+function driverDone(agent: Agent): Promise<void> {
+  return (agent as Agent & { done: Promise<void> }).done
+}
 
 /** Regression tests for agent-loop boundary, identity, and lifecycle contracts. */
 
@@ -24,7 +28,7 @@ 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') {
@@ -35,13 +39,15 @@ 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 }])
 }
 
 describe('session log records what agent/step-result actually produced', () => {
   it('a step-result rewrite is what the log, derived history, and tool dispatch all see', async () => {
-    const adapter = new MockAdapter([textResponse('original'), textResponse('done')])
+    const original = textResponse('original')
+    original[original.length - 1] = { type: 'finish', reason: { kind: 'stop' }, replayState: { private: 'original-state' } }
+    const adapter = new MockAdapter([original, textResponse('done')])
     const ctx = await harness(adapter)
     const executed: string[] = []
     ctx.tools.register(defineTool({
@@ -53,7 +59,7 @@ describe('session log records what agent/step-result actually produced', () => {
         return [{ type: 'text', text: 'ran' }]
       },
     }))
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     // Plugin rewrites the message: replaces the text AND adds a tool call.
     let rewritten = false
@@ -78,6 +84,7 @@ describe('session log records what agent/step-result actually produced', () => {
     const recorded = agent.session.events.find(e => e.type === 'assistant/message')!
     expect(JSON.stringify(recorded.data)).toContain('rewritten')
     expect(JSON.stringify(recorded.data)).not.toContain('original')
+    expect(recorded.type === 'assistant/message' && recorded.data.provenance.replayState).toBeUndefined()
     // tool/call + tool/result correlate with the injected call id
     const callEvent = agent.session.events.find(e => e.type === 'tool/call')!
     if (callEvent.type !== 'tool/call') throw new Error('wrong event type')
@@ -87,10 +94,117 @@ describe('session log records what agent/step-result actually produced', () => {
     expect(JSON.stringify(derived)).toContain('rewritten')
     expect(JSON.stringify(derived)).not.toContain('original')
   })
+
+  it('records adapter replay state when step-result preserves the assembled content', async () => {
+    const response = textResponse('unchanged')
+    const replayState = { private: 'state' }
+    response[response.length - 1] = { type: 'finish', reason: { kind: 'stop' }, replayState }
+    const adapter = new MockAdapter([response])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(SessionId('replay-state'), { provider: 'mock', model: 'next-model' })
+
+    send(agent, 'go')
+    await waitForIdle(ctx, agent)
+
+    const recorded = agent.session.events.find(e => e.type === 'assistant/message')
+    expect(recorded?.type === 'assistant/message' && recorded.data.provenance).toEqual({
+      provider: 'mock', model: 'next-model', replayState,
+    })
+    expect(agent.session.deriveMessages().at(-1)?.provenance).toEqual({
+      provider: 'mock', model: 'next-model', replayState,
+    })
+  })
+
+  it('drops adapter replay state when step-result mutates assembled content in place', async () => {
+    const response = textResponse('original')
+    response[response.length - 1] = { type: 'finish', reason: { kind: 'stop' }, replayState: { private: 'state' } }
+    const adapter = new MockAdapter([response])
+    const ctx = await harness(adapter)
+    ctx.on('agent/step-result', async (_agent, _turn, _step, message) => {
+      const block = message.content[0]
+      if (block?.type === 'text') block.text = 'mutated'
+      return message
+    })
+    const agent = ctx.agentLoop.create(SessionId('mutated-replay-state'), { provider: 'mock', model: 'next-model' })
+
+    send(agent, 'go')
+    await waitForIdle(ctx, agent)
+
+    const recorded = agent.session.events.find(event => event.type === 'assistant/message')
+    expect(recorded?.type === 'assistant/message' && recorded.data.content).toEqual([{ type: 'text', text: 'mutated' }])
+    expect(recorded?.type === 'assistant/message' && recorded.data.provenance.replayState).toBeUndefined()
+  })
+})
+
+describe('successful provider completion survives agent/step-result failure', () => {
+  async function expectContentlessCompletionAnchor(
+    response: StreamChunk[],
+    id: string,
+    providerText: string,
+  ): Promise<void> {
+    const adapter = new MockAdapter([response])
+    const ctx = await harness(adapter)
+    await ctx.plugin(Invariants)
+    const agent = ctx.agentLoop.create(SessionId(id), { provider: 'mock', model: 'mock' })
+    const failure = new Error(`${id} result processing failed`)
+    const reported: Error[] = []
+
+    ctx.on('agent/step-result', async () => {
+      throw failure
+    })
+    ctx.on('agent/error', (subject, _turn, _step, error) => {
+      if (subject === agent) reported.push(error)
+    })
+
+    send(agent, 'go')
+    await waitForIdle(ctx, agent)
+
+    const events = [...agent.session.events]
+    const chunks = events.filter(event => event.type === 'assistant/chunk')
+    const completions = events.filter(event => event.type === 'assistant/message')
+    expect(completions).toHaveLength(1)
+    expect(completions[0]?.type === 'assistant/message' && completions[0].data).toEqual({
+      turn: 1,
+      step: 1,
+      content: [],
+      provenance: { provider: 'mock', model: 'mock' },
+      usage: { inputTokens: 10, outputTokens: providerText.length },
+    })
+    expect(completions[0]?.sourceEventSeqs).toEqual(chunks.map(event => event.seq))
+    expect(agent.session.deriveMessages()).toEqual([
+      { role: 'user', content: [{ type: 'text', text: 'go' }] },
+    ])
+    expect(reported).toHaveLength(1)
+    expect(reported[0]).toBe(failure)
+    const turnEnd = events.findLast(event => event.type === 'turn/end')
+    expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toEqual({
+      kind: 'error',
+      step: 1,
+      message: failure.message,
+    })
+  }
+
+  it('records one content-less anchor when ordinary stop result processing rejects', async () => {
+    const providerText = 'ordinary provider output'
+    await expectContentlessCompletionAnchor(
+      textResponse(providerText),
+      'a-step-result-stop-failure',
+      providerText,
+    )
+  })
+
+  it('records one content-less anchor when max-token result processing rejects', async () => {
+    const providerText = 'truncated provider output'
+    await expectContentlessCompletionAnchor(
+      maxTokensResponse(providerText),
+      'a-step-result-max-token-failure',
+      providerText,
+    )
+  })
 })
 
 describe('abort during tool execution ends the turn', () => {
-  it('aborting the in-flight step inside a tool prevents both remaining tools and the next model step', async () => {
+  it('balances an aborted tool batch through context, steering, and post-step before closing', async () => {
     const adapter = new MockAdapter([
       // model asks for two tool calls in one step
       [
@@ -104,21 +218,29 @@ describe('abort during tool execution ends the turn', () => {
     ])
     const ctx = await harness(adapter)
     const executed: string[] = []
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
     ctx.tools.register(defineTool({
       name: 'aborter',
       description: '',
       parameters: {},
-      async execute() {
+      async execute(_args, exec) {
         executed.push('aborter')
-        // Fire the in-flight step's AbortController directly (the loop registers
-        // it on the agent). This is the bare step-abort path — distinct from
-        // cancel(), which would also clear the inbox; here the subject is the
-        // loop's response to its running step being aborted mid-tool.
+        exec.agent?.steer(
+          [{ type: 'text', text: 'steering before abort' }],
+          { source: { kind: 'plugin', plugin: 'abort-test' } },
+        )
+        // Exercise bare step abort without `cancel()` clearing queued work.
         ;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('user interrupt')
         return [{ type: 'text', text: 'done' }]
       },
     }))
+    ctx.on('tools/post-execute', async exec => ({
+      kind: 'accept',
+      additionalContexts: [{
+        content: [{ type: 'text', text: `context for ${exec.callId}` }],
+        source: { kind: 'plugin', plugin: 'abort-test' },
+      }],
+    }))
     ctx.tools.register(defineTool({
       name: 'second',
       description: '',
@@ -130,14 +252,248 @@ describe('abort during tool execution ends the turn', () => {
     }))
 
     const reasons: TurnEndReason[] = []
-    ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
+    const order: string[] = []
+    ctx.on('session/event', (session, event) => {
+      if (session !== agent.session) return
+      switch (event.type) {
+        case 'assistant/message': order.push('assistant/message'); break
+        case 'tool/call': order.push(`tool/call:${event.data.callId}`); break
+        case 'tool/result': {
+          const outcome = event.data.error?.code === 'ABORTED' ? 'synthetic-aborted' : 'real'
+          order.push(`tool/result:${event.data.callId}:${outcome}`)
+          break
+        }
+        case 'context/message': order.push('context/message'); break
+        case 'steering/message': order.push('steering/message'); break
+        case 'step/end': order.push('step/end'); break
+        case 'turn/end': {
+          reasons.push(event.data.reason)
+          order.push(`turn/end:${event.data.reason.kind}`)
+          break
+        }
+      }
+    })
+    let postSteps = 0
+    ctx.on('agent/post-step', (subject, turn, step, signal) => {
+      if (subject !== agent) return
+      postSteps += 1
+      expect({ turn, step, aborted: signal.aborted }).toEqual({ turn: 1, step: 1, aborted: true })
+      order.push('agent/post-step')
+    })
 
     send(agent, 'go')
     await waitForIdle(ctx, agent)
 
-    expect(executed).toEqual(['aborter'])           // second tool never ran
-    expect(adapter.requests).toHaveLength(1)        // no follow-up model call
+    expect(executed).toEqual(['aborter'])
+    expect(adapter.requests).toHaveLength(1)
+    expect(postSteps).toBe(1)
+    expect(order).toEqual([
+      'assistant/message',
+      'tool/call:c1',
+      'tool/result:c1:real',
+      'tool/call:c2',
+      'tool/result:c2:synthetic-aborted',
+      'context/message',
+      'steering/message',
+      'agent/post-step',
+      'step/end',
+      'turn/end:aborted',
+    ])
     expect(reasons).toEqual([{ kind: 'aborted', reason: 'user interrupt' }])
+    const calls = agent.session.events.filter(event => event.type === 'tool/call')
+    const results = agent.session.events.filter(event => event.type === 'tool/result')
+    expect(calls.map(event => event.data.callId)).toEqual([CallId('c1'), CallId('c2')])
+    expect(results).toHaveLength(2)
+    expect(results[0]!.data).toMatchObject({ callId: CallId('c1'), isError: false })
+    expect(results[1]!.data).toMatchObject({
+      callId: CallId('c2'),
+      isError: true,
+      error: { name: 'AbortError', code: 'ABORTED' },
+    })
+  })
+
+  it('records context accepted before a tool-step abort in the same turn', async () => {
+    const adapter = new MockAdapter([toolCallResponse('c1', 'aborter', {})])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(SessionId('a-abort-injection'), { provider: 'mock', model: 'mock' })
+    ctx.tools.register(defineTool({
+      name: 'aborter',
+      description: '',
+      parameters: {},
+      async execute() {
+        agent.inject([{ type: 'text', text: 'accepted before abort' }], { source: { kind: 'plugin', plugin: 'test' } })
+        ;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('user interrupt')
+        return [{ type: 'text', text: 'done' }]
+      },
+    }))
+    ctx.on('tools/post-execute', async (): Promise<PostToolDecision> => ({
+      kind: 'accept',
+      additionalContexts: [{
+        content: [{ type: 'text', text: 'accepted result context after abort' }],
+        source: { kind: 'plugin', plugin: 'test' },
+      }],
+    }))
+
+    send(agent, 'go')
+    await waitForIdle(ctx, agent)
+
+    const events = [...agent.session.events]
+    expect(events
+      .filter(event => event.type === 'tool/result' || event.type === 'context/message'
+        || event.type === 'step/end' || event.type === 'turn/end')
+      .map(event => event.type))
+      .toEqual(['tool/result', 'context/message', 'context/message', 'step/end', 'turn/end'])
+    expect(events
+      .filter(event => event.type === 'context/message')
+      .map(event => event.data.content))
+      .toEqual([
+        [{ type: 'text', text: 'accepted before abort' }],
+        [{ type: 'text', text: 'accepted result context after abort' }],
+      ])
+  })
+
+  it('records post-tool context when a later call aborts the batch', async () => {
+    const adapter = new MockAdapter([[
+      { type: 'block-start', index: 0, blockType: 'tool-call' },
+      { type: 'block-end', index: 0, block: { type: 'tool-call', id: CallId('c1'), name: 'first', arguments: '{}' } },
+      { type: 'block-start', index: 1, blockType: 'tool-call' },
+      { type: 'block-end', index: 1, block: { type: 'tool-call', id: CallId('c2'), name: 'aborter', arguments: '{}' } },
+      { type: 'finish', reason: { kind: 'tool-calls' } },
+    ] satisfies StreamChunk[]])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(SessionId('a-later-abort-context'), { provider: 'mock', model: 'mock' })
+    ctx.tools.register(defineTool({
+      name: 'first',
+      description: '',
+      parameters: {},
+      async execute() {
+        return [{ type: 'text', text: 'first done' }]
+      },
+    }))
+    ctx.tools.register(defineTool({
+      name: 'aborter',
+      description: '',
+      parameters: {},
+      async execute() {
+        ;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('user interrupt')
+        return [{ type: 'text', text: 'aborted' }]
+      },
+    }))
+    ctx.on('tools/post-execute', async (exec, _result, next): Promise<PostToolDecision> => {
+      if (exec.callId !== CallId('c1')) return next()
+      return {
+        kind: 'accept',
+        additionalContexts: [{
+          content: [{ type: 'text', text: 'accepted after first result' }],
+          source: { kind: 'plugin', plugin: 'test' },
+        }],
+      }
+    })
+
+    send(agent, 'go')
+    await waitForIdle(ctx, agent)
+
+    const events = [...agent.session.events]
+    expect(events
+      .filter(event => event.type === 'tool/result' || event.type === 'context/message'
+        || event.type === 'step/end' || event.type === 'turn/end')
+      .map(event => event.type))
+      .toEqual(['tool/result', 'tool/result', 'context/message', 'step/end', 'turn/end'])
+    expect(events.find(event => event.type === 'context/message')?.data.content)
+      .toEqual([{ type: 'text', text: 'accepted after first result' }])
+  })
+
+  it('drains deferred context before disposal reaches quiescence', async () => {
+    const adapter = new MockAdapter([toolCallResponse('c1', 'waiter', {})])
+    const ctx = await harness(adapter)
+    const started = Promise.withResolvers<undefined>()
+    let agent!: Agent
+    const fiber = await ctx.plugin(Object.assign((inner: Context) => {
+      agent = inner.agentLoop.create(SessionId('a-dispose-injection'), { provider: 'mock', model: 'mock' })
+    }, { inject: ['agentLoop'] }))
+    ctx.tools.register(defineTool({
+      name: 'waiter',
+      description: '',
+      parameters: {},
+      async execute(_args, exec) {
+        agent.inject([{ type: 'text', text: 'accepted before disposal' }], { source: { kind: 'plugin', plugin: 'test' } })
+        started.resolve(undefined)
+        const signal = exec.signal
+        if (!signal) throw new Error('tool execution signal is missing')
+        await new Promise<void>((resolve) => {
+          if (signal.aborted) resolve()
+          else signal.addEventListener('abort', () => { resolve() }, { once: true })
+        })
+        return [{ type: 'text', text: 'done' }]
+      },
+    }))
+    ctx.on('tools/post-execute', async (): Promise<PostToolDecision> => ({
+      kind: 'accept',
+      additionalContexts: [{
+        content: [{ type: 'text', text: 'accepted result context during disposal' }],
+        source: { kind: 'plugin', plugin: 'test' },
+      }],
+    }))
+
+    send(agent, 'go')
+    await started.promise
+    await fiber.dispose()
+
+    expect(agent.session.events
+      .filter(event => event.type === 'context/message')
+      .map(event => event.data.content))
+      .toEqual([
+        [{ type: 'text', text: 'accepted before disposal' }],
+        [{ type: 'text', text: 'accepted result context during disposal' }],
+      ])
+    expect(agent.session.events.find(event => event.type === 'turn/end')?.data.reason)
+      .toEqual({ kind: 'disposed' })
+  })
+
+  it('limits injection deferral to the current tool batch', async () => {
+    const adapter = new MockAdapter([
+      [
+        { type: 'block-start', index: 0, blockType: 'tool-call' },
+        { type: 'block-end', index: 0, block: { type: 'tool-call', id: CallId('c1'), name: 'aborter', arguments: '{}' } },
+        { type: 'block-start', index: 1, blockType: 'tool-call' },
+        { type: 'block-end', index: 1, block: { type: 'tool-call', id: CallId('c2'), name: 'second', arguments: '{}' } },
+        { type: 'finish', reason: { kind: 'tool-calls' } },
+      ] satisfies StreamChunk[],
+      textResponse('later turn'),
+    ])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(SessionId('a-historical-tool-pair'), { provider: 'mock', model: 'mock' })
+    ctx.tools.register(defineTool({
+      name: 'aborter',
+      description: '',
+      parameters: {},
+      async execute() {
+        ;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('user interrupt')
+        return [{ type: 'text', text: 'done' }]
+      },
+    }))
+    ctx.tools.register(defineTool({
+      name: 'second',
+      description: '',
+      parameters: {},
+      async execute() {
+        return [{ type: 'text', text: 'must not run' }]
+      },
+    }))
+
+    send(agent, 'leave an unmatched historical call')
+    await waitForIdle(ctx, agent)
+    ctx.on('agent/pre-step', (subject, turn) => {
+      if (subject === agent && turn === 2) {
+        agent.inject([{ type: 'text', text: 'new turn context' }], { source: { kind: 'plugin', plugin: 'test' } })
+      }
+    })
+    send(agent, 'start a text-only turn')
+    await waitForIdle(ctx, agent)
+
+    expect(agent.session.events.find(event => event.type === 'context/message')?.data.content)
+      .toEqual([{ type: 'text', text: 'new turn context' }])
+    expect(JSON.stringify(adapter.requests[1]?.messages)).toContain('new turn context')
   })
 })
 
@@ -148,7 +504,7 @@ describe('steering from late extension points is never stranded', () => {
       textResponse('continued because of steering'),
     ])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     let steeredOnce = false
     ctx.on('agent/turn-continuation', async (_agent, _turn, _decision, next) => {
@@ -174,7 +530,7 @@ describe('steering from late extension points is never stranded', () => {
       textResponse('after goal reminder'),
     ])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     let steeredOnce = false
     ctx.on('session/event', (subject, event) => {
@@ -202,7 +558,7 @@ describe('steering from late extension points is never stranded', () => {
   it('steer() from a turn/end session-event listener becomes a queued message for the next turn', async () => {
     const adapter = new MockAdapter([textResponse('turn 1'), textResponse('turn 2')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     const turns: number[] = []
     let steeredOnce = false
@@ -228,7 +584,7 @@ describe('steering from late extension points is never stranded', () => {
   it('steering queued during an aborted step is re-delivered, not silently consumed', async () => {
     const adapter = new MockAdapter(['hang', textResponse('recovered')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     send(agent, 'go')
     await new Promise(r => setTimeout(r, 30))
@@ -251,7 +607,7 @@ describe('plugin exceptions are contained', () => {
   it('a throwing agent/turn-continuation listener ends the turn with an error, loop survives', async () => {
     const adapter = new MockAdapter([textResponse('one'), textResponse('two')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     let threwOnce = false
     ctx.on('agent/turn-continuation', async (): Promise<ContinuationDecision> => {
@@ -279,7 +635,7 @@ describe('plugin exceptions are contained', () => {
   it('a rejecting first-turn flush settles before the queued tail starts', async () => {
     const adapter = new MockAdapter([textResponse('one'), textResponse('two')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     const firstFlush = Promise.withResolvers<undefined>()
     const releaseFirstFlush = Promise.withResolvers<undefined>()
@@ -319,9 +675,9 @@ describe('disposed status is part of the agent/status contract', () => {
     const adapter = new MockAdapter(['hang'])
     const ctx = await harness(adapter)
 
-    let agent!: ReactLoopAgent
+    let agent!: Agent
     const fiber = await ctx.plugin(Object.assign((inner: Context) => {
-      agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' })
+      agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', model: 'mock' })
     }, { inject: ['agentLoop'] }))
 
     const statuses: string[] = []
@@ -333,7 +689,7 @@ describe('disposed status is part of the agent/status contract', () => {
     await new Promise(r => setTimeout(r, 30))
     send(agent, 'queued tail')
     await fiber.dispose()
-    await agent.done
+    await driverDone(agent)
 
     expect(statuses).toEqual(['running', 'disposed'])
     expect(reasons).toEqual([{ kind: 'disposed' }])
@@ -350,9 +706,9 @@ describe('disposed status is part of the agent/status contract', () => {
     const adapter = new MockAdapter(['hang'])
     const ctx = await harness(adapter)
 
-    let agent!: ReactLoopAgent
+    let agent!: Agent
     const fiber = await ctx.plugin(Object.assign((inner: Context) => {
-      agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' })
+      agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', model: 'mock' })
     }, { inject: ['agentLoop'] }))
 
     ctx.on('agent/status', (_agent, status) => {
@@ -362,10 +718,10 @@ describe('disposed status is part of the agent/status contract', () => {
     send(agent, 'go')
     await new Promise(r => setTimeout(r, 30))
     await fiber.dispose()
-    await agent.done // must not hang
+    await driverDone(agent) // must not hang
 
     expect(agent.status).toBe('disposed')
-    expect(ctx.agents.get(AgentId('scoped'))).toBeUndefined() // unregistered despite the throw
+    expect(ctx.agents.get(SessionId('scoped'))).toBeUndefined() // unregistered despite the throw
   })
 })
 
@@ -378,13 +734,13 @@ describe('adapter registration, routing, and accepted-input ownership', () => {
     expect(() => ctx.llm.registerAdapter(['m1'], new MockAdapter([])))
       .toThrow('already registered')
     // the original registration survives the failed attempt
-    expect(ctx.llm.models()).toEqual(['m1'])
+    expect(ctx.llm.listProviders()).toEqual([{ id: 'm1', name: 'm1' }])
   })
 
   it('an agent without a model fails the step with a clear error (not NO_ADAPTER for "default")', async () => {
     const adapter = new MockAdapter([textResponse('never')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), {}) // no model
+    const agent = ctx.agentLoop.create(SessionId('a1'), {}) // no model
 
     const errors: Error[] = []
     ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error))
@@ -392,17 +748,17 @@ describe('adapter registration, routing, and accepted-input ownership', () => {
     send(agent, 'go')
     await waitForIdle(ctx, agent)
     expect(errors).toHaveLength(1)
-    expect(errors[0]!.message).toContain('has no model')
+    expect(errors[0]!.message).toContain('has no provider/model')
     expect(errors[0]!.message).toContain('agent/request')
   })
 
   it('the agent/request waterfall can supply the model for a model-less agent', async () => {
     const adapter = new MockAdapter([textResponse('routed')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), {}) // no model — router plugin decides
+    const agent = ctx.agentLoop.create(SessionId('a1'), {}) // no model — router plugin decides
 
     ctx.on('agent/request', async (_agent, _turn, _step, config, _next) => {
-      return { ...config, model: 'mock' }
+      return { ...config, provider: 'mock', model: 'mock' }
     })
 
     send(agent, 'go')
@@ -414,7 +770,7 @@ describe('adapter registration, routing, and accepted-input ownership', () => {
   it('agent/queued carries the resolved source; steering/message records its source', async () => {
     const adapter = new MockAdapter([toolCallResponse('c1', 'noop', {}), textResponse('done')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
     ctx.tools.register(defineTool({
       name: 'noop',
       description: '',
@@ -442,7 +798,7 @@ describe('adapter registration, routing, and accepted-input ownership', () => {
   it('send() owns content and source before notification and delivery', async () => {
     const adapter = new MockAdapter([textResponse('done')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('owned-send'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('owned-send'), { provider: 'mock', model: 'mock' })
     const content = [{ type: 'text' as const, text: 'accepted-send' }]
     const source = { kind: 'plugin' as const, plugin: 'accepted-source' }
     let notifiedContent: ContentBlock[] | undefined
@@ -478,7 +834,7 @@ describe('adapter registration, routing, and accepted-input ownership', () => {
   it('running steer() owns content and source before notification and delivery', async () => {
     const adapter = new MockAdapter([toolCallResponse('c1', 'gate', {}), textResponse('done')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('owned-steer'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('owned-steer'), { provider: 'mock', model: 'mock' })
     const entered = Promise.withResolvers<undefined>()
     const release = Promise.withResolvers<undefined>()
     ctx.tools.register(defineTool({
@@ -532,7 +888,7 @@ describe('turn numbering continues across seeded sessions', () => {
   it('a forked agent continues turn numbers after the seed log', async () => {
     const first = new MockAdapter([textResponse('turn one')])
     const ctx = await harness(first)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
     send(agent, 'first')
     await waitForIdle(ctx, agent)
 
@@ -548,7 +904,9 @@ describe('turn numbering continues across seeded sessions', () => {
     ctx2.llm.registerAdapter(['mock'], second)
 
     const seeded = ctx2.sessions.create(SessionId('forked'), { seed: [...agent.session.events] })
-    const prepared = prepareReactLoopAgent(ctx2, AgentId('forked-agent'), { model: 'mock' }, seeded)
+    const prepared = prepareReactLoopAgent(
+      ctx2, SessionId('forked-agent'), { provider: 'mock', model: 'mock' }, seeded, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
+    )
     const forked = prepared.agent
     prepared.markPublished()
     ctx2.effect(() => prepared.startDriver())
@@ -592,7 +950,7 @@ describe('a finish-error stream chunk ends the turn as error, not completed', ()
     ]
     const adapter = new MockAdapter([errorStream])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a-finish-error'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a-finish-error'), { provider: 'mock', model: 'mock' })
 
     const reasons: TurnEndReason[] = []
     ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
@@ -617,7 +975,7 @@ describe('a finish-error stream chunk ends the turn as error, not completed', ()
     ]
     const adapter = new MockAdapter([abortedStream])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a-finish-aborted'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a-finish-aborted'), { provider: 'mock', model: 'mock' })
 
     const reasons: TurnEndReason[] = []
     ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
@@ -635,7 +993,7 @@ describe('a finish-error stream chunk ends the turn as error, not completed', ()
     ]
     const adapter = new MockAdapter([errorStream])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a-finish-error-nocode'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a-finish-error-nocode'), { provider: 'mock', model: 'mock' })
 
     const reasons: TurnEndReason[] = []
     ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
@@ -651,7 +1009,7 @@ describe('step boundary publication order', () => {
   it('the step/start event is in session.events when its session/event listener fires', async () => {
     const adapter = new MockAdapter([textResponse('done')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a-step-order'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a-step-order'), { provider: 'mock', model: 'mock' })
 
     // Append commits before observers run.
     const observed: { turn: number; step: number; lastEventType: string | undefined; sawStepStart: boolean }[] = []
@@ -691,7 +1049,7 @@ describe('turn and step boundary recovery', () => {
   }
 
   /** Count turn/step boundary events for balance assertions. */
-  function boundaryCounts(agent: ReactLoopAgent) {
+  function boundaryCounts(agent: Agent) {
     const e = [...agent.session.events]
     return {
       turnStart: e.filter(x => x.type === 'turn/start').length,
@@ -706,7 +1064,7 @@ describe('turn and step boundary recovery', () => {
   it('a throwing step/start observer cannot change a successful turn', async () => {
     const adapter = new MockAdapter([textResponse('request completed')])
     const ctx = await balancedHarness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a-stepstart'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a-stepstart'), { provider: 'mock', model: 'mock' })
 
     // Session owns post-commit containment. The loop sees a successful append,
     // runs the request, and balances the ordinary step and turn boundaries.
@@ -735,7 +1093,7 @@ describe('turn and step boundary recovery', () => {
   it('a pre-commit step/start validation failure does not invent a step boundary', async () => {
     const adapter = new MockAdapter([textResponse('never reached')])
     const ctx = await balancedHarness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a-stepstart-veto'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a-stepstart-veto'), { provider: 'mock', model: 'mock' })
     let rejected = false
     ctx.on('internal/dispatch', (_mode, name, args) => {
       if (name !== 'session/event') return
@@ -766,7 +1124,7 @@ describe('turn and step boundary recovery', () => {
     const errorStream: StreamChunk[] = [{ type: 'finish', reason: { kind: 'error', message: 'provider failed' } }]
     const adapter = new MockAdapter([errorStream])
     const ctx = await balancedHarness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a-turnend-veto'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a-turnend-veto'), { provider: 'mock', model: 'mock' })
     let rejected = false
     ctx.on('internal/dispatch', (_mode, name, args) => {
       if (name !== 'session/event') return
@@ -800,7 +1158,7 @@ describe('turn and step boundary recovery', () => {
   it('a one-shot step/end validation failure keeps the step open until retry succeeds', async () => {
     const adapter = new MockAdapter([textResponse('completed before close validation')])
     const ctx = await balancedHarness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a-stepend-veto'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a-stepend-veto'), { provider: 'mock', model: 'mock' })
     let rejected = false
     ctx.on('internal/dispatch', (_mode, name, args) => {
       if (name !== 'session/event') return
@@ -832,7 +1190,7 @@ describe('turn and step boundary recovery', () => {
     const errorStream: StreamChunk[] = [{ type: 'finish', reason: { kind: 'error', message: 'provider 500' } }]
     const adapter = new MockAdapter([errorStream, textResponse('turn 2 ok')])
     const ctx = await balancedHarness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a-errorlistener'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a-errorlistener'), { provider: 'mock', model: 'mock' })
 
     let threw = false
     ctx.on('agent/error', () => { if (!threw) { threw = true; throw new Error('boom error-listener') } })
@@ -863,9 +1221,9 @@ describe('turn and step boundary recovery', () => {
     // balanced with reason disposed (no error event for a disposal).
     const adapter = new MockAdapter(['hang'])
     const ctx = await balancedHarness(adapter)
-    let agent!: ReactLoopAgent
+    let agent!: Agent
     const fiber = await ctx.plugin(Object.assign((inner: Context) => {
-      agent = inner.agentLoop.create(AgentId('a-dispose'), { model: 'mock' })
+      agent = inner.agentLoop.create(SessionId('a-dispose'), { provider: 'mock', model: 'mock' })
     }, { inject: ['agentLoop'] }))
 
     const reasons: TurnEndReason[] = []
@@ -874,7 +1232,7 @@ describe('turn and step boundary recovery', () => {
     send(agent, 'go')
     await new Promise(r => setTimeout(r, 30))
     await fiber.dispose() // dispose during the hanging step
-    await agent.done
+    await driverDone(agent)
 
     const e = [...agent.session.events]
     const turnStarts = e.filter(x => x.type === 'turn/start').length
@@ -890,9 +1248,9 @@ describe('turn and step boundary recovery', () => {
     // Disposal remains authoritative when the listener also throws.
     const adapter = new MockAdapter([textResponse('never reached')])
     const ctx = await balancedHarness(adapter)
-    let agent!: ReactLoopAgent
+    let agent!: Agent
     const fiber = await ctx.plugin(Object.assign((inner: Context) => {
-      agent = inner.agentLoop.create(AgentId('a-prestep-dispose-throw'), { model: 'mock' })
+      agent = inner.agentLoop.create(SessionId('a-prestep-dispose-throw'), { provider: 'mock', model: 'mock' })
     }, { inject: ['agentLoop'] }))
 
     let threw = false
@@ -906,7 +1264,7 @@ describe('turn and step boundary recovery', () => {
     ctx.on('agent/error', (_a, _t, _s, error) => void errorEmits.push(error))
 
     send(agent, 'go')
-    await agent.done
+    await driverDone(agent)
 
     const e = [...agent.session.events]
     // Balanced: one turn/start, one turn/end carrying disposed (NOT error).
@@ -923,7 +1281,7 @@ describe('turn and step boundary recovery', () => {
   it('a throwing turn/start observer cannot starve the loop or later turns', async () => {
     const adapter = new MockAdapter([textResponse('turn 1'), textResponse('turn 2')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a-preturn'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a-preturn'), { provider: 'mock', model: 'mock' })
 
     let threw = false
     ctx.on('session/event', (_session, event) => {
@@ -954,7 +1312,7 @@ describe('turn and step boundary recovery', () => {
   it('a throwing step/end observer cannot rewrite the turn outcome', async () => {
     const adapter = new MockAdapter([textResponse('all good'), textResponse('turn 2 ok')])
     const ctx = await balancedHarness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a-stepend-throw'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a-stepend-throw'), { provider: 'mock', model: 'mock' })
 
     let threw = false
     ctx.on('session/event', (_s, event) => {
@@ -993,7 +1351,7 @@ describe('turn and step boundary recovery', () => {
     const errorStream: StreamChunk[] = [{ type: 'finish', reason: { kind: 'error', message: 'provider 500' } }]
     const adapter = new MockAdapter([errorStream, textResponse('turn 2 ok')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a-stependthrow'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a-stependthrow'), { provider: 'mock', model: 'mock' })
 
     let threw = false
     ctx.on('session/event', (_s, event) => {
@@ -1023,7 +1381,7 @@ describe('turn and step boundary recovery', () => {
     // boundary stays authoritative and the loop continues normally.
     const adapter = new MockAdapter([textResponse('turn 1'), textResponse('turn 2')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a-turnendappend'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a-turnendappend'), { provider: 'mock', model: 'mock' })
 
     let threw = false
     ctx.on('session/event', (_s, event) => {
@@ -1069,7 +1427,7 @@ describe('tool result call identity', () => {
       return Promise.resolve({ kind: 'accept', content: [{ type: 'text', text: 'ok' }] })
     }, { prepend: true })
 
-    const agent = ctx.agentLoop.create(AgentId('a-callid'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a-callid'), { provider: 'mock', model: 'mock' })
     send(agent, 'use tool')
     await waitForIdle(ctx, agent)
 
@@ -1093,13 +1451,14 @@ describe('tool result call identity', () => {
   })
 })
 
-describe('surface: assistant/message omits sourceEventSeqs when no chunks streamed', () => {
-  it('a step-result listener injecting content over an empty stream appends with surfaceOp but no sourceEventSeqs', async () => {
-    // Injected result content with no chunks must omit empty sourceEventSeqs.
+describe('surface: assistant/message records exact empty provenance when no chunks streamed', () => {
+  it('a step-result listener injecting content over an empty stream records sourceEventSeqs []', async () => {
+    // The explicit empty source set distinguishes a known empty provider
+    // stream from legacy events whose provenance was not recorded.
     const adapter = new MockAdapter([[]])
     const ctx = await harness(adapter)
     await ctx.plugin(Invariants)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     ctx.on('agent/step-result', async (_agent, _turn, _step, _message, _next) => ({
       role: 'assistant' as const,
@@ -1112,7 +1471,7 @@ describe('surface: assistant/message omits sourceEventSeqs when no chunks stream
     const recorded = agent.session.events.find(e => e.type === 'assistant/message')!
     expect(recorded.type).toBe('assistant/message')
     expect(recorded.surfaceOp).toBe('append')
-    expect(recorded.sourceEventSeqs).toBeUndefined()
+    expect(recorded.sourceEventSeqs).toEqual([])
     // The injected content reaches derived history.
     expect(JSON.stringify(agent.session.deriveMessages())).toContain('injected')
   })
@@ -1144,9 +1503,9 @@ describe('disposal and cancellation during pre-step assembly', () => {
       return next()
     })
 
-    let agent!: ReactLoopAgent
+    let agent!: Agent
     const fiber = await ctx.plugin(Object.assign((inner: Context) => {
-      agent = inner.agentLoop.create(AgentId('a-dispose-assemble'), { model: 'mock' })
+      agent = inner.agentLoop.create(SessionId('a-dispose-assemble'), { provider: 'mock', model: 'mock' })
     }, { inject: ['agentLoop'] }))
 
     const reasons: TurnEndReason[] = []
@@ -1161,7 +1520,7 @@ describe('disposal and cancellation during pre-step assembly', () => {
 
     releaseAssemble()
     await disposalDone
-    await agent.done
+    await driverDone(agent)
     unlisten()
 
     // Turn boundaries are durable rows; there is no `agent/*` mirror to assert.
@@ -1194,9 +1553,9 @@ describe('disposal and cancellation during pre-step assembly', () => {
       return next()
     })
 
-    let agent!: ReactLoopAgent
+    let agent!: Agent
     const fiber = await ctx.plugin(Object.assign((inner: Context) => {
-      agent = inner.agentLoop.create(AgentId('a-cancel-assemble'), { model: 'mock' })
+      agent = inner.agentLoop.create(SessionId('a-cancel-assemble'), { provider: 'mock', model: 'mock' })
     }, { inject: ['agentLoop'] }))
 
     const reasons: TurnEndReason[] = []
@@ -1209,7 +1568,7 @@ describe('disposal and cancellation during pre-step assembly', () => {
     releaseAssemble()
     await waitForIdle(ctx, agent)
     await fiber.dispose()
-    await agent.done
+    await driverDone(agent)
     unlisten()
 
     const e = [...agent.session.events]
@@ -1248,9 +1607,9 @@ describe('disposal and cancellation during pre-step assembly', () => {
       await blocker
     })
 
-    let agent!: ReactLoopAgent
+    let agent!: Agent
     const fiber = await ctx.plugin(Object.assign((inner: Context) => {
-      agent = inner.agentLoop.create(AgentId('a-dispose-prestep'), { model: 'mock' })
+      agent = inner.agentLoop.create(SessionId('a-dispose-prestep'), { provider: 'mock', model: 'mock' })
     }, { inject: ['agentLoop'] }))
 
     const reasons: TurnEndReason[] = []
@@ -1263,7 +1622,7 @@ describe('disposal and cancellation during pre-step assembly', () => {
     const disposalDone = fiber.dispose()
     releasePreStep()
     await disposalDone
-    await agent.done
+    await driverDone(agent)
 
     // After the pre-step seam finishes, the post-seam cancel/dispose check
     // catches disposal. The step was never opened, no LLM call was made.
@@ -1299,9 +1658,9 @@ describe('disposal and cancellation during pre-step assembly', () => {
       await blocker
     })
 
-    let agent!: ReactLoopAgent
+    let agent!: Agent
     const fiber = await ctx.plugin(Object.assign((inner: Context) => {
-      agent = inner.agentLoop.create(AgentId('a-cancel-prestep'), { model: 'mock' })
+      agent = inner.agentLoop.create(SessionId('a-cancel-prestep'), { provider: 'mock', model: 'mock' })
     }, { inject: ['agentLoop'] }))
 
     const reasons: TurnEndReason[] = []
@@ -1314,7 +1673,7 @@ describe('disposal and cancellation during pre-step assembly', () => {
     releasePreStep()
     await waitForIdle(ctx, agent)
     await fiber.dispose()
-    await agent.done
+    await driverDone(agent)
 
     const e = [...agent.session.events]
     expect(e.filter(x => x.type === 'turn/start')).toHaveLength(1)
@@ -1349,9 +1708,9 @@ describe('disposal and cancellation during pre-step assembly', () => {
       return next()
     })
 
-    let agent!: ReactLoopAgent
+    let agent!: Agent
     const fiber = await ctx.plugin(Object.assign((inner: Context) => {
-      agent = inner.agentLoop.create(AgentId('a-dispose-no-leak'), { model: 'mock' })
+      agent = inner.agentLoop.create(SessionId('a-dispose-no-leak'), { provider: 'mock', model: 'mock' })
     }, { inject: ['agentLoop'] }))
 
     send(agent, 'go')
@@ -1360,7 +1719,7 @@ describe('disposal and cancellation during pre-step assembly', () => {
     const disposalDone = fiber.dispose()
     releaseAssemble()
     await disposalDone
-    await agent.done
+    await driverDone(agent)
 
     const e = [...agent.session.events]
     expect(e.filter(x => x.type === 'turn/start')).toHaveLength(1)

packages/core/agent-loop/tests/coverage-edges.spec.ts

@@ -1,14 +1,19 @@
 import { describe, expect, it } from 'vitest'
 import { Context } from 'cordis'
 import LlmService, { CallId, LlmError, StreamChunk } from '@deepseek-ai/dsh-llm'
-import SessionStore, { TurnEndReason } from '@deepseek-ai/dsh-session'
+import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session'
 import type { SessionEvent } from '@deepseek-ai/dsh-session'
 import SystemPrompt 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 AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
+
+import AgentLoop from '@deepseek-ai/dsh-agent-loop'
 import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts'
 
+function driverDone(agent: Agent): Promise<void> {
+  return (agent as Agent & { done: Promise<void> }).done
+}
+
 async function harness(adapter: MockAdapter) {
   const ctx = new Context()
   await ctx.plugin(LlmService)
@@ -21,7 +26,7 @@ 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') {
@@ -32,7 +37,7 @@ 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 }])
 }
 
@@ -40,7 +45,7 @@ describe('inbox acceptance', () => {
   it('rejects non-serializable content or source synchronously before notification or enqueue', async () => {
     const adapter = new MockAdapter([textResponse('turn 1')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
     let queued = 0
     ctx.on('agent/queued', () => { queued += 1 })
 
@@ -80,7 +85,7 @@ describe('tool JSON parse', () => {
         return [{ type: 'text', text: typeof args === 'string' ? `raw: ${args}` : JSON.stringify(args) }]
       },
     }))
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     send(agent, 'use tool')
     await waitForIdle(ctx, agent)
@@ -113,7 +118,7 @@ describe('tool JSON parse', () => {
         return [{ type: 'text', text: 'ran with empty args' }]
       },
     }))
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     send(agent, 'use tool')
     await waitForIdle(ctx, agent)
@@ -126,7 +131,7 @@ describe('toError normalization', () => {
   it('normalizes non-Error throws from pre-commit dispatch validation via the runLoop backstop', async () => {
     const adapter = new MockAdapter([textResponse('ok')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     let threwOnce = false
     ctx.on('internal/dispatch', (_mode, name, args) => {
@@ -162,7 +167,7 @@ describe('toError normalization', () => {
   it('normalizes non-Error throws from agent/request waterfall via inline toError in runStep catch', async () => {
     const adapter = new MockAdapter([textResponse('irrelevant')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     let threwOnce = false
     ctx.on('agent/request', async (_agent, _turn, _step, _options, _next) => {
@@ -190,7 +195,7 @@ describe('coded error data emission', () => {
   it('errorData includes code when a coded error (LlmError) is thrown from a plugin', async () => {
     const adapter = new MockAdapter([textResponse('turn 1')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     let threwOnce = false
     ctx.on('agent/request', async (_agent, _turn, _step, _options, next) => {
@@ -222,9 +227,9 @@ describe('disposed vs aborted branching', () => {
   it('handles dispose during model streaming producing reason "disposed"', async () => {
     const adapter = new MockAdapter(['hang'])
     const ctx = await harness(adapter)
-    let agent!: ReactLoopAgent
+    let agent!: Agent
     const fiber = await ctx.plugin(Object.assign((inner: Context) => {
-      agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' })
+      agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', model: 'mock' })
     }, { inject: ['agentLoop'] }))
 
     const reasons: TurnEndReason[] = []
@@ -233,14 +238,14 @@ describe('disposed vs aborted branching', () => {
     send(agent, 'go')
     await new Promise(r => setTimeout(r, 30))
     await fiber.dispose() // dispose during hang
-    await agent.done
+    await driverDone(agent)
 
     // Disposal wins abort classification because the error path checks it first.
     expect(reasons).toContainEqual({ kind: 'disposed' })
   })
 })
 
-describe('structured tool error propagation (the runtime-validation RFC, part 2)', () => {
+describe('structured tool error propagation (the runtime-validation Agent Note, part 2)', () => {
   it('forwards a tool HarnessError onto the tool/result session event', async () => {
     const { HarnessError } = await import('@deepseek-ai/dsh-llm')
     // First model turn calls the tool; second turn (after the tool result is
@@ -250,7 +255,7 @@ describe('structured tool error propagation (the runtime-validation RFC, part 2)
       textResponse('done'),
     ])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
     ctx.tools.register(defineTool({
       name: 'boom',
       description: 'always fails',

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

@@ -1,16 +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 AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
+import AgentRegistry, { type Agent, type ContinuationDecision, type PromptDecision, type SessionStartSource } from '@deepseek-ai/dsh-agent'
+
+import AgentLoop from '@deepseek-ai/dsh-agent-loop'
 import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts'
 
 /**
@@ -34,7 +30,7 @@ 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') {
@@ -45,11 +41,11 @@ 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]
 }
 
@@ -57,7 +53,7 @@ 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'), { 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) => {
@@ -76,7 +72,7 @@ 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'), { 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' }] }))
@@ -94,7 +90,7 @@ 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'), { 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> =>
@@ -119,17 +115,14 @@ describe('agent/prompt-submit', () => {
     expect(ctxMsg?.type === 'context/message' && ctxMsg.data.source).toEqual({ kind: 'plugin', plugin: 'test' })
     expect(ctxMsg?.type === 'context/message' && ctxMsg.data.envelope).toBe('raw')
     expect(ctxMsg?.type === 'context/message' && ctxMsg.data.meta).toEqual(meta)
-    // both the prompt and the injected context reach the model
     const sent = JSON.stringify(adapter.requests[0]!.messages)
     expect(sent).toContain('extra ctx')
   })
 
-  it('a prompt-submit rewrite + additionalContexts is VISIBLE to the agent/pre-step seam (merged ordering)', async () => {
-    // Prompt rewrites and injected context land before `agent/pre-step`, so a
-    // compaction listener measures the current surface before the single derive.
+  it('runs pre-step after prompt rewrites and injected context become durable', async () => {
     const adapter = new MockAdapter([textResponse('ok')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     ctx.on('agent/prompt-submit', async (): Promise<PromptDecision> =>
       ({
@@ -138,8 +131,6 @@ describe('agent/prompt-submit', () => {
         additionalContexts: [{ content: [{ type: 'text', text: 'injected ctx' }], source: { kind: 'plugin', plugin: 'test' } }],
       }))
 
-    // The pre-step seam (where compaction lives) derives the surface it would act
-    // on. Capture what it sees on the first step.
     let preStepDerived: string | undefined
     ctx.on('agent/pre-step', (subject, _turn, step) => {
       if (subject === agent && step === 1) preStepDerived = JSON.stringify(subject.session.deriveMessages())
@@ -148,8 +139,6 @@ describe('agent/prompt-submit', () => {
     send(agent, 'ORIGINAL prompt')
     await waitForIdle(ctx, agent)
 
-    // The pre-step seam ran and saw BOTH the rewrite (not the original) and the
-    // injected context — i.e. the prompt-submit effects landed before it.
     expect(preStepDerived).toBeDefined()
     expect(preStepDerived).toContain('REWRITTEN prompt')
     expect(preStepDerived).toContain('injected ctx')
@@ -159,7 +148,7 @@ 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'), { 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' }))
@@ -193,7 +182,7 @@ describe('agent/prompt-submit', () => {
   it('adjacent blocked and allowed prompts keep independent turn outcomes', async () => {
     const adapter = new MockAdapter([textResponse('ran once')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { 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('')
@@ -231,7 +220,7 @@ describe('agent/prompt-submit', () => {
   it('a throwing prompt-submit listener ends its turn balanced while an adjacent message survives', async () => {
     const adapter = new MockAdapter([textResponse('after')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     let threw = false
     ctx.on('agent/prompt-submit', async () => {
@@ -275,7 +264,7 @@ 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'), { 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)
@@ -294,7 +283,7 @@ describe('agent/session-start', () => {
       agent.inject([{ type: 'text', text: 'session preamble' }], { source: { kind: 'plugin', plugin: 'test' } })
     })
 
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
     send(agent, 'go')
     await waitForIdle(ctx, agent)
 
@@ -312,8 +301,8 @@ 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'), { 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')
@@ -326,8 +315,8 @@ 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'), { model: 'mock' })
-    const agentB = ctx.agentLoop.create(AgentId('prefix-b'), { 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}`)
@@ -364,7 +353,7 @@ 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'), { 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
@@ -386,18 +375,18 @@ describe('agent/session-prefix', () => {
       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')
+    // header event: reuse means no changed snapshot ever.
+    const headerEvents = events(agent).filter(e => e.type === 'request/header')
     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 () => {
+  it('composes before the first pre-step and records the prefix on the request header', async () => {
     const adapter = new MockAdapter([textResponse('ok')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { 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[] = []
@@ -405,26 +394,21 @@ describe('agent/session-prefix', () => {
       order.push('compose')
       return [reminder, ...await next()]
     })
-    const seen: (readonly Message[])[] = []
-    ctx.on('agent/pre-step', (_agent, _turn, _step, _system, sessionPrefix) => {
+    ctx.on('agent/pre-step', () => {
       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])
+    expect(agent.session.requestHeader()?.messagePrefix).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' })
+    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
@@ -446,7 +430,7 @@ 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'), { 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())
@@ -462,7 +446,7 @@ 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'), { 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[]> => {
@@ -491,7 +475,7 @@ 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'), { 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 +487,7 @@ describe('agent/session-prefix', () => {
     // 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)
+    expect(events(agent).filter(e => e.type === 'request/header')).toHaveLength(1)
   })
 })
 
@@ -512,7 +496,7 @@ 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'), { 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> => {
@@ -544,7 +528,7 @@ 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'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     ctx.on('agent/turn-continuation', async (): Promise<ContinuationDecision> => ({ action: 'stop' }))
 
@@ -574,7 +558,7 @@ 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'), { 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> =>
@@ -622,7 +606,7 @@ describe('tool additionalContexts buffering across a step', () => {
         return [{ type: 'text', text: 'outer result' }]
       },
     }))
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     send(agent, 'go')
     await waitForIdle(ctx, agent)
@@ -649,7 +633,7 @@ 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'), { 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' }
@@ -711,7 +695,7 @@ 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'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     send(agent, 'please echo hi')
     await waitForIdle(ctx, agent)
@@ -734,7 +718,7 @@ 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'), { 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) })
@@ -753,7 +737,7 @@ 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'), { 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

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

@@ -4,10 +4,15 @@ import LlmService, { CallId, StreamChunk } from '@deepseek-ai/dsh-llm'
 import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session'
 import SystemPrompt 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 AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
+
+import AgentLoop from '@deepseek-ai/dsh-agent-loop'
 import { MockAdapter, maxTokensResponse, textResponse, toolCallResponse } from './mock-adapter.ts'
 
+function driverDone(agent: Agent): Promise<void> {
+  return (agent as Agent & { done: Promise<void> }).done
+}
+
 async function harness(adapter: MockAdapter, persona = '') {
   const ctx = new Context()
   await ctx.plugin(LlmService)
@@ -25,7 +30,7 @@ async function harness(adapter: MockAdapter, persona = '') {
  * invoke this right after send(), when the loop hasn't woken yet (status is
  * still 'idle' synchronously), so polling the current status would lie.
  */
-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') {
@@ -36,7 +41,7 @@ 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 }])
 }
 
@@ -44,7 +49,7 @@ describe('agent loop', () => {
   it('runs a simple turn: queued message → model → idle, with ordered events', async () => {
     const adapter = new MockAdapter([textResponse('hello there')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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
@@ -92,7 +97,7 @@ describe('agent loop', () => {
         return [{ type: 'text', text: `echo: ${args.text}` }]
       },
     }))
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     send(agent, 'use the tool')
     await waitForIdle(ctx, agent)
@@ -131,7 +136,7 @@ describe('agent loop', () => {
         return { content: [{ type: 'text', text: 'ok' }], meta: { diffs: [{ path: 'a.txt', oldText: null, newText: 'x' }] } }
       },
     }))
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     send(agent, 'use the tool')
     await waitForIdle(ctx, agent)
@@ -155,7 +160,7 @@ describe('agent loop', () => {
         return []
       },
     }))
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     send(agent, 'hi')
     await waitForIdle(ctx, agent)
@@ -169,13 +174,12 @@ describe('agent loop', () => {
     const adapter = new MockAdapter([textResponse('ok')])
     const ctx = await harness(adapter, 'Working in {{cwd}}.')
     const handle = await ctx.agents.create({
-      agentId: AgentId('a-cwd'),
       sessionId: SessionId('s-cwd'),
       meta: { cwd: '/work/space' },
-      agentOptions: { model: 'mock' },
+      agentOptions: { provider: 'mock', model: 'mock' },
     })
 
-    const agent = handle.agent as ReactLoopAgent
+    const agent = handle.agent
     send(agent, 'hi')
     await waitForIdle(ctx, agent)
 
@@ -188,7 +192,7 @@ describe('agent loop', () => {
     const ctx = await harness(adapter, 'In {{cwd}}.')
     const errors: Error[] = []
     ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error))
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     send(agent, 'hi')
     await waitForIdle(ctx, agent)
@@ -223,13 +227,14 @@ describe('agent loop', () => {
     const adapter = new MockAdapter([textResponse('ok')])
     const ctx = await harness(adapter, 'You run on {{model}}.')
     ctx.on('system-prompt/assemble', async (assembly, _context, next) => {
+      assembly.variables['provider'] = 'mock'
       assembly.variables['model'] = 'mock'
       return next()
     })
     ctx.on('agent/request', async (_agent, _turn, _step, config, _next) => {
-      return { ...config, model: 'mock' }
+      return { ...config, provider: 'mock', model: 'mock' }
     })
-    const agent = ctx.agentLoop.create(AgentId('a-late-model'), {})
+    const agent = ctx.agentLoop.create(SessionId('a-late-model'), {})
 
     send(agent, 'hi')
     await waitForIdle(ctx, agent)
@@ -255,7 +260,7 @@ describe('agent loop', () => {
       parameters: {},
       execute: () => Promise.resolve({ content: [{ type: 'text' as const, text: 'apparent success' }], meta }),
     }))
-    const agent = ctx.agentLoop.create(AgentId('bad-meta-agent'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('bad-meta-agent'), { provider: 'mock', model: 'mock' })
 
     send(agent, 'use the tool')
     await waitForIdle(ctx, agent)
@@ -284,7 +289,7 @@ describe('agent loop', () => {
     const adapter = new MockAdapter([textResponse('ok')])
     const ctx = await harness(adapter)
     ctx.on('system-prompt/assemble', async () => ({ sections: [], tools: [], variables: {} }))
-    const agent = ctx.agentLoop.create(AgentId('a-no-system'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a-no-system'), { provider: 'mock', model: 'mock' })
 
     send(agent, 'hi')
     await waitForIdle(ctx, agent)
@@ -296,7 +301,7 @@ describe('agent loop', () => {
   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 agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     send(agent, 'hi')
     await waitForIdle(ctx, agent)
@@ -320,7 +325,7 @@ describe('agent loop', () => {
     ])
     const ctx = await harness(adapter)
 
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
     ctx.tools.register(defineTool({
       name: 'slow',
       description: '',
@@ -352,7 +357,7 @@ describe('agent loop', () => {
   it('same-tick idle steering inherits one-send-one-turn FIFO behavior', async () => {
     const adapter = new MockAdapter([textResponse('first'), textResponse('second')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     const idle = waitForIdle(ctx, agent)
     agent.steer([{ type: 'text', text: 'first idle steer' }])
@@ -372,7 +377,7 @@ describe('agent loop', () => {
   it('inject() while idle wraps context in a one-shot turn, visible to the next request', async () => {
     const adapter = new MockAdapter([textResponse('ok')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     agent.inject([{ type: 'text', text: 'file changed: a.ts' }], { source: { kind: 'plugin', plugin: 'watcher' } })
     // The idle inject records a self-contained turn (turn/start → context/message
@@ -396,7 +401,7 @@ describe('agent loop', () => {
   it('inject() can persist raw structured context without the generic context envelope', async () => {
     const adapter = new MockAdapter([textResponse('ok')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('raw-context'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('raw-context'), { provider: 'mock', model: 'mock' })
     const text = '<system-reminder>Additional instructions from: pkg/AGENTS.md</system-reminder>'
     const meta = {
       kind: 'workspace-instructions',
@@ -419,22 +424,30 @@ describe('agent loop', () => {
     expect(requestText).not.toContain('<context source=')
   })
 
-  it('inject() while running appends into the open turn (no extra synthetic turn)', async () => {
+  it('defers inject() during tool execution until after the tool result', async () => {
     const adapter = new MockAdapter([
       toolCallResponse('c1', 'noticer', {}, 'calling'),
       textResponse('done'),
     ])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
-    // A tool that injects mid-execution: at this point the agent is running, so
-    // inject must append the context/message into the ALREADY-open turn rather
-    // than wrap it in its own one-shot turn.
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
+    let visibleDuringTool = false
+    const meta = { kind: 'deferred-test', version: 1 }
     ctx.tools.register(defineTool({
       name: 'noticer',
       description: 'injects a notice',
       parameters: {},
       async execute() {
-        agent.inject([{ type: 'text', text: 'mid-turn notice' }], { source: { kind: 'plugin', plugin: 'x' } })
+        await Promise.resolve()
+        const first = { type: 'text' as const, text: 'mid-turn notice' }
+        agent.inject([first], {
+          source: { kind: 'plugin', plugin: 'x' },
+          envelope: 'raw',
+          meta,
+        })
+        first.text = 'mutated after inject'
+        agent.inject([{ type: 'text', text: 'second notice' }], { source: { kind: 'plugin', plugin: 'x' } })
+        visibleDuringTool = agent.session.events.some(e => e.type === 'context/message')
         return [{ type: 'text', text: 'ok' }]
       },
     }))
@@ -442,13 +455,67 @@ describe('agent loop', () => {
     send(agent, 'go')
     await waitForIdle(ctx, agent)
 
-    // Exactly ONE turn ran (no synthetic injection turn), and the mid-turn
-    // context/message sits inside it.
+    expect(visibleDuringTool).toBe(false)
+
+    // The injection stays in the open turn, but its user-role context cannot
+    // split the assistant tool call from the provider's tool-result message.
     const turnStarts = agent.session.events.filter(e => e.type === 'turn/start')
     expect(turnStarts).toHaveLength(1)
     const ts0 = turnStarts[0]!
     expect(ts0.type === 'turn/start' && ts0.data.trigger.kind).toBe('message')
-    expect(agent.session.events.some(e => e.type === 'context/message')).toBe(true)
+    const result = agent.session.events.find(e => e.type === 'tool/result')!
+    const contexts = agent.session.events.filter(e => e.type === 'context/message')
+    expect(contexts).toHaveLength(2)
+    expect(result.seq).toBeLessThan(contexts[0]!.seq)
+    expect(contexts[0]?.type === 'context/message' && contexts[0].data).toMatchObject({
+      envelope: 'raw',
+      meta,
+    })
+    expect(contexts.flatMap(event => event.type === 'context/message' ? event.data.content : []))
+      .toEqual([
+        { type: 'text', text: 'mid-turn notice' },
+        { type: 'text', text: 'second notice' },
+      ])
+
+    const secondRequest = adapter.requests[1]!.messages
+    const resultIndex = secondRequest.findIndex(message =>
+      message.content.some(block => block.type === 'tool-result'))
+    const contextIndexes = secondRequest.flatMap((message, index) =>
+      message.content.some(block => block.type === 'text'
+        && (block.text.includes('mid-turn notice') || block.text.includes('second notice')))
+        ? [index]
+        : [])
+    expect(resultIndex).toBeGreaterThanOrEqual(0)
+    expect(contextIndexes).toHaveLength(2)
+    expect(contextIndexes.every(index => index > resultIndex)).toBe(true)
+  })
+
+  it('rejects non-JSON context before it enters the active tool-batch FIFO', async () => {
+    const adapter = new MockAdapter([
+      toolCallResponse('c1', 'invalid-injector', {}, 'calling'),
+      textResponse('done'),
+    ])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(SessionId('invalid-context'), { provider: 'mock', model: 'mock' })
+    ctx.tools.register(defineTool({
+      name: 'invalid-injector',
+      description: 'attempts an invalid context injection',
+      parameters: {},
+      async execute() {
+        expect(() => {
+          agent.inject([{ type: 'text', text: 'invalid' }], {
+            source: { kind: 'plugin', plugin: 'test' },
+            meta: { bigint: 1n } as never,
+          })
+        }).toThrow('agent context must be losslessly JSON-serializable')
+        return [{ type: 'text', text: 'rejected invalid context' }]
+      },
+    }))
+
+    send(agent, 'go')
+    await waitForIdle(ctx, agent)
+
+    expect(agent.session.events.some(event => event.type === 'context/message')).toBe(false)
   })
 
   it('agent/turn-continuation can force-continue (/loop pattern) and force-stop', async () => {
@@ -459,7 +526,7 @@ describe('agent loop', () => {
       textResponse('step 3'),
     ])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     let steps = 0
     ctx.on('session/event', (_session, event) => { if (event.type === 'step/end') steps++ })
@@ -485,7 +552,7 @@ describe('agent loop', () => {
         return [{ type: 'text', text: String(args.text) }]
       },
     }))
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     ctx.on('agent/turn-continuation', async () => ({ action: 'stop' }) as const)
 
@@ -500,8 +567,7 @@ describe('agent loop', () => {
   it('agent/request waterfall switches models by returning a replacement config; the switch is logged', async () => {
     const adapter = new MockAdapter([textResponse('ok')])
     const ctx = await harness(adapter)
-    ctx.llm.registerAdapter(['other-model'], adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     ctx.on('agent/request', async (_agent, _turn, _step, config, _next) => {
       // The seed is frozen — config is not a mutable per-call knob; a switch
@@ -521,10 +587,6 @@ describe('agent loop', () => {
   })
 
   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'),
@@ -534,23 +596,21 @@ describe('agent loop', () => {
       name: 'echo', description: 'echo', parameters: {},
       async execute() { return [{ type: 'text', text: 'echoed' }] },
     }))
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', 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 })
+    const fires: { turn: number; step: number; signal: AbortSignal }[] = []
+    ctx.on('agent/pre-step', (subject, turn, step, signal) => {
+      if (subject === agent) fires.push({ turn, step, signal })
     })
 
     send(agent, 'go')
     await waitForIdle(ctx, agent)
 
-    // One fire per step, in order, each with the assembled system prompt
-    // (here just the loop's own harness-identity section — no persona set).
-    const HARNESS = 'You are an AI agent powered by the DeepSeek Harness SDK.'
-    expect(fires).toEqual([
-      { turn: 1, step: 1, fullSystemPrompt: HARNESS },
-      { turn: 1, step: 2, fullSystemPrompt: HARNESS },
+    expect(fires.map(({ turn, step }) => ({ turn, step }))).toEqual([
+      { turn: 1, step: 1 },
+      { turn: 1, step: 2 },
     ])
+    expect(fires.every(({ signal }) => signal instanceof AbortSignal)).toBe(true)
   })
 
   it('agent/pre-step fires BEFORE the step it precedes opens (events land outside the step)', async () => {
@@ -558,7 +618,7 @@ describe('agent loop', () => {
     // same step's request must include it.
     const adapter = new MockAdapter([textResponse('ok')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     let injected = false
     ctx.on('agent/pre-step', (subject) => {
@@ -592,7 +652,7 @@ describe('agent loop', () => {
     // closing, the turn records error, and the loop remains available.
     const adapter = new MockAdapter([textResponse('second turn ok')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     let throwOnce = true
     ctx.on('agent/pre-step', () => {
@@ -626,7 +686,7 @@ describe('agent loop', () => {
   it('cancel() mid-stream ends the turn with reason aborted', async () => {
     const adapter = new MockAdapter(['hang'])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     const reasons: TurnEndReason[] = []
     ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
@@ -646,7 +706,7 @@ describe('agent loop', () => {
     // turn stops by default and ends max-tokens, not completed.
     const adapter = new MockAdapter([maxTokensResponse('truncat')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     const reasons: TurnEndReason[] = []
     ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
@@ -669,7 +729,7 @@ describe('agent loop', () => {
       textResponse('second half'),
     ])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     let steps = 0
     ctx.on('session/event', (_session, event) => { if (event.type === 'step/end') steps++ })
@@ -690,7 +750,7 @@ describe('agent loop', () => {
     expect(adapter.requests).toHaveLength(2)
     expect(adapter.requests[1]!.messages).toEqual([
       { role: 'user', content: [{ type: 'text', text: 'go' }] },
-      { role: 'assistant', content: [{ type: 'text', text: 'first half' }] },
+      { role: 'assistant', content: [{ type: 'text', text: 'first half' }], provenance: { provider: 'mock', model: 'mock' } },
     ])
     expect(reasons).toEqual([{ kind: 'max-tokens' }])
   })
@@ -700,7 +760,7 @@ describe('agent loop', () => {
     // stop. The per-turn reason must be independent — turn 2 ends completed.
     const adapter = new MockAdapter([maxTokensResponse('cut'), textResponse('clean')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     const reasons: TurnEndReason[] = []
     ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
@@ -733,7 +793,7 @@ describe('agent loop', () => {
         return [{ type: 'text', text: 'should not run' }]
       },
     }))
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     const reasons: TurnEndReason[] = []
     ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
@@ -749,14 +809,13 @@ describe('agent loop', () => {
     // skips that host so it does not create a spurious assistant turn.
     const assistantMessage = agent.session.events.find(e => e.type === 'assistant/message')
     expect(assistantMessage?.type === 'assistant/message' && assistantMessage.data).toEqual({
-      turn: 1, step: 1, content: [], usage: { inputTokens: 10, outputTokens: 5 },
+      turn: 1, step: 1, content: [], provenance: { provider: 'mock', model: 'mock' }, usage: { inputTokens: 10, outputTokens: 5 },
     })
   })
 
-  it('appends no assistant/message for a max-tokens step with empty content and no usage', async () => {
-    // A max-tokens step truncated to a dropped tool call AND with no usage chunk has nothing to
-    // record: empty content and no accounting → no assistant/message (the empty-content host
-    // exists only to carry usage).
+  it('appends an empty completion anchor for a max-tokens step with no usage', async () => {
+    // The truncated tool call is dropped from durable content, while the
+    // successful provider call still needs an exact replay anchor.
     const callId = CallId('c1')
     const adapter = new MockAdapter([[
       { type: 'block-start', index: 0, blockType: 'tool-call' },
@@ -771,7 +830,7 @@ describe('agent loop', () => {
       parameters: { text: { type: 'string' } },
       async execute() { return [{ type: 'text', text: 'should not run' }] },
     }))
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     const reasons: TurnEndReason[] = []
     ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
@@ -780,17 +839,23 @@ describe('agent loop', () => {
     await waitForIdle(ctx, agent)
 
     expect(reasons).toEqual([{ kind: 'max-tokens' }])
-    expect(agent.session.events.some(e => e.type === 'assistant/message')).toBe(false)
+    const assistant = agent.session.events.find(e => e.type === 'assistant/message')!
+    expect(assistant.type === 'assistant/message' && assistant.data).toEqual({
+      turn: 1,
+      step: 1,
+      content: [],
+      provenance: { provider: 'mock', model: 'mock' },
+    })
+    expect(assistant.sourceEventSeqs?.length).toBeGreaterThan(0)
     expect(agent.session.deriveMessages()).toEqual([{ role: 'user', content: [{ type: 'text', text: 'go' }] }])
   })
 
-  it('appends no assistant/message for a normal stop finish with empty content and no usage', async () => {
-    // A clean `stop` finish that streamed nothing assembled (no blocks) and
-    // carried no usage chunk has nothing to record: the content-or-usage guard
-    // on the normal step path suppresses a pure trace-only empty assistant/message.
+  it('appends an empty completion anchor for a normal stop with no usage', async () => {
+    // A clean content-less call stays absent from derived messages but remains
+    // a durable successful-call boundary for replay consumers.
     const adapter = new MockAdapter([[{ type: 'finish', reason: { kind: 'stop' } }]])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     const reasons: TurnEndReason[] = []
     ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
@@ -799,7 +864,14 @@ describe('agent loop', () => {
     await waitForIdle(ctx, agent)
 
     expect(reasons).toEqual([{ kind: 'completed' }])
-    expect(agent.session.events.some(e => e.type === 'assistant/message')).toBe(false)
+    const assistant = agent.session.events.find(e => e.type === 'assistant/message')!
+    expect(assistant.type === 'assistant/message' && assistant.data).toEqual({
+      turn: 1,
+      step: 1,
+      content: [],
+      provenance: { provider: 'mock', model: 'mock' },
+    })
+    expect(assistant.sourceEventSeqs?.length).toBe(1)
     expect(agent.session.deriveMessages()).toEqual([{ role: 'user', content: [{ type: 'text', text: 'go' }] }])
   })
 
@@ -820,7 +892,7 @@ describe('agent loop', () => {
       expect(message.content).toEqual([{ type: 'text', text: 'partial text' }])
       return next()
     })
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     send(agent, 'go')
     await waitForIdle(ctx, agent)
@@ -829,7 +901,7 @@ describe('agent loop', () => {
     expect(agent.session.events.some(e => e.type === 'tool/call')).toBe(false)
     expect(agent.session.deriveMessages()).toEqual([
       { role: 'user', content: [{ type: 'text', text: 'go' }] },
-      { role: 'assistant', content: [{ type: 'text', text: 'partial text' }] },
+      { role: 'assistant', content: [{ type: 'text', text: 'partial text' }], provenance: { provider: 'mock', model: 'mock' } },
     ])
   })
 
@@ -847,7 +919,7 @@ describe('agent loop', () => {
         return [{ type: 'text', text: String(args.text) }]
       },
     }))
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
     let threw = false
     // Post-commit session observers cannot control the loop. The tool call still
     // drives the second model request, and the turn completes normally.
@@ -866,7 +938,7 @@ describe('agent loop', () => {
   it('keeps same-tick sends in separate turns and checkpoints before the next starts', async () => {
     const adapter = new MockAdapter([textResponse('first answer'), textResponse('second answer')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     const firstFlush = Promise.withResolvers<undefined>()
     const releaseFirstFlush = Promise.withResolvers<undefined>()
@@ -906,7 +978,7 @@ describe('agent loop', () => {
   it('holds a turn-end listener send behind the closing turn checkpoint', async () => {
     const adapter = new MockAdapter([textResponse('first answer'), textResponse('second answer')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     const firstFlush = Promise.withResolvers<undefined>()
     const releaseFirstFlush = Promise.withResolvers<undefined>()
@@ -951,7 +1023,7 @@ describe('agent loop', () => {
   it('keeps a reentrant agent/queued send as the next independent turn', async () => {
     const adapter = new MockAdapter([textResponse('first'), textResponse('second')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     let nested = false
     ctx.on('agent/queued', (subject) => {
@@ -978,7 +1050,7 @@ describe('agent loop', () => {
   it('preserves independent turn sources across an adjacent microtask send', async () => {
     const adapter = new MockAdapter([textResponse('first'), textResponse('second')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     const idle = waitForIdle(ctx, agent)
     agent.send([{ type: 'text', text: 'user message' }])
@@ -1008,7 +1080,7 @@ describe('agent loop', () => {
   it('keeps a session-listener send after dequeue in the following turn', async () => {
     const adapter = new MockAdapter([textResponse('first'), textResponse('second')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     const turns: number[] = []
     ctx.on('session/event', (_s, event) => { if (event.type === 'turn/start') turns.push(event.data.turn) })
@@ -1033,7 +1105,7 @@ describe('agent loop', () => {
   })
 
   it('keeps a model-adapter callback send in the following turn', async () => {
-    const agentRef: { current?: ReactLoopAgent } = {}
+    const agentRef: { current?: Agent } = {}
     const adapter = new MockAdapter([
       () => {
         const agent = agentRef.current
@@ -1044,7 +1116,7 @@ describe('agent loop', () => {
       textResponse('second'),
     ])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
     agentRef.current = agent
 
     const idle = waitForIdle(ctx, agent)
@@ -1064,7 +1136,7 @@ describe('agent loop', () => {
   it('awaits session/flush at turn end (persistence checkpoint)', async () => {
     const adapter = new MockAdapter([textResponse('ok')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     let flushed = 0
     let flushedBeforeIdle = false
@@ -1084,7 +1156,7 @@ describe('agent loop', () => {
   it('errors from the model surface as agent/error and end the turn', async () => {
     const adapter = new MockAdapter([]) // script exhausted → throws
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     const errors: Error[] = []
     const reasons: TurnEndReason[] = []
@@ -1107,21 +1179,21 @@ describe('agent loop', () => {
     const adapter = new MockAdapter(['hang'])
     const ctx = await harness(adapter)
 
-    let agent!: ReactLoopAgent
+    let agent!: Agent
     const fiber = await ctx.plugin(Object.assign((inner: Context) => {
-      agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' })
+      agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', model: 'mock' })
     }, { inject: ['agentLoop'] }))
 
-    expect(ctx.agents.get(AgentId('scoped'))).toBe(agent)
+    expect(ctx.agents.get(SessionId('scoped'))).toBe(agent)
     send(agent, 'go')
     await new Promise(r => setTimeout(r, 30))
     expect(agent.status).toBe('running')
 
     await fiber.dispose()
-    await agent.done
+    await driverDone(agent)
 
     expect(agent.status).toBe('disposed')
-    expect(ctx.agents.get(AgentId('scoped'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('scoped'))).toBeUndefined()
     expect(() => { send(agent, 'too late') }).toThrow('disposed')
   })
 
@@ -1134,13 +1206,14 @@ describe('agent loop', () => {
     await ctx.plugin(ToolRegistry)
     await ctx.plugin(AgentRegistry)
     await ctx.plugin(AgentLoop, {
-      agents: [{ id: AgentId('config-agent'), model: 'mock' }],
+      agents: [{ id: SessionId('config-agent'), provider: 'mock', model: 'mock' }],
     })
     ctx.llm.registerAdapter(['mock'], adapter)
 
-    const agent = ctx.agents.get(AgentId('config-agent'))! as ReactLoopAgent
+    const agent = ctx.agents.list()[0]!
     expect(agent).toBeDefined()
-    expect(agent.id).toBe('config-agent')
+    expect(agent.id).toBe(agent.session.id)
+    expect(agent.id).toMatch(/^config-agent-session-/)
     expect(agent.options.model).toBe('mock')
 
     // the agent is alive: send triggers a turn
@@ -1157,10 +1230,10 @@ describe('agent loop', () => {
     await ctx.plugin(ToolRegistry)
     await ctx.plugin(AgentRegistry)
     await ctx.plugin(AgentLoop, {
-      agents: [{ id: AgentId('config-agent'), model: 'mock', cwd: '/work/project' }],
+      agents: [{ id: SessionId('config-agent'), provider: 'mock', model: 'mock', cwd: '/work/project' }],
     })
 
-    const agent = ctx.agents.get(AgentId('config-agent'))! as ReactLoopAgent
+    const agent = ctx.agents.list()[0]!
     expect(agent.session.header.cwd).toBe('/work/project')
   })
 
@@ -1178,7 +1251,7 @@ describe('agent loop', () => {
         return [{ type: 'text', text: String(args.text) }]
       },
     }))
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
     send(agent, 'run')
     await waitForIdle(ctx, agent)
 

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

@@ -1,7 +1,12 @@
 /**
- * Deterministic property tests for inbox scheduling: every sent message logs
- * once, turn numbers increase, and status follows idle→running→idle/disposed.
- * Schedules advance on status events rather than wall-clock sleeps.
+ * Property-based tests for the agent loop's inbox/turn scheduling (the
+ * property-testing Agent Note). Deterministic by construction: schedules are driven
+ * through the `agent/status` settle signal (no wall-clock sleeps), so a flake
+ * is a finding, not timing noise.
+ *
+ * Invariants: every sent message appears exactly once in the log (none lost);
+ * turn numbers strictly increase; status transitions follow the legal machine
+ * idle→running→idle (and →disposed at teardown).
  */
 
 import { describe, expect, it } from 'vitest'
@@ -9,11 +14,12 @@ import { Context } from 'cordis'
 import LlmService from '@deepseek-ai/dsh-llm'
 import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm'
 import { LlmAdapter } from '@deepseek-ai/dsh-llm'
-import SessionStore from '@deepseek-ai/dsh-session'
+import SessionStore, { SessionId } 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'
-import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
+import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
+
+import AgentLoop from '@deepseek-ai/dsh-agent-loop'
 import fc from 'fast-check'
 
 /** A never-exhausting adapter: every model call returns the same short reply. */
@@ -42,7 +48,7 @@ async function harness() {
 }
 
 /** Resolve on the agent's next transition to idle (event-based, not polled). */
-function nextIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
+function nextIdle(ctx: Context, agent: Agent): Promise<void> {
   return new Promise((resolve) => {
     const dispose = ctx.on('agent/status', (subject, status) => {
       if (subject === agent && status === 'idle') {
@@ -55,7 +61,7 @@ function nextIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
 
 /** Record every status transition for the legal-machine assertion. Returns
  * the seen list plus a disposer for the listener (per the registry convention). */
-function recordStatus(ctx: Context, agent: ReactLoopAgent): { seen: string[]; dispose: () => void } {
+function recordStatus(ctx: Context, agent: Agent): { seen: string[]; dispose: () => void } {
   const seen: string[] = []
   const dispose = ctx.on('agent/status', (subject, status) => {
     if (subject === agent) seen.push(status)
@@ -63,25 +69,25 @@ function recordStatus(ctx: Context, agent: ReactLoopAgent): { seen: string[]; di
   return { seen, dispose }
 }
 
-function userMessageTexts(agent: ReactLoopAgent): string[] {
+function userMessageTexts(agent: Agent): string[] {
   return agent.session.events
     .filter(e => e.type === 'user/message')
     .map(e => (e.data as { content: { type: string; text?: string }[] }).content.map(b => b.text ?? '').join(''))
 }
 
-function turnNumbers(agent: ReactLoopAgent): number[] {
+function turnNumbers(agent: Agent): number[] {
   return agent.session.events
     .filter(e => e.type === 'turn/start')
     .map(e => (e.data as { turn: number }).turn)
 }
 
-function turnEndNumbers(agent: ReactLoopAgent): number[] {
+function turnEndNumbers(agent: Agent): number[] {
   return agent.session.events
     .filter(e => e.type === 'turn/end')
     .map(e => (e.data as { turn: number }).turn)
 }
 
-function userMessageCountsByTurn(agent: ReactLoopAgent): number[] {
+function userMessageCountsByTurn(agent: Agent): number[] {
   const counts: number[] = []
   for (const event of agent.session.events) {
     if (event.type === 'turn/start') counts.push(0)
@@ -105,7 +111,7 @@ describe('agent loop scheduling properties', () => {
       async (texts) => {
         const ctx = await harness()
         try {
-          const agent = ctx.agentLoop.create(AgentId('a'), { model: 'mock' })
+          const agent = ctx.agentLoop.create(SessionId('a'), { provider: 'mock', model: 'mock' })
           const { seen: trace } = recordStatus(ctx, agent)
           const idle = nextIdle(ctx, agent)
           // Send all in one synchronous tick: they queue before the loop wakes.
@@ -133,7 +139,7 @@ describe('agent loop scheduling properties', () => {
       async (texts) => {
         const ctx = await harness()
         try {
-          const agent = ctx.agentLoop.create(AgentId('a'), { model: 'mock' })
+          const agent = ctx.agentLoop.create(SessionId('a'), { provider: 'mock', model: 'mock' })
           for (const text of texts) {
             const idle = nextIdle(ctx, agent)
             agent.send([{ type: 'text', text }])
@@ -158,7 +164,7 @@ describe('agent loop scheduling properties', () => {
       async (steps) => {
         const ctx = await harness()
         try {
-          const agent = ctx.agentLoop.create(AgentId('a'), { model: 'mock' })
+          const agent = ctx.agentLoop.create(SessionId('a'), { provider: 'mock', model: 'mock' })
           // Capture before each send; the last waiter covers the final turn, and
           // awaiting an already-settled earlier waiter is harmless.
           let lastIdle: Promise<void> | undefined

packages/core/agent-loop/tests/request-cache.e2e.ts

@@ -1,10 +1,11 @@
 import { afterEach, describe, expect, it } from 'vitest'
 import { Context } from 'cordis'
 import LlmService from '@deepseek-ai/dsh-llm'
-import SessionStore from '@deepseek-ai/dsh-session'
+import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
 import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
 import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
-import AgentRegistry, { AgentId, type Agent } from '@deepseek-ai/dsh-agent'
+import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
+
 import AgentLoop from '@deepseek-ai/dsh-agent-loop'
 import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
 
@@ -13,7 +14,7 @@ import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
  * multi-step tool turn (plus a follow-up turn) against the live DeepSeek API must report
  * `cacheReadTokens > 0` on every request after the first — the adapter maps the provider's
  * `prompt_cache_hit_tokens`, and the per-step usage recorded on `assistant/message` events is
- * the production observable for cache behavior (the reconstructability RFC's measurement
+ * the production observable for cache behavior (the reconstructability Agent Note's measurement
  * layer: prefix stability is corollary #1). Mocks establish append-extension;
  * this key-gated test establishes a real provider cache hit.
  */
@@ -43,7 +44,7 @@ async function loopHarness(): Promise<Context> {
   await created.plugin(ToolRegistry)
   await created.plugin(AgentRegistry)
   await created.plugin(AgentLoop, { agents: [] })
-  await created.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] })
+  await created.plugin(LlmDeepSeek)
   created.tools.register(defineTool({
     name: 'lookup',
     description: 'Look up the stored value for a key.',
@@ -69,7 +70,7 @@ function waitForIdle(context: Context, agent: Agent): Promise<void> {
 describe.skipIf(!process.env.DEEPSEEK_API_KEY)('log-derived request cache hits (real API)', () => {
   it('every request after the first hits the provider prefix cache', async () => {
     ctx = await loopHarness()
-    const agent = ctx.agentLoop.create(AgentId('cache-e2e'), { model: 'deepseek-v4-flash' })
+    const agent = ctx.agentLoop.create(SessionId('cache-e2e'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
 
     // Turn 1: forces a tool call → at least two steps (two model requests).
     agent.send([{ type: 'text', text: 'Look up the key "deploy-color" with the lookup tool and tell me the value.' }])

packages/core/agent-loop/tests/request-log.spec.ts

@@ -1,9 +1,8 @@
 /**
- * recordRequestHeader unit tests: exactly one of four things per request —
+ * recordRequestHeader unit tests: exactly one of three things per request —
  * an 'initial' snapshot (log has no header yet), a 'resume' snapshot (fresh
- * loop instance over a log that has one), nothing (header unchanged), a
- * round-tripping delta, or a 'fallback' snapshot when the delta encoding
- * cannot express the change (pure tool reordering).
+ * loop instance over a log that has one), nothing (header unchanged), or a
+ * full 'change' snapshot.
  */
 
 import { describe, expect, it } from 'vitest'
@@ -23,14 +22,14 @@ function openSession(id: string): Session {
 }
 
 function headerEvents(session: Session): SessionEvent[] {
-  return session.events.filter(e => e.type === 'request/header' || e.type === 'request/header-delta')
+  return session.events.filter(e => e.type === 'request/header')
 }
 
 describe('recordRequestHeader', () => {
   it("anchors a new conversation with an 'initial' snapshot, then logs nothing while unchanged", () => {
     const session = openSession('rl-initial')
     const state = createTransmissionLog()
-    const header = canonicalHeader({ config: { model: 'm' }, system: 's', tools: [tool('t')] })
+    const header = canonicalHeader({ config: { provider: 'mock', model: 'm' }, system: 's', tools: [tool('t')] })
 
     recordRequestHeader(session, state, header)
     const [first] = headerEvents(session)
@@ -42,7 +41,7 @@ describe('recordRequestHeader', () => {
 
   it("anchors a fresh loop instance over an anchored log with a 'resume' snapshot, even unchanged", () => {
     const session = openSession('rl-resume')
-    const header = canonicalHeader({ config: { model: 'm' }, system: 's' })
+    const header = canonicalHeader({ config: { provider: 'mock', model: 'm' }, system: 's' })
     recordRequestHeader(session, createTransmissionLog(), header)
 
     // A second instance (process restart / fork): the boundary itself is a
@@ -53,33 +52,31 @@ describe('recordRequestHeader', () => {
     expect(events[1]?.type === 'request/header' && events[1].data.reason).toBe('resume')
   })
 
-  it('logs a round-tripping delta for a mid-run change, and the fold reproduces the header', () => {
-    const session = openSession('rl-delta')
+  it("logs a full 'change' snapshot for a mid-run change, and the fold reproduces the header", () => {
+    const session = openSession('rl-change')
     const state = createTransmissionLog()
-    const first = canonicalHeader({ config: { model: 'm' }, system: 'a\nb', tools: [tool('t')] })
+    const first = canonicalHeader({ config: { provider: 'mock', model: 'm' }, system: 'a\nb', tools: [tool('t')] })
     recordRequestHeader(session, state, first)
 
-    const second = canonicalHeader({ config: { model: 'm' }, system: 'a\nc', tools: [tool('t'), tool('u')] })
+    const second = canonicalHeader({ config: { provider: 'mock', model: 'm' }, system: 'a\nc', tools: [tool('t'), tool('u')] })
     recordRequestHeader(session, state, second)
     const events = headerEvents(session)
     expect(events).toHaveLength(2)
-    expect(events[1]?.type).toBe('request/header-delta')
+    expect(events[1]?.type === 'request/header' && events[1].data.reason).toBe('change')
     expect(session.requestHeader()).toEqual(second)
   })
 
-  it("records a change the delta cannot express (pure reordering) as a 'fallback' snapshot", () => {
-    const session = openSession('rl-fallback')
+  it("records a pure tool reordering as a 'change' snapshot", () => {
+    const session = openSession('rl-reorder')
     const state = createTransmissionLog()
-    const first = canonicalHeader({ config: { model: 'm' }, tools: [tool('a'), tool('b')] })
+    const first = canonicalHeader({ config: { provider: 'mock', model: 'm' }, tools: [tool('a'), tool('b')] })
     recordRequestHeader(session, state, first)
 
-    const reordered = canonicalHeader({ config: { model: 'm' }, tools: [tool('b'), tool('a')] })
+    const reordered = canonicalHeader({ config: { provider: 'mock', model: 'm' }, tools: [tool('b'), tool('a')] })
     recordRequestHeader(session, state, reordered)
     const events = headerEvents(session)
     expect(events).toHaveLength(2)
-    expect(events[1]?.type === 'request/header' && events[1].data.reason).toBe('fallback')
-    // The fold still lands on the exact header — deltas are an encoding
-    // optimization, never a correctness dependency.
+    expect(events[1]?.type === 'request/header' && events[1].data.reason).toBe('change')
     expect(session.requestHeader()).toEqual(reordered)
   })
 })

packages/core/agent-loop/tests/request-reconstruction.spec.ts

@@ -1,9 +1,8 @@
 /**
  * Loop-level reconstructability: every request the loop sends is a pure function of the
- * session log — messages are the derivation at the step/start boundary, the header is the fold
- * of request/header* events — and every request is an append-extension of its predecessor
- * unless a logged event (compaction replace, header change) explains the difference. Mock-adapter
- * requests are the observable, and the final offline rebuild states the full contract end to end.
+ * session log — messages derive at the step/start boundary and the header is the latest
+ * request/header snapshot. Each request extends its predecessor unless a logged compaction
+ * replacement or header change explains the difference.
  */
 
 import { describe, expect, it } from 'vitest'
@@ -13,8 +12,9 @@ import type { GenerateOptions } from '@deepseek-ai/dsh-llm'
 import SessionStore, { Session, SessionId, foldRequestHeader } from '@deepseek-ai/dsh-session'
 import SystemPrompt 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 AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
+
+import AgentLoop from '@deepseek-ai/dsh-agent-loop'
 import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts'
 
 async function harness(adapter: MockAdapter, persona = 'stable base') {
@@ -29,7 +29,7 @@ async function harness(adapter: MockAdapter, persona = 'stable base') {
   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') {
@@ -40,7 +40,7 @@ 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 }])
 }
 
@@ -72,7 +72,7 @@ describe('request stability across the loop', () => {
     ])
     const ctx = await harness(adapter)
     registerEcho(ctx)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     send(agent, 'go')
     await waitForIdle(ctx, agent)
@@ -85,7 +85,7 @@ describe('request stability across the loop', () => {
       expect(Object.isFrozen(request.messages)).toBe(true)
     }
     // One anchoring header snapshot; no further header events (nothing changed).
-    const headerEvents = agent.session.events.filter(e => e.type === 'request/header' || e.type === 'request/header-delta')
+    const headerEvents = agent.session.events.filter(e => e.type === 'request/header')
     expect(headerEvents).toHaveLength(1)
     expect(headerEvents[0]?.type === 'request/header' && headerEvents[0].data.reason).toBe('initial')
   })
@@ -93,7 +93,7 @@ describe('request stability across the loop', () => {
   it('a later turn append-extends the previous turn (one conversation, one log)', async () => {
     const adapter = new MockAdapter([textResponse('one'), textResponse('two')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     send(agent, 'first')
     await waitForIdle(ctx, agent)
@@ -107,7 +107,7 @@ describe('request stability across the loop', () => {
   it('a compaction replace rewrites the resend, and the log explains it', async () => {
     const adapter = new MockAdapter([textResponse('one'), textResponse('two')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     send(agent, 'first')
     await waitForIdle(ctx, agent)
@@ -122,8 +122,8 @@ describe('request stability across the loop', () => {
         content: [{ type: 'text', text: '[summary of turn 1]' }],
         source: { kind: 'plugin', plugin: 'test-compact' },
       }, {
-        surfaceOp: { op: 'replace', start: nodes[0]!.seq, end: nodes[1]!.seq },
-        sourceEventSeqs: [nodes[0]!.seq, nodes[1]!.seq],
+        surfaceOp: { op: 'replace', start: nodes[0]!, end: nodes[1]! },
+        sourceEventSeqs: [nodes[0]!, nodes[1]!],
       })
     })
 
@@ -137,24 +137,25 @@ describe('request stability across the loop', () => {
     expect(agent.session.events.filter(e => e.type === 'request/header')).toHaveLength(1)
   })
 
-  it('a real system-prompt change is a logged header delta; a stable prompt logs nothing', async () => {
+  it('a real system-prompt change is a full changed-header snapshot; a stable prompt logs nothing', async () => {
     const adapter = new MockAdapter([textResponse('one'), textResponse('two'), textResponse('three')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     send(agent, 'first')
     await waitForIdle(ctx, agent)
     send(agent, 'second')
     await waitForIdle(ctx, agent)
     // Identical assembly re-rendered per step is NOT a change.
-    expect(agent.session.events.filter(e => e.type === 'request/header-delta')).toHaveLength(0)
+    expect(agent.session.events.filter(e => e.type === 'request/header')).toHaveLength(1)
 
     ctx.systemPrompt.section({ name: 'extra', order: 2, text: 'new guidance' })
     send(agent, 'third')
     await waitForIdle(ctx, agent)
 
-    const deltas = agent.session.events.filter(e => e.type === 'request/header-delta')
-    expect(deltas).toHaveLength(1)
+    const snapshots = agent.session.events.filter(e => e.type === 'request/header')
+    expect(snapshots).toHaveLength(2)
+    expect(snapshots[1]?.data.reason).toBe('change')
     expect(adapter.requests[2]!.system).toContain('new guidance')
     // History is preserved across the change — only the header moved.
     expect(adapter.requests[2]!.messages.length).toBeGreaterThan(adapter.requests[1]!.messages.length)
@@ -163,7 +164,7 @@ describe('request stability across the loop', () => {
   it('an inject() during the agent/request waterfall joins the NEXT request (the step/start boundary)', async () => {
     const adapter = new MockAdapter([textResponse('one'), textResponse('two')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     let injected = false
     ctx.on('agent/request', async (_agent, _turn, _step, _config, next) => {
@@ -191,7 +192,7 @@ describe('request stability across the loop', () => {
   it('a mutation attempt on the frozen request content throws into the step (loud, not silent)', async () => {
     const adapter = new MockAdapter([textResponse('one')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     const errors: Error[] = []
     ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error))
@@ -212,7 +213,7 @@ describe('request stability across the loop', () => {
   it('a fresh loop instance over a seeded log anchors with a resume snapshot and stays cache-aligned', async () => {
     const adapter = new MockAdapter([textResponse('one')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('gen1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('gen1'), { provider: 'mock', model: 'mock' })
     send(agent, 'first')
     await waitForIdle(ctx, agent)
 
@@ -221,12 +222,11 @@ describe('request stability across the loop', () => {
     const adapter2 = new MockAdapter([textResponse('two')])
     const ctx2 = await harness(adapter2)
     const handle = await ctx2.agents.create({
-      agentId: AgentId('gen2'),
       sessionId: SessionId('gen2-session'),
       seed: [...agent.session.events],
-      agentOptions: { model: 'mock' },
+      agentOptions: { provider: 'mock', model: 'mock' },
     })
-    const agent2 = handle.agent as ReactLoopAgent
+    const agent2 = handle.agent
     send(agent2, 'second')
     await waitForIdle(ctx2, agent2)
 
@@ -241,7 +241,7 @@ describe('request stability across the loop', () => {
   it('a delegating listener cannot mutate the seed through next() — the fold stays log-true', async () => {
     const adapter = new MockAdapter([textResponse('one'), textResponse('two')])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     ctx.on('agent/request', async (_agent, _turn, _step, _config, next) => {
       const config = await next()
@@ -260,9 +260,9 @@ describe('request stability across the loop', () => {
     send(agent, 'second')
     await waitForIdle(ctx, agent)
 
-    // No delta was logged (nothing really changed), and the session's own
+    // No changed snapshot was logged (nothing really changed), and the session's own
     // fold is immutable state.
-    expect(agent.session.events.filter(e => e.type === 'request/header-delta')).toHaveLength(0)
+    expect(agent.session.events.filter(e => e.type === 'request/header')).toHaveLength(1)
     expect(Object.isFrozen(agent.session.requestHeader())).toBe(true)
     expect(adapter.requests[1]!.temperature).toBeUndefined()
   })
@@ -275,7 +275,7 @@ describe('request stability across the loop', () => {
     ])
     const ctx = await harness(adapter)
     registerEcho(ctx)
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
 
     send(agent, 'go')
     await waitForIdle(ctx, agent)
@@ -296,7 +296,7 @@ describe('request stability across the loop', () => {
       const rebuilt = new Session(SessionId(`rebuild-${index}`), structuredClone(events.slice(0, stepStart.seq)))
       expect(structuredClone(request.messages)).toEqual(rebuilt.deriveMessages())
 
-      // Header: the fold of request/header* events up to this step's dispatch
+      // Header: the latest request/header snapshot up to this step's dispatch
       // (its header event sits between step/start and the first chunk).
       const firstChunk = events.find(e => e.type === 'assistant/chunk' && e.seq > stepStart.seq)!
       const header = foldRequestHeader(events.slice(0, firstChunk.seq))!

packages/core/agent-loop/tests/request-recovery.spec.ts

@@ -0,0 +1,516 @@
+import { describe, expect, it, vi } from 'vitest'
+import { Context } from 'cordis'
+import LlmService, {
+  CallId,
+  CONTEXT_WINDOW_EXCEEDED_CODE,
+  LlmAdapter,
+  LlmError,
+} from '@deepseek-ai/dsh-llm'
+import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm'
+import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
+import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
+import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
+import type { PostToolDecision } from '@deepseek-ai/dsh-tools'
+import AgentRegistry from '@deepseek-ai/dsh-agent'
+import type { Agent } from '@deepseek-ai/dsh-agent'
+import AgentLoop from '@deepseek-ai/dsh-agent-loop'
+import { maxTokensResponse, textResponse, toolCallResponse } from './mock-adapter.ts'
+
+class FailureScriptAdapter extends LlmAdapter {
+  requests: GenerateOptions[] = []
+
+  constructor(private readonly entries: (Error | StreamChunk[])[]) {
+    super()
+  }
+
+  async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
+    this.requests.push(options)
+    const entry = this.entries.shift()
+    if (entry === undefined) throw new Error('failure script exhausted')
+    if (entry instanceof Error) throw entry
+    yield* entry
+  }
+}
+
+class IteratorConstructionFailureAdapter extends LlmAdapter {
+  stream(_options: GenerateOptions): AsyncIterable<StreamChunk> {
+    return {
+      [Symbol.asyncIterator](): AsyncIterator<StreamChunk> {
+        throw new LlmError('iterator construction failed', 'ITERATOR_CONSTRUCTION')
+      },
+    }
+  }
+}
+
+class SynchronousDispatchFailureAdapter extends LlmAdapter {
+  constructor(private readonly error: Error) {
+    super()
+  }
+
+  stream(_options: GenerateOptions): AsyncIterable<StreamChunk> {
+    throw this.error
+  }
+}
+
+class IteratorResultGetterFailureAdapter extends LlmAdapter {
+  constructor(
+    private readonly field: 'done' | 'value',
+    private readonly error: Error,
+  ) {
+    super()
+  }
+
+  stream(_options: GenerateOptions): AsyncIterable<StreamChunk> {
+    const result = this.field === 'done' ? {} : { done: false }
+    Object.defineProperty(result, this.field, { get: () => { throw this.error } })
+    return {
+      [Symbol.asyncIterator](): AsyncIterator<StreamChunk> {
+        return { next: () => Promise.resolve(result as unknown as IteratorResult<StreamChunk>) }
+      },
+    }
+  }
+}
+
+const streamListenerFailureCases: readonly [string, (ctx: Context) => void][] = [
+  ['synchronous listener throw', (ctx) => {
+    ctx.on('llm/stream', () => { throw new Error('synchronous stream listener failed') })
+  }],
+  ['invalid listener iterable', (ctx) => {
+    ctx.on('llm/stream', () => ({}) as AsyncIterable<StreamChunk>)
+  }],
+  ['listener wrapper iteration failure', (ctx) => {
+    ctx.on('llm/stream', (_options, next) => (async function * () {
+      for await (const chunk of next()) {
+        yield chunk
+        throw new Error('stream listener wrapper failed')
+      }
+    })())
+  }],
+]
+
+async function harness(adapter?: LlmAdapter): Promise<Context> {
+  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: [] })
+  if (adapter) ctx.llm.registerAdapter(['mock'], adapter)
+  return ctx
+}
+
+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') {
+        dispose()
+        resolve()
+      }
+    })
+  })
+}
+
+function send(agent: Agent): void {
+  agent.send([{ type: 'text', text: 'go' }])
+}
+
+function contextError(message = 'context too large'): LlmError {
+  return new LlmError(message, CONTEXT_WINDOW_EXCEEDED_CODE)
+}
+
+describe('agent post-step and request-error lifecycle', () => {
+  it('fires post-step after results, buffered context, and steering but before step/end', async () => {
+    const twoCalls: StreamChunk[] = [
+      { type: 'block-start', index: 0, blockType: 'tool-call' },
+      { type: 'block-end', index: 0, block: { type: 'tool-call', id: CallId('call-1'), name: 'work', arguments: '{}' } },
+      { type: 'block-start', index: 1, blockType: 'tool-call' },
+      { type: 'block-end', index: 1, block: { type: 'tool-call', id: CallId('call-2'), name: 'work', arguments: '{}' } },
+      { type: 'usage', usage: { inputTokens: 10, outputTokens: 5 } },
+      { type: 'finish', reason: { kind: 'tool-calls' } },
+    ]
+    const adapter = new FailureScriptAdapter([twoCalls, textResponse('done')])
+    const ctx = await harness(adapter)
+    ctx.tools.register(defineTool({
+      name: 'work',
+      description: 'do work',
+      parameters: {},
+      async execute(_args, exec) {
+        if (exec.callId === CallId('call-2')) {
+          exec.agent?.steer([{ type: 'text', text: 'steered' }], { source: { kind: 'plugin', plugin: 'test' } })
+        }
+        return [{ type: 'text', text: 'worked' }]
+      },
+    }))
+    ctx.on('tools/post-execute', async (exec, _result): Promise<PostToolDecision> => ({
+      kind: 'accept',
+      additionalContexts: [{
+        content: [{ type: 'text', text: `context for ${exec.callId}` }],
+        source: { kind: 'plugin', plugin: 'test' },
+      }],
+    }))
+    const agent = ctx.agentLoop.create(SessionId('post-step-order'), { provider: 'mock', model: 'mock' })
+    const order: string[] = []
+    ctx.on('session/event', (_session, event) => {
+      if (
+        event.type === 'assistant/message' || event.type === 'tool/call'
+        || event.type === 'tool/result' || event.type === 'context/message'
+        || event.type === 'steering/message' || event.type === 'step/end'
+      ) {
+        if (!('step' in event.data) || event.data.step === 1) order.push(event.type)
+      }
+    })
+    ctx.on('agent/post-step', (subject, turn, step, signal) => {
+      if (subject !== agent || step !== 1) return
+      expect({ turn, step, aborted: signal.aborted }).toEqual({ turn: 1, step: 1, aborted: false })
+      subject.inject([{ type: 'text', text: 'listener mutation' }], { source: { kind: 'plugin', plugin: 'post-step' } })
+      order.push('agent/post-step')
+    })
+
+    send(agent)
+    await waitForIdle(ctx, agent)
+
+    expect(order).toEqual([
+      'assistant/message',
+      'tool/call',
+      'tool/result',
+      'tool/call',
+      'tool/result',
+      'context/message',
+      'context/message',
+      'steering/message',
+      'context/message',
+      'agent/post-step',
+      'step/end',
+    ])
+  })
+
+  it('fires post-step for max-tokens and lets cancellation override that success', async () => {
+    const adapter = new FailureScriptAdapter([maxTokensResponse('partial')])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(SessionId('cancel-post-step-max-tokens'), { provider: 'mock', model: 'mock' })
+    let entered!: () => void
+    const postStepEntered = new Promise<void>((resolve) => { entered = resolve })
+    ctx.on('agent/post-step', async (_agent, turn, step, signal) => {
+      expect({ turn, step }).toEqual({ turn: 1, step: 1 })
+      entered()
+      await new Promise<void>((resolve) => {
+        signal.addEventListener('abort', () => { resolve() }, { once: true })
+      })
+    })
+
+    send(agent)
+    const idle = waitForIdle(ctx, agent)
+    await postStepEntered
+    agent.cancel('cancelled during max-tokens post-step')
+    await idle
+
+    expect(agent.session.events.find(event => event.type === 'assistant/message')).toMatchObject({
+      data: { usage: { inputTokens: 10, outputTokens: 7 } },
+    })
+    expect(agent.session.events.at(-1)).toMatchObject({
+      type: 'turn/end',
+      data: { reason: { kind: 'aborted', reason: 'cancelled during max-tokens post-step' } },
+    })
+  })
+
+  it('closes the successful step as disposed when disposal lands during post-step', async () => {
+    const adapter = new FailureScriptAdapter([
+      toolCallResponse('dispose-call', 'work', {}),
+      textResponse('must not continue'),
+    ])
+    const ctx = await harness(adapter)
+    ctx.tools.register(defineTool({
+      name: 'work',
+      description: 'do work',
+      parameters: {},
+      async execute() { return [{ type: 'text', text: 'worked' }] },
+    }))
+    const agent = ctx.agentLoop.create(SessionId('dispose-post-step'), { provider: 'mock', model: 'mock' })
+    let entered!: () => void
+    const postStepEntered = new Promise<void>((resolve) => { entered = resolve })
+    ctx.on('agent/post-step', async (_agent, turn, step, signal) => {
+      expect({ turn, step }).toEqual({ turn: 1, step: 1 })
+      entered()
+      await new Promise<void>((resolve) => {
+        signal.addEventListener('abort', () => { resolve() }, { once: true })
+      })
+    })
+
+    send(agent)
+    await postStepEntered
+    await ctx.fiber.dispose()
+
+    expect(adapter.requests).toHaveLength(1)
+    const boundaries = agent.session.events.filter(event =>
+      event.type === 'step/start' || event.type === 'step/end',
+    )
+    expect(boundaries.map(event => event.type)).toEqual(['step/start', 'step/end'])
+    expect(boundaries.map(event => event.data)).toEqual([
+      { turn: 1, step: 1 },
+      { turn: 1, step: 1 },
+    ])
+    expect(agent.session.events.at(-1)).toMatchObject({
+      type: 'turn/end',
+      data: { reason: { kind: 'disposed' } },
+    })
+  })
+
+  it.each([
+    ['thrown', contextError()],
+    ['in-band', [{ type: 'finish', reason: { kind: 'error', message: 'too large', code: CONTEXT_WINDOW_EXCEEDED_CODE } }] satisfies StreamChunk[]],
+  ] as const)('recovers a %s request failure in a new reconstructable step', async (_style, failure) => {
+    const adapter = new FailureScriptAdapter([failure, textResponse('recovered')])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(SessionId(`recover-${_style}`), { provider: 'mock', model: 'mock' })
+    const attempts: number[] = []
+    ctx.on('agent/request-error', async (subject, turn, step, error, attempt) => {
+      expect(subject).toBe(agent)
+      expect({ turn, step, code: error.code }).toEqual({ turn: 1, step: 1, code: CONTEXT_WINDOW_EXCEEDED_CODE })
+      attempts.push(attempt)
+      subject.session.append('context/message', {
+        content: [{ type: 'text', text: 'RECOVERY SURFACE MUTATION' }],
+        source: { kind: 'plugin', plugin: 'test-recovery' },
+      }, { surfaceOp: 'append' })
+      return { action: 'retry' }
+    })
+
+    send(agent)
+    await waitForIdle(ctx, agent)
+
+    expect(attempts).toEqual([0])
+    expect(adapter.requests).toHaveLength(2)
+    expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('RECOVERY SURFACE MUTATION')
+    const starts = agent.session.events.filter(event => event.type === 'step/start')
+    const ends = agent.session.events.filter(event => event.type === 'step/end')
+    expect(starts.map(event => event.data.step)).toEqual([1, 2])
+    expect(ends.map(event => event.data.step)).toEqual([1, 2])
+    const recovery = agent.session.events.find(event => event.type === 'context/message')!
+    expect(ends[0]!.seq).toBeLessThan(recovery.seq)
+    expect(recovery.seq).toBeLessThan(starts[1]!.seq)
+  })
+
+  it.each(streamListenerFailureCases)('does not offer %s to request recovery', async (_name, install) => {
+    const ctx = await harness(new FailureScriptAdapter([textResponse('unused')]))
+    const agent = ctx.agentLoop.create(SessionId(`stream-plugin-${_name.replaceAll(' ', '-')}`), { provider: 'mock', model: 'mock' })
+    let recoveries = 0
+    install(ctx)
+    ctx.on('agent/request-error', async (_agent, _turn, _step, _error, _attempt, _signal, next) => {
+      recoveries += 1
+      return next()
+    })
+
+    send(agent)
+    await waitForIdle(ctx, agent)
+
+    expect(recoveries).toBe(0)
+    expect(agent.session.events.at(-1)).toMatchObject({ type: 'turn/end', data: { reason: { kind: 'error' } } })
+  })
+
+  it('does not offer a nested model-call failure as the outer request failure', async () => {
+    const outer = new FailureScriptAdapter([textResponse('outer adapter must not run')])
+    const nested = new FailureScriptAdapter([contextError('nested overflow')])
+    const ctx = await harness(outer)
+    ctx.llm.registerAdapter(['nested'], nested)
+    ctx.on('llm/stream', (options, next) => {
+      if (options.provider !== 'mock') return next()
+      return (async function* () {
+        yield* ctx.llm.stream({
+          provider: 'nested',
+          model: 'nested',
+          messages: [],
+          ...options.signal === undefined ? {} : { signal: options.signal },
+        })
+        yield* next()
+      })()
+    })
+    const agent = ctx.agentLoop.create(SessionId('nested-stream-not-recoverable'), { provider: 'mock', model: 'mock' })
+    let recoveries = 0
+    ctx.on('agent/request-error', async (_agent, _turn, _step, _error, _attempt, _signal, next) => {
+      recoveries += 1
+      return next()
+    })
+
+    send(agent)
+    await waitForIdle(ctx, agent)
+
+    expect(nested.requests).toHaveLength(1)
+    expect(outer.requests).toHaveLength(0)
+    expect(recoveries).toBe(0)
+    expect(agent.session.events.at(-1)).toMatchObject({
+      type: 'turn/end',
+      data: { reason: { kind: 'error', message: 'nested overflow', code: CONTEXT_WINDOW_EXCEEDED_CODE } },
+    })
+  })
+
+  it.each(['prompt-submit', 'prompt-assembly', 'pre-step', 'request'] as const)(
+    'does not offer %s middleware failures to request recovery',
+    async (boundary) => {
+      const adapter = new FailureScriptAdapter([textResponse('unused')])
+      const ctx = await harness(adapter)
+      if (boundary === 'prompt-submit') {
+        ctx.on('agent/prompt-submit', () => { throw new Error('prompt submit failed') })
+      } else if (boundary === 'prompt-assembly') {
+        ctx.on('system-prompt/assemble', () => { throw new Error('prompt assembly failed') })
+      } else if (boundary === 'pre-step') {
+        ctx.on('agent/pre-step', () => { throw new Error('pre-step failed') })
+      } else {
+        ctx.on('agent/request', () => { throw new Error('request middleware failed') })
+      }
+      const agent = ctx.agentLoop.create(SessionId(`${boundary}-not-recoverable`), { provider: 'mock', model: 'mock' })
+      let recoveries = 0
+      ctx.on('agent/request-error', async (_agent, _turn, _step, _error, _attempt, _signal, next) => {
+        recoveries += 1
+        return next()
+      })
+
+      send(agent)
+      await waitForIdle(ctx, agent)
+
+      expect(recoveries).toBe(0)
+      expect(adapter.requests).toHaveLength(0)
+      expect(agent.session.events.at(-1)).toMatchObject({ type: 'turn/end', data: { reason: { kind: 'error' } } })
+    },
+  )
+
+  it('does not offer result, tool, or post-step plugin failures to request recovery', async () => {
+    for (const failure of ['result', 'tool', 'post-step'] as const) {
+      const adapter = new FailureScriptAdapter([
+        failure === 'tool' ? toolCallResponse(`call-${failure}`, 'work', {}) : textResponse('done'),
+        ...(failure === 'tool' ? [textResponse('done')] : []),
+      ])
+      const ctx = await harness(adapter)
+      if (failure === 'result') ctx.on('agent/step-result', () => { throw new Error('result failed') })
+      if (failure === 'post-step') ctx.on('agent/post-step', () => { throw new Error('post-step failed') })
+      if (failure === 'tool') {
+        vi.spyOn(ctx.tools, 'execute').mockRejectedValue(new Error('tool service failed'))
+      }
+      const agent = ctx.agentLoop.create(SessionId(`${failure}-not-recoverable`), { provider: 'mock', model: 'mock' })
+      let recoveries = 0
+      ctx.on('agent/request-error', async (_agent, _turn, _step, _error, _attempt, _signal, next) => {
+        recoveries += 1
+        return next()
+      })
+      send(agent)
+      await waitForIdle(ctx, agent)
+      expect(recoveries, failure).toBe(0)
+    }
+  })
+
+  it.each([
+    ['synchronous dispatch', (error: Error) => new SynchronousDispatchFailureAdapter(error)],
+    ['done getter', (error: Error) => new IteratorResultGetterFailureAdapter('done', error)],
+    ['value getter', (error: Error) => new IteratorResultGetterFailureAdapter('value', error)],
+  ] as const)('preserves original Error identity for adapter %s', async (_name, makeAdapter) => {
+    const original = contextError(`${_name} overflow`)
+    const ctx = await harness(makeAdapter(original))
+    const agent = ctx.agentLoop.create(SessionId(`identity-${_name.replaceAll(' ', '-')}`), { provider: 'mock', model: 'mock' })
+    let seen: Error | undefined
+    ctx.on('agent/request-error', async (_agent, _turn, _step, error, _attempt, _signal, next) => {
+      seen = error
+      return next()
+    })
+
+    send(agent)
+    await waitForIdle(ctx, agent)
+
+    expect(seen).toBe(original)
+  })
+
+  it('classifies iterator construction and explicit NO_ADAPTER as model-request failures', async () => {
+    for (const scenario of ['iterator', 'no-adapter'] as const) {
+      const ctx = scenario === 'iterator' ? await harness(new IteratorConstructionFailureAdapter()) : await harness()
+      const agent = ctx.agentLoop.create(SessionId(`request-boundary-${scenario}`), { provider: 'mock', model: 'mock' })
+      let seen = ''
+      ctx.on('agent/request-error', async (_agent, _turn, _step, error, _attempt, _signal, next) => {
+        seen = error.code ?? ''
+        return next()
+      })
+      send(agent)
+      await waitForIdle(ctx, agent)
+      expect(seen).toBe(scenario === 'iterator' ? 'ITERATOR_CONSTRUCTION' : 'NO_ADAPTER')
+    }
+  })
+
+  it('tracks consecutive retry attempts and resets after a successful request', async () => {
+    const capped = new FailureScriptAdapter([contextError('first overflow'), contextError('second overflow')])
+    const cappedCtx = await harness(capped)
+    const cappedAgent = cappedCtx.agentLoop.create(SessionId('retry-cap'), { provider: 'mock', model: 'mock' })
+    const cappedAttempts: number[] = []
+    cappedCtx.on('agent/request-error', async (_agent, _turn, _step, _error, attempt, _signal, next) => {
+      cappedAttempts.push(attempt)
+      return attempt < 1 ? { action: 'retry' } : next()
+    })
+    send(cappedAgent)
+    await waitForIdle(cappedCtx, cappedAgent)
+    expect(cappedAttempts).toEqual([0, 1])
+
+    const reset = new FailureScriptAdapter([
+      contextError('first overflow'),
+      toolCallResponse('retry-reset-call', 'work', {}),
+      contextError('later overflow'),
+    ])
+    const resetCtx = await harness(reset)
+    resetCtx.tools.register(defineTool({
+      name: 'work',
+      description: 'continue',
+      parameters: {},
+      async execute() { return [{ type: 'text', text: 'worked' }] },
+    }))
+    const resetAgent = resetCtx.agentLoop.create(SessionId('retry-reset'), { provider: 'mock', model: 'mock' })
+    const resetAttempts: { step: number; attempt: number }[] = []
+    resetCtx.on('agent/request-error', async (_agent, _turn, step, _error, attempt, _signal, next) => {
+      resetAttempts.push({ step, attempt })
+      return resetAttempts.length === 1 ? { action: 'retry' } : next()
+    })
+    send(resetAgent)
+    await waitForIdle(resetCtx, resetAgent)
+    expect(resetAttempts).toEqual([{ step: 1, attempt: 0 }, { step: 3, attempt: 0 }])
+  })
+
+  it('preserves the original provider error when recovery throws', async () => {
+    const adapter = new FailureScriptAdapter([contextError('original overflow')])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(SessionId('recovery-throws'), { provider: 'mock', model: 'mock' })
+    ctx.on('agent/request-error', () => { throw new Error('recovery exploded') })
+
+    send(agent)
+    await waitForIdle(ctx, agent)
+
+    expect(agent.session.events.at(-1)).toMatchObject({
+      type: 'turn/end',
+      data: { reason: { kind: 'error', message: 'original overflow', code: CONTEXT_WINDOW_EXCEEDED_CODE } },
+    })
+  })
+
+  it.each(['cancel', 'dispose'] as const)('keeps %s live through request recovery', async (action) => {
+    const adapter = new FailureScriptAdapter([contextError()])
+    const ctx = await harness(adapter)
+    const agent = ctx.agentLoop.create(SessionId(`${action}-recovery`), { provider: 'mock', model: 'mock' })
+    let entered!: () => void
+    const recoveryEntered = new Promise<void>((resolve) => { entered = resolve })
+    ctx.on('agent/request-error', async (_agent, _turn, _step, _error, _attempt, signal) => {
+      entered()
+      await new Promise<void>((resolve) => {
+        signal.addEventListener('abort', () => { resolve() }, { once: true })
+      })
+      return { action: 'retry' }
+    })
+
+    send(agent)
+    const idle = waitForIdle(ctx, agent)
+    await recoveryEntered
+    if (action === 'cancel') {
+      agent.cancel('cancelled during recovery')
+      await idle
+    } else {
+      await ctx.fiber.dispose()
+    }
+
+    expect(adapter.requests).toHaveLength(1)
+    expect(agent.session.events.at(-1)).toMatchObject({
+      type: 'turn/end',
+      data: { reason: action === 'cancel' ? { kind: 'aborted', reason: 'cancelled during recovery' } : { kind: 'disposed' } },
+    })
+  })
+})

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

@@ -8,9 +8,10 @@ import SessionStore, { Session, SessionId } from '@deepseek-ai/dsh-session'
 import type { SessionEvent } 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'
+import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
+
 import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
-import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
+import AgentLoop from '@deepseek-ai/dsh-agent-loop'
 import { MockAdapter, textResponse } from './mock-adapter.ts'
 
 const dirs: string[] = []
@@ -50,7 +51,7 @@ async function persistSession(sessionId: SessionId): Promise<string> {
   return root
 }
 
-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') { dispose(); resolve() }
@@ -74,7 +75,7 @@ function throwUnknown(value: unknown): never {
   throw value
 }
 
-describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
+describe('the session-persistence Agent Note: AgentLoop factory create/resume', () => {
   it('normalizes a non-Error resume publication failure for rollback and rethrows it', async () => {
     const sessionId = SessionId('unknown-resume-failure-s')
     const root = await persistSession(sessionId)
@@ -83,11 +84,10 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
     ctx.on('session/created', () => throwUnknown(failure))
 
     await expect(ctx.agents.resume({
-      agentId: AgentId('unknown-resume-failure'),
       resumeSessionId: sessionId,
     })).rejects.toBe(failure)
 
-    expect(ctx.agents.get(AgentId('unknown-resume-failure'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('unknown-resume-failure'))).toBeUndefined()
     expect(ctx.sessions.get(sessionId)).toBeUndefined()
     await ctx.fiber.dispose()
   })
@@ -95,27 +95,26 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
   it('createAgent uses the caller-supplied sessionId (not ${id}-session)', async () => {
     const adapter = new MockAdapter([textResponse('hi')])
     const { ctx } = await persistentHarness(adapter)
-    const { agent } = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('custom-session'), meta: { cwd: '/w' } })
+    const { agent } = await ctx.agents.create({ sessionId: SessionId('custom-session'), meta: { cwd: '/w' } })
     expect(agent.session.id).toBe('custom-session')
     expect(agent.session.header.cwd).toBe('/w')
     await ctx.fiber.dispose()
   })
 
-  it('createAgent rejects a duplicate agent id BEFORE creating the session (no orphan)', async () => {
+  it('createAgent rejects a duplicate identity without orphaning a session', async () => {
     const adapter = new MockAdapter([textResponse('hi')])
     const { ctx } = await persistentHarness(adapter)
-    await ctx.agents.create({ agentId: AgentId('dup'), sessionId: SessionId('sess-a') })
-    // A second create with the SAME agent id but a fresh session id must reject
-    // up front — and must NOT leave an orphaned 'sess-b' session behind.
-    await expect(ctx.agents.create({ agentId: AgentId('dup'), sessionId: SessionId('sess-b') })).rejects.toThrow(/already registered/)
-    expect(ctx.sessions.get(SessionId('sess-b'))).toBeUndefined()
+    const sessionId = SessionId('sess-a')
+    await ctx.agents.create({ sessionId })
+    await expect(ctx.agents.create({ sessionId })).rejects.toThrow(/already exists/)
+    expect(ctx.sessions.list()).toHaveLength(1)
     await ctx.fiber.dispose()
   })
 
   it('createAgent works without meta (no cwd)', async () => {
     const adapter = new MockAdapter([textResponse('hi')])
     const { ctx } = await persistentHarness(adapter)
-    const { agent } = await ctx.agents.create({ agentId: AgentId('a-nometa'), sessionId: SessionId('nometa-session') })
+    const { agent } = await ctx.agents.create({ sessionId: SessionId('nometa-session') })
     expect(agent.session.id).toBe('nometa-session')
     expect(agent.session.header.cwd).toBeUndefined()
     await ctx.fiber.dispose()
@@ -125,7 +124,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
     // Lifecycle 1: create a no-cwd session and run a turn.
     const adapter1 = new MockAdapter([textResponse('a')])
     const { ctx: ctx1, root } = await persistentHarness(adapter1)
-    const a1 = (await ctx1.agents.create({ agentId: AgentId('m'), sessionId: SessionId('nocwd-sess') })).agent as ReactLoopAgent
+    const a1 = (await ctx1.agents.create({ sessionId: SessionId('nocwd-sess') })).agent
     a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } })
     await waitForIdle(ctx1, a1)
     await ctx1.fiber.dispose()
@@ -141,7 +140,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
     await ctx2.plugin(AgentLoop, { agents: [] })
     await ctx2.plugin(SessionPersistenceJsonl, { root })
     ctx2.llm.registerAdapter(['mock'], adapter2)
-    const a2 = (await ctx2.agents.resume({ agentId: AgentId('m'), resumeSessionId: SessionId('nocwd-sess') })).agent as ReactLoopAgent
+    const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('nocwd-sess') })).agent
     expect(a2.session.header.cwd).toBeUndefined()
     await ctx2.fiber.dispose()
   })
@@ -152,7 +151,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
     const { ctx: ctx1, root } = await persistentHarness(adapter1)
     const sources1: string[] = []
     ctx1.on('agent/session-start', (_agent, source) => void sources1.push(source))
-    const a1 = (await ctx1.agents.create({ agentId: AgentId('s'), sessionId: SessionId('start-sess') })).agent as ReactLoopAgent
+    const a1 = (await ctx1.agents.create({ sessionId: SessionId('start-sess') })).agent
     expect(sources1).toEqual(['startup'])
     a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } })
     await waitForIdle(ctx1, a1)
@@ -171,7 +170,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
     ctx2.llm.registerAdapter(['mock'], adapter2)
     const sources2: string[] = []
     ctx2.on('agent/session-start', (_agent, source) => void sources2.push(source))
-    await ctx2.agents.resume({ agentId: AgentId('s'), resumeSessionId: SessionId('start-sess') })
+    await ctx2.agents.resume({ resumeSessionId: SessionId('start-sess') })
     expect(sources2).toEqual(['resume'])
     await ctx2.fiber.dispose()
   })
@@ -186,7 +185,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
 
     ctx.on('session/created', (session) => {
       expect(ctx.sessions.get(session.id)).toBe(session)
-      expect(ctx.agents.get(AgentId('resumed-atomic'))?.session).toBe(session)
+      expect(ctx.agents.get(sessionId)?.session).toBe(session)
       order.push('session/created')
     })
     ctx.on('agent/created', (agent) => {
@@ -199,11 +198,10 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
     })
 
     const resuming = ctx.agents.resume({
-      agentId: AgentId('resumed-atomic'),
       resumeSessionId: sessionId,
-      agentOptions: { model: 'mock' },
+      agentOptions: { provider: 'mock', model: 'mock' },
       setup: async (agentCtx) => {
-        expect(agentCtx.agent?.id).toBe(AgentId('resumed-atomic'))
+        expect(agentCtx.agent?.id).toBe(sessionId)
         expect(agentCtx.agent?.session.events).toHaveLength(2)
         agentCtx.on('session/created', () => void order.push('setup-listener:session/created'))
         agentCtx.on('agent/created', () => void order.push('setup-listener:agent/created'))
@@ -215,7 +213,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
     })
 
     await setupStarted.promise
-    expect(ctx.agents.get(AgentId('resumed-atomic'))).toBeUndefined()
+    expect(ctx.agents.get(sessionId)).toBeUndefined()
     expect(ctx.sessions.get(sessionId)).toBeUndefined()
     expect(order).toEqual(['setup:start'])
 
@@ -236,17 +234,15 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
 
   it('successful resume disposal retires its caller-owned transaction effects', async () => {
     const sessionId = SessionId('resume-retired-effects-s')
-    const agentId = AgentId('resume-retired-effects')
     const root = await persistSession(sessionId)
     const ctx = await mountPersistentHarness(root, new MockAdapter([textResponse('next')]))
     const handle = await ctx.agents.resume({
-      agentId,
       resumeSessionId: sessionId,
-      agentOptions: { model: 'mock' },
+      agentOptions: { provider: 'mock', model: 'mock' },
     })
     const transactionLabels = [
-      `agentLoop.owner(${agentId})`,
-      `agentLoop.lifecycle(${agentId})`,
+      `agentLoop.owner(${sessionId})`,
+      `agentLoop.lifecycle(${sessionId})`,
     ]
 
     expect(ctx.fiber.getEffects().map(effect => effect.label)).toEqual(expect.arrayContaining(transactionLabels))
@@ -255,7 +251,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
     await ctx.fiber.dispose()
   })
 
-  it('resume setup rejection publishes nothing, unwinds, and releases both identities', async () => {
+  it('resume setup rejection publishes nothing, unwinds, and releases the identity', async () => {
     const sessionId = SessionId('resume-setup-reject')
     const root = await persistSession(sessionId)
     const ctx = await mountPersistentHarness(root, new MockAdapter([textResponse('next')]))
@@ -265,9 +261,8 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
     ctx.on('agent/session-start', () => void published.push('agent/session-start'))
 
     await expect(ctx.agents.resume({
-      agentId: AgentId('resume-reject'),
       resumeSessionId: sessionId,
-      agentOptions: { model: 'mock' },
+      agentOptions: { provider: 'mock', model: 'mock' },
       setup: async () => {
         await Promise.resolve()
         throw new Error('resume setup failed')
@@ -275,12 +270,11 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
     })).rejects.toThrow('resume setup failed')
 
     expect(published).toEqual([])
-    expect(ctx.agents.get(AgentId('resume-reject'))).toBeUndefined()
+    expect(ctx.agents.get(sessionId)).toBeUndefined()
     expect(ctx.sessions.get(sessionId)).toBeUndefined()
     const retry = await ctx.agents.resume({
-      agentId: AgentId('resume-reject'),
       resumeSessionId: sessionId,
-      agentOptions: { model: 'mock' },
+      agentOptions: { provider: 'mock', model: 'mock' },
     })
     await retry.dispose()
     await ctx.fiber.dispose()
@@ -299,9 +293,8 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
     let resuming!: ReturnType<typeof ctx.agents.resume>
     const owner = await ctx.plugin(Object.assign((inner: Context) => {
       resuming = inner.agents.resume({
-        agentId: AgentId('resume-owner-race'),
         resumeSessionId: sessionId,
-        agentOptions: { model: 'mock' },
+        agentOptions: { provider: 'mock', model: 'mock' },
         setup: async () => {
           setupStarted.resolve(undefined)
           await gate.promise
@@ -313,7 +306,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
     await owner.dispose()
     await expect(resuming).rejects.toThrow(/owner disposed during setup/)
     expect(published).toEqual([])
-    expect(ctx.agents.get(AgentId('resume-owner-race'))).toBeUndefined()
+    expect(ctx.agents.get(sessionId)).toBeUndefined()
     expect(ctx.sessions.get(sessionId)).toBeUndefined()
 
     gate.resolve(undefined)
@@ -322,9 +315,8 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
     await ctx.fiber.dispose()
   })
 
-  it('owner unload aborts a never-settling persistence load, releases identities, and blocks late publication', async () => {
+  it('owner unload aborts a never-settling persistence load, releases the identity, and blocks late publication', async () => {
     const sessionId = SessionId('resume-load-owner-unload')
-    const agentId = AgentId('resume-load-race')
     const root = await persistSession(sessionId)
     const ctx = await mountPersistentHarness(root, new MockAdapter([textResponse('next')]))
     const snapshot = await ctx.sessionPersistence.load(sessionId)
@@ -348,19 +340,19 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
 
     let resuming!: ReturnType<typeof ctx.agents.resume>
     const owner = await ctx.plugin(Object.assign((inner: Context) => {
-      resuming = inner.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { model: 'mock' } })
+      resuming = inner.agents.resume({ resumeSessionId: sessionId, agentOptions: { provider: 'mock', model: 'mock' } })
     }, { inject: ['agents'] }))
     await loadStarted.promise
 
     const rejection = expect(promptly(resuming)).rejects.toThrow(/owner disposed during setup/)
     await promptly(owner.dispose())
     expect(published).toEqual([])
-    expect(ctx.agents.get(agentId)).toBeUndefined()
+    expect(ctx.agents.get(sessionId)).toBeUndefined()
     expect(ctx.sessions.get(sessionId)).toBeUndefined()
 
     // owner.dispose() awaited transaction settlement, so the same identities
     // can be reused before awaiting the public rejection.
-    const retry = await promptly(ctx.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { model: 'mock' } }))
+    const retry = await promptly(ctx.agents.resume({ resumeSessionId: sessionId, agentOptions: { provider: 'mock', model: 'mock' } }))
     await rejection
     expect(loads).toBe(2)
     expect(published).toEqual(['session/created', 'agent/created', 'agent/session-start'])
@@ -370,7 +362,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
     lateLoad.resolve(structuredClone(snapshot))
     await Promise.resolve()
     await Promise.resolve()
-    expect(ctx.agents.get(agentId)).toBe(retry.agent)
+    expect(ctx.agents.get(sessionId)).toBe(retry.agent)
     expect(ctx.sessions.get(sessionId)).toBe(retry.agent.session)
     expect(published).toEqual(['session/created', 'agent/created', 'agent/session-start'])
 
@@ -380,7 +372,6 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
 
   it('AgentLoop unload aborts persistence load and awaits wrapper settlement', async () => {
     const sessionId = SessionId('resume-load-factory-unload')
-    const agentId = AgentId('resume-load-factory-race')
     const root = await persistSession(sessionId)
     const ctx = new Context()
     await ctx.plugin(LlmService)
@@ -404,14 +395,14 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
     ctx.on('session/created', () => void published.push('session/created'))
     ctx.on('agent/created', () => void published.push('agent/created'))
 
-    const resuming = ctx.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { model: 'mock' } })
+    const resuming = ctx.agents.resume({ resumeSessionId: sessionId, agentOptions: { provider: 'mock', model: 'mock' } })
     await loadStarted.promise
     const rejection = expect(promptly(resuming)).rejects.toThrow(/agent loop is not active/)
     await promptly(loopFiber.dispose())
     await rejection
 
     expect(published).toEqual([])
-    expect(ctx.agents.get(agentId)).toBeUndefined()
+    expect(ctx.agents.get(sessionId)).toBeUndefined()
     expect(ctx.sessions.get(sessionId)).toBeUndefined()
     lateLoad.resolve(structuredClone(snapshot))
     await Promise.resolve()
@@ -452,7 +443,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
     await ctx2.plugin(AgentLoop, { agents: [] })
     await ctx2.plugin(SessionPersistenceJsonl, { root })
     ctx2.llm.registerAdapter(['mock'], adapter2)
-    const a2 = (await ctx2.agents.resume({ agentId: AgentId('m'), resumeSessionId: SessionId('forked-sess') })).agent as ReactLoopAgent
+    const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('forked-sess') })).agent
     expect(a2.session.header.parentSession).toBe('parent-sess')
     expect(a2.session.header.cwd).toBe('/w')
     expect(a2.session.header.seedLength).toBe(seed.length)
@@ -464,7 +455,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
     // clean disposal follows, so disk presence proves its own checkpoint ran.
     const adapter1 = new MockAdapter([textResponse('answer')])
     const { ctx: ctx1, root } = await persistentHarness(adapter1)
-    const a1 = (await ctx1.agents.create({ agentId: AgentId('m'), sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent as ReactLoopAgent
+    const a1 = (await ctx1.agents.create({ sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent
     a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } })
     await waitForIdle(ctx1, a1)
     a1.inject([{ type: 'text', text: 'background task 42 finished' }], { source: { kind: 'plugin', plugin: 'tool-bash' } })
@@ -487,7 +478,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
     // survive persistence and resume.
     const adapter1 = new MockAdapter([textResponse('answer')])
     const { ctx: ctx1, root } = await persistentHarness(adapter1)
-    const a1 = (await ctx1.agents.create({ agentId: AgentId('m'), sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent as ReactLoopAgent
+    const a1 = (await ctx1.agents.create({ sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent
     a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } })
     await waitForIdle(ctx1, a1)
     a1.inject([{ type: 'text', text: 'background task 42 finished' }], { source: { kind: 'plugin', plugin: 'tool-bash' } })
@@ -505,7 +496,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
     await ctx2.plugin(AgentLoop, { agents: [] })
     await ctx2.plugin(SessionPersistenceJsonl, { root })
     ctx2.llm.registerAdapter(['mock'], adapter2)
-    const a2 = (await ctx2.agents.resume({ agentId: AgentId('m'), resumeSessionId: SessionId('inject-sess') })).agent as ReactLoopAgent
+    const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('inject-sess') })).agent
     const flat = JSON.stringify(a2.session.deriveMessages())
     expect(flat).toContain('background task 42 finished')
     await ctx2.fiber.dispose()
@@ -515,7 +506,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
     // Lifecycle 1: run one full turn, persisting it.
     const adapter1 = new MockAdapter([textResponse('first answer')])
     const { ctx: ctx1, root } = await persistentHarness(adapter1)
-    const a1 = (await ctx1.agents.create({ agentId: AgentId('main'), sessionId: SessionId('sess-resume'), meta: { cwd: '/w' } })).agent as ReactLoopAgent
+    const a1 = (await ctx1.agents.create({ sessionId: SessionId('sess-resume'), meta: { cwd: '/w' } })).agent
     a1.send([{ type: 'text', text: 'first question' }], { source: { kind: 'user' } })
     await waitForIdle(ctx1, a1)
     const events1 = [...a1.session.events]
@@ -535,7 +526,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
     await ctx2.plugin(SessionPersistenceJsonl, { root })
     ctx2.llm.registerAdapter(['mock'], adapter2)
 
-    const a2 = (await ctx2.agents.resume({ agentId: AgentId('main'), resumeSessionId: SessionId('sess-resume') })).agent as ReactLoopAgent
+    const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('sess-resume') })).agent
     // The resumed session carries the prior history…
     expect(a2.session.id).toBe('sess-resume')
     expect(a2.session.events.length).toBe(events1.length)
@@ -563,7 +554,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
     await ctx.plugin(AgentRegistry)
     await ctx.plugin(AgentLoop, { agents: [] })
     ctx.llm.registerAdapter(['mock'], adapter)
-    await expect(ctx.agents.resume({ agentId: AgentId('m'), resumeSessionId: SessionId('nope') }))
+    await expect(ctx.agents.resume({ resumeSessionId: SessionId('nope') }))
       .rejects.toThrow(/session persistence is not configured/)
     await ctx.fiber.dispose()
   })

packages/core/agent-loop/tests/scope-lifecycle.spec.ts

@@ -4,10 +4,11 @@ import LlmService from '@deepseek-ai/dsh-llm'
 import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session'
 import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
 import ToolRegistry from '@deepseek-ai/dsh-tools'
-import AgentRegistry, { AgentId, agentEvents, assembleContextFor } from '@deepseek-ai/dsh-agent'
+import AgentRegistry, { agentEvents, assembleContextFor } from '@deepseek-ai/dsh-agent'
+
 import type { Agent } from '@deepseek-ai/dsh-agent'
 import { scopeOf } from '@deepseek-ai/dsh-scope'
-import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
+import AgentLoop from '@deepseek-ai/dsh-agent-loop'
 import type { ContentBlock } from '@deepseek-ai/dsh-llm'
 import { MockAdapter, textResponse } from './mock-adapter.ts'
 
@@ -27,7 +28,7 @@ async function harness(adapter: MockAdapter = new MockAdapter([textResponse('ok'
   return (await harnessWithLoop(adapter)).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') {
@@ -57,33 +58,31 @@ function disposeCurrentLifecycle(ownerCtx: Context): void {
 }
 
 describe('agent scope lifecycle', () => {
-  it('rejects an already-aborted creation signal before publishing either identity', async () => {
+  it('rejects an already-aborted creation signal before publishing either object', async () => {
     const ctx = await harness()
     const reason = new Error('cancelled before creation')
     const controller = new AbortController()
     controller.abort(reason)
 
     await expect(ctx.agents.create({
-      agentId: AgentId('pre-aborted'),
       sessionId: SessionId('pre-aborted-s'),
       signal: controller.signal,
     })).rejects.toBe(reason)
 
-    expect(ctx.agents.get(AgentId('pre-aborted'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('pre-aborted-s'))).toBeUndefined()
     expect(ctx.sessions.get(SessionId('pre-aborted-s'))).toBeUndefined()
 
     const valueController = new AbortController()
     valueController.abort('plain cancellation reason')
     await expect(ctx.agents.create({
-      agentId: AgentId('pre-aborted-value'),
       sessionId: SessionId('pre-aborted-value-s'),
       signal: valueController.signal,
     })).rejects.toMatchObject({
-      message: 'agent "pre-aborted-value" creation aborted',
+      message: 'agent "pre-aborted-value-s" creation aborted',
       cause: 'plain cancellation reason',
     })
 
-    expect(ctx.agents.get(AgentId('pre-aborted-value'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('pre-aborted-value-s'))).toBeUndefined()
     expect(ctx.sessions.get(SessionId('pre-aborted-value-s'))).toBeUndefined()
     await ctx.fiber.dispose()
   })
@@ -100,12 +99,11 @@ describe('agent scope lifecycle', () => {
     })
 
     await expect(ctx.agents.create({
-      agentId: AgentId('prepare-abort'),
       sessionId: SessionId('prepare-abort-s'),
       signal: controller.signal,
     })).rejects.toBe(reason)
 
-    expect(ctx.agents.get(AgentId('prepare-abort'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('prepare-abort-s'))).toBeUndefined()
     expect(ctx.sessions.get(SessionId('prepare-abort-s'))).toBeUndefined()
     await ctx.fiber.dispose()
   })
@@ -124,7 +122,7 @@ describe('agent scope lifecycle', () => {
     thrown = createFailure
     let createCaught: unknown
     try {
-      ctx.agentLoop.create(AgentId('unknown-create'))
+      ctx.agentLoop.create(SessionId('unknown-create'))
     } catch (error: unknown) {
       createCaught = error
     }
@@ -133,28 +131,45 @@ describe('agent scope lifecycle', () => {
     const ownedFailure = { source: 'createAgent' }
     thrown = ownedFailure
     await expect(ctx.agents.create({
-      agentId: AgentId('unknown-owned-create'),
       sessionId: SessionId('unknown-owned-create-s'),
     })).rejects.toBe(ownedFailure)
 
-    expect(ctx.agents.get(AgentId('unknown-create'))).toBeUndefined()
-    expect(ctx.agents.get(AgentId('unknown-owned-create'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('unknown-create'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('unknown-owned-create-s'))).toBeUndefined()
     await ctx.fiber.dispose()
   })
 
   it('wires agent.ctx: tagged with the agent, DX field set, ctx.agent safe elsewhere', async () => {
     const ctx = await harness()
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
     expect(scopeOf(agent.ctx)).toBe(agent)
     expect(agent.ctx.agent).toBe(agent)
     // The root accessor default: a plain context answers undefined, not a throw.
     expect(ctx.agent).toBeUndefined()
-    await ctx.agents.get(AgentId('a1'))?.whenIdle()
+    await ctx.agents.get(SessionId('a1'))?.whenIdle()
+  })
+
+  it('records agents created through an agent context as non-root runtime children', async () => {
+    const ctx = await harness()
+    const root = await ctx.agents.create({
+      sessionId: SessionId('runtime-root'),
+      agentOptions: { model: 'mock' },
+    })
+    const child = await root.agent.ctx.agents.create({
+      sessionId: SessionId('runtime-child'),
+      agentOptions: { model: 'mock' },
+    })
+
+    expect(ctx.agents.list()).toEqual([root.agent, child.agent])
+    expect(ctx.agents.roots()).toEqual([root.agent])
+
+    await child.dispose()
+    await root.dispose()
   })
 
   it('scoped registrations live in the agent world and die with the agent', async () => {
     const ctx = await harness()
-    const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), agentOptions: { model: 'mock' } })
+    const handle = await ctx.agents.create({ sessionId: SessionId('s1'), agentOptions: { provider: 'mock', model: 'mock' } })
     const { agent } = handle
     agent.ctx.systemPrompt.section({ name: 'deployment:persona', order: 0, text: 'You run tests.' })
     agent.ctx.tools.register({
@@ -179,8 +194,8 @@ describe('agent scope lifecycle', () => {
 
   it('agent.ctx listeners hear only their own agent (scoped dispatch end to end)', async () => {
     const ctx = await harness(new MockAdapter([textResponse('one'), textResponse('two')]))
-    const a = ctx.agentLoop.create(AgentId('a'), { model: 'mock' })
-    const b = ctx.agentLoop.create(AgentId('b'), { model: 'mock' })
+    const a = ctx.agentLoop.create(SessionId('a'), { provider: 'mock', model: 'mock' })
+    const b = ctx.agentLoop.create(SessionId('b'), { provider: 'mock', model: 'mock' })
 
     const heard: string[] = []
     a.ctx.on('agent/status', (subject, status) => void heard.push(`a-sees:${subject.id}:${status}`))
@@ -210,9 +225,8 @@ describe('agent scope lifecycle', () => {
     })
 
     const handle = await ctx.agents.create({
-      agentId: AgentId('child'),
       sessionId: SessionId('child-s'),
-      agentOptions: { model: 'mock' },
+      agentOptions: { provider: 'mock', model: 'mock' },
       setup: async (agentCtx) => {
         order.push('setup')
         await Promise.resolve()
@@ -224,26 +238,25 @@ describe('agent scope lifecycle', () => {
     await handle.dispose()
   })
 
-  it('keeps both identities unpublished until async setup completes, then announces in order', async () => {
+  it('keeps both objects unpublished until async setup completes, then announces in order', async () => {
     const ctx = await harness()
     const gate = Promise.withResolvers<undefined>()
     const setupStarted = Promise.withResolvers<undefined>()
     const order: string[] = []
     ctx.on('session/created', (session) => {
       expect(ctx.sessions.get(session.id)).toBe(session)
-      expect(ctx.agents.get(AgentId('atomic'))?.session).toBe(session)
+      expect(ctx.agents.get(session.id)?.session).toBe(session)
       order.push('session/created')
     })
     ctx.on('agent/created', () => void order.push('agent/created'))
     ctx.on('agent/session-start', () => void order.push('agent/session-start'))
-    const acceptedOptions = { model: 'mock' }
+    const acceptedOptions = { provider: 'mock', model: 'mock' }
 
     const creating = ctx.agents.create({
-      agentId: AgentId('atomic'),
-      sessionId: SessionId('atomic-s'),
+      sessionId: SessionId('atomic'),
       agentOptions: acceptedOptions,
       setup: async (agentCtx) => {
-        expect(agentCtx.agent?.id).toBe(AgentId('atomic'))
+        expect(agentCtx.agent?.id).toBe(SessionId('atomic'))
         agentCtx.on('session/created', () => void order.push('setup-listener:session/created'))
         agentCtx.on('agent/created', () => void order.push('setup-listener:agent/created'))
         order.push('setup:start')
@@ -253,8 +266,8 @@ describe('agent scope lifecycle', () => {
       },
     })
     await setupStarted.promise
-    expect(ctx.agents.get(AgentId('atomic'))).toBeUndefined()
-    expect(ctx.sessions.get(SessionId('atomic-s'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('atomic'))).toBeUndefined()
+    expect(ctx.sessions.get(SessionId('atomic'))).toBeUndefined()
     expect(order).toEqual(['setup:start'])
     gate.resolve(undefined)
     const handle = await creating
@@ -281,17 +294,15 @@ describe('agent scope lifecycle', () => {
       if (started === 2) bothStarted.resolve(undefined)
       await gate.promise
     }
-    const agentId = AgentId('concurrent-final-enter')
+    const sessionId = SessionId('concurrent-final-enter')
     const first = ctx.agents.create({
-      agentId,
-      sessionId: SessionId('concurrent-final-enter-a'),
-      agentOptions: { model: 'mock' },
+      sessionId,
+      agentOptions: { provider: 'mock', model: 'mock' },
       setup,
     })
     const second = ctx.agents.create({
-      agentId,
-      sessionId: SessionId('concurrent-final-enter-b'),
-      agentOptions: { model: 'mock' },
+      sessionId,
+      agentOptions: { provider: 'mock', model: 'mock' },
       setup,
     })
     await bothStarted.promise
@@ -304,7 +315,7 @@ describe('agent scope lifecycle', () => {
     const rejected = outcomes.filter((outcome): outcome is PromiseRejectedResult => outcome.status === 'rejected')
     expect(fulfilled).toHaveLength(1)
     expect(rejected).toHaveLength(1)
-    expect(String(rejected[0]!.reason)).toMatch(/already registered/)
+    expect(String(rejected[0]!.reason)).toMatch(/already exists/)
     expect(ctx.agents.list()).toEqual([fulfilled[0]!.value.agent])
     expect(ctx.sessions.list()).toEqual([fulfilled[0]!.value.agent.session])
 
@@ -318,9 +329,8 @@ describe('agent scope lifecycle', () => {
     const pendingController = new AbortController()
     const setupStarted = Promise.withResolvers<undefined>()
     const pending = ctx.agents.create({
-      agentId: AgentId('signal-pending'),
       sessionId: SessionId('signal-pending-s'),
-      agentOptions: { model: 'mock' },
+      agentOptions: { provider: 'mock', model: 'mock' },
       signal: pendingController.signal,
       setup: async () => {
         setupStarted.resolve(undefined)
@@ -330,14 +340,13 @@ describe('agent scope lifecycle', () => {
     await setupStarted.promise
     pendingController.abort(new Error('cancel pending creation'))
     await expect(pending).rejects.toThrow('cancel pending creation')
-    expect(ctx.agents.get(AgentId('signal-pending'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('signal-pending-s'))).toBeUndefined()
     expect(ctx.sessions.get(SessionId('signal-pending-s'))).toBeUndefined()
 
     const liveController = new AbortController()
     const live = await ctx.agents.create({
-      agentId: AgentId('signal-live'),
       sessionId: SessionId('signal-live-s'),
-      agentOptions: { model: 'mock' },
+      agentOptions: { provider: 'mock', model: 'mock' },
       signal: liveController.signal,
     })
     liveController.abort(new Error('too late'))
@@ -358,9 +367,8 @@ describe('agent scope lifecycle', () => {
     let creating!: ReturnType<typeof ctx.agents.create>
     const owner = await ctx.plugin(Object.assign((inner: Context) => {
       creating = inner.agents.create({
-        agentId: AgentId('owner-race'),
         sessionId: SessionId('owner-race-s'),
-        agentOptions: { model: 'mock' },
+        agentOptions: { provider: 'mock', model: 'mock' },
         setup: async () => {
           setupStarted.resolve(undefined)
           await gate.promise
@@ -372,7 +380,7 @@ describe('agent scope lifecycle', () => {
     await owner.dispose()
     await expect(creating).rejects.toThrow(/owner disposed during setup/)
     expect(published).toEqual([])
-    expect(ctx.agents.get(AgentId('owner-race'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('owner-race-s'))).toBeUndefined()
     expect(ctx.sessions.get(SessionId('owner-race-s'))).toBeUndefined()
     // Let the losing callback settle; Promise.race already observes it.
     gate.resolve(undefined)
@@ -386,9 +394,8 @@ describe('agent scope lifecycle', () => {
     let creating2!: ReturnType<typeof ctx.agents.create>
     const owner2 = await ctx.plugin(Object.assign((inner: Context) => {
       creating2 = inner.agents.create({
-        agentId: AgentId('owner-race-2'),
         sessionId: SessionId('owner-race-s-2'),
-        agentOptions: { model: 'mock' },
+        agentOptions: { provider: 'mock', model: 'mock' },
         setup: async () => {
           setupStarted2.resolve(undefined)
           await gate2.promise
@@ -400,7 +407,7 @@ describe('agent scope lifecycle', () => {
     const unload2 = owner2.dispose()
     await expect(creating2).rejects.toThrow(/owner disposed during setup/)
     await unload2
-    expect(ctx.agents.get(AgentId('owner-race-2'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('owner-race-s-2'))).toBeUndefined()
     expect(ctx.sessions.get(SessionId('owner-race-s-2'))).toBeUndefined()
   })
 
@@ -413,9 +420,8 @@ describe('agent scope lifecycle', () => {
     ctx.on('agent/created', () => void published.push('agent/created'))
 
     const creating = ctx.agents.create({
-      agentId: AgentId('factory-setup-race'),
       sessionId: SessionId('factory-setup-race-s'),
-      agentOptions: { model: 'mock' },
+      agentOptions: { provider: 'mock', model: 'mock' },
       setup: async () => {
         setupStarted.resolve(undefined)
         await gate.promise
@@ -426,7 +432,7 @@ describe('agent scope lifecycle', () => {
     await loopFiber.dispose()
     await expect(creating).rejects.toThrow(/agent loop is not active/)
     expect(published).toEqual([])
-    expect(ctx.agents.get(AgentId('factory-setup-race'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('factory-setup-race-s'))).toBeUndefined()
     expect(ctx.sessions.get(SessionId('factory-setup-race-s'))).toBeUndefined()
 
     gate.resolve(undefined)
@@ -444,15 +450,14 @@ describe('agent scope lifecycle', () => {
     })
 
     const creating = ctx.agents.create({
-      agentId: AgentId('factory-scope-race'),
       sessionId: SessionId('factory-scope-race-s'),
-      agentOptions: { model: 'mock' },
+      agentOptions: { provider: 'mock', model: 'mock' },
       setup: () => { setupCalls += 1 },
     })
     await expect(creating).rejects.toThrow(/agent loop is not active/)
     await loopFiber.dispose()
     expect(setupCalls).toBe(0)
-    expect(ctx.agents.get(AgentId('factory-scope-race'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('factory-scope-race-s'))).toBeUndefined()
     expect(ctx.sessions.get(SessionId('factory-scope-race-s'))).toBeUndefined()
 
     await ctx.fiber.dispose()
@@ -479,9 +484,8 @@ describe('agent scope lifecycle', () => {
     const owner = ctx.plugin(Object.assign((inner: Context) => {
       ownerFiber = inner.fiber
       creating = inner.agents.create({
-        agentId: AgentId('caller-scope-race'),
         sessionId: SessionId('caller-scope-race-s'),
-        agentOptions: { model: 'mock' },
+        agentOptions: { provider: 'mock', model: 'mock' },
       })
     }, { inject: ['agents'] }))
 
@@ -495,7 +499,7 @@ describe('agent scope lifecycle', () => {
     await ownerDisposal
     await owner
     expect(scopeFiber?.uid).toBeNull()
-    expect(ctx.agents.get(AgentId('caller-scope-race'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('caller-scope-race-s'))).toBeUndefined()
     expect(ctx.sessions.get(SessionId('caller-scope-race-s'))).toBeUndefined()
     await owner.dispose()
     await ctx.fiber.dispose()
@@ -511,21 +515,21 @@ describe('agent scope lifecycle', () => {
       void loopFiber.dispose()
     })
 
-    expect(() => ctx.agentLoop.create(AgentId('config-scope-race'), { model: 'mock' }))
+    expect(() => ctx.agentLoop.create(SessionId('config-scope-race'), { provider: 'mock', model: 'mock' }))
       .toThrow(/agent loop is not active/)
     await loopFiber.dispose()
-    expect(ctx.agents.get(AgentId('config-scope-race'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('config-scope-race'))).toBeUndefined()
     expect(ctx.sessions.list()).toHaveLength(sessionsBefore)
     await ctx.fiber.dispose()
   })
 
   it('synchronous create leaves no lifecycle state when session preparation fails', async () => {
     const ctx = await harness()
-    const id = AgentId('config-prepare-failure')
+    const id = SessionId('config-prepare-failure')
 
-    expect(() => ctx.agentLoop.create(id, { model: 'mock' }, { cwd: 'relative' }))
+    expect(() => ctx.agentLoop.create(id, { provider: 'mock', model: 'mock' }, { cwd: 'relative' }))
       .toThrow(/absolute path/)
-    const replacement = ctx.agentLoop.create(id, { model: 'mock' }, { cwd: '/recovered' })
+    const replacement = ctx.agentLoop.create(id, { provider: 'mock', model: 'mock' }, { cwd: '/recovered' })
     expect(ctx.agents.get(id)).toBe(replacement)
     await replacement.whenIdle()
     await ctx.fiber.dispose()
@@ -542,12 +546,11 @@ describe('agent scope lifecycle', () => {
     })
 
     await expect(ctx.agents.create({
-      agentId: AgentId('factory-scope-throw'),
       sessionId: SessionId('factory-scope-throw-s'),
-      agentOptions: { model: 'mock' },
+      agentOptions: { provider: 'mock', model: 'mock' },
     })).rejects.toThrow('scope preparation failed')
     await loopFiber.dispose()
-    expect(ctx.agents.get(AgentId('factory-scope-throw'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('factory-scope-throw-s'))).toBeUndefined()
     expect(ctx.sessions.get(SessionId('factory-scope-throw-s'))).toBeUndefined()
 
     await ctx.fiber.dispose()
@@ -556,23 +559,21 @@ describe('agent scope lifecycle', () => {
   it('AgentLoop unload is a structural co-owner of every live programmatic agent', async () => {
     const { ctx, loopFiber } = await harnessWithLoop()
     const loop = ctx.agentLoop
-    const agentId = AgentId('factory-live')
+    const sessionId = SessionId('factory-live')
     const handle = await ctx.agents.create({
-      agentId,
       sessionId: SessionId('factory-live-s'),
-      agentOptions: { model: 'mock' },
+      agentOptions: { provider: 'mock', model: 'mock' },
     })
 
     await loopFiber.dispose()
     expect(handle.agent.status).toBe('disposed')
-    expect(ctx.agents.get(agentId)).toBeUndefined()
-    expect(ctx.sessions.get(SessionId('factory-live-s'))).toBeUndefined()
-    expect(ctx.fiber.getEffects().filter(effect => effect.label === `agentLoop.owner(${agentId})`)).toEqual([])
+    expect(ctx.agents.get(sessionId)).toBeUndefined()
+    expect(ctx.sessions.get(sessionId)).toBeUndefined()
+    expect(ctx.fiber.getEffects().filter(effect => effect.label === `agentLoop.owner(${sessionId})`)).toEqual([])
     // The consumer handle shares the provider's completed quiescence boundary.
     await handle.dispose()
 
     await expect(loop.createAgent(ctx, {
-      agentId: AgentId('factory-inactive'),
       sessionId: SessionId('factory-inactive-s'),
     })).rejects.toThrow('agent loop is not active')
     await ctx.fiber.dispose()
@@ -583,9 +584,8 @@ describe('agent scope lifecycle', () => {
     let creating!: ReturnType<typeof ctx.agents.create>
     const owner = await ctx.plugin(Object.assign((inner: Context) => {
       creating = inner.agents.create({
-        agentId: AgentId('dependency-origin'),
         sessionId: SessionId('dependency-origin-s'),
-        agentOptions: { model: 'mock' },
+        agentOptions: { provider: 'mock', model: 'mock' },
         setup: (agentCtx) => {
           agentCtx.tools.register({
             name: 'dependency-origin-tool',
@@ -623,7 +623,7 @@ describe('agent scope lifecycle', () => {
     })
     ctx.on('session/created', (session) => {
       if (session.id !== SessionId('session-created-barrier-s')) return
-      const agent = ctx.agents.get(AgentId('session-created-barrier'))!
+      const agent = ctx.agents.get(SessionId('session-created-barrier-s'))!
       expect(ctx.sessions.get(session.id)).toBe(session)
       expect(agent.session).toBe(session)
       agent.ctx.effect(() => () => { lifecycle.push('scope-disposed') })
@@ -638,9 +638,8 @@ describe('agent scope lifecycle', () => {
     const owner = await ctx.plugin(Object.assign((inner: Context) => {
       ownerCtx = inner
       creating = inner.agents.create({
-        agentId: AgentId('session-created-barrier'),
         sessionId: SessionId('session-created-barrier-s'),
-        agentOptions: { model: 'mock' },
+        agentOptions: { provider: 'mock', model: 'mock' },
       })
     }, { inject: ['agents'] }))
 
@@ -652,7 +651,7 @@ describe('agent scope lifecycle', () => {
       'session-disposed',
       'scope-disposed',
     ])
-    expect(ctx.agents.get(AgentId('session-created-barrier'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('session-created-barrier-s'))).toBeUndefined()
     expect(ctx.sessions.get(SessionId('session-created-barrier-s'))).toBeUndefined()
     await ctx.fiber.dispose()
   })
@@ -666,19 +665,19 @@ describe('agent scope lifecycle', () => {
       if (session.id === SessionId('agent-created-barrier-s')) lifecycle.push('session-created')
     })
     ctx.on('agent/created', (agent) => {
-      if (agent.id !== AgentId('agent-created-barrier')) return
+      if (agent.id !== SessionId('agent-created-barrier-s')) return
       lifecycle.push('agent-created:dispose')
       disposeCurrentLifecycle(ownerCtx)
     })
     ctx.on('agent/created', (agent) => {
-      if (agent.id !== AgentId('agent-created-barrier')) return
+      if (agent.id !== SessionId('agent-created-barrier-s')) return
       expect(ctx.agents.get(agent.id)).toBe(agent)
       expect(ctx.sessions.get(agent.session.id)).toBe(agent.session)
       agent.ctx.effect(() => () => { lifecycle.push('scope-disposed') })
       lifecycle.push('agent-created:observer')
     })
     ctx.on('agent/disposed', (agent) => {
-      if (agent.id === AgentId('agent-created-barrier')) lifecycle.push('agent-disposed')
+      if (agent.id === SessionId('agent-created-barrier-s')) lifecycle.push('agent-disposed')
     })
     ctx.on('session/disposed', (session) => {
       if (session.id === SessionId('agent-created-barrier-s')) lifecycle.push('session-disposed')
@@ -687,9 +686,8 @@ describe('agent scope lifecycle', () => {
     const owner = await ctx.plugin(Object.assign((inner: Context) => {
       ownerCtx = inner
       creating = inner.agents.create({
-        agentId: AgentId('agent-created-barrier'),
         sessionId: SessionId('agent-created-barrier-s'),
-        agentOptions: { model: 'mock' },
+        agentOptions: { provider: 'mock', model: 'mock' },
       })
     }, { inject: ['agents'] }))
 
@@ -703,7 +701,7 @@ describe('agent scope lifecycle', () => {
       'session-disposed',
       'scope-disposed',
     ])
-    expect(ctx.agents.get(AgentId('agent-created-barrier'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('agent-created-barrier-s'))).toBeUndefined()
     expect(ctx.sessions.get(SessionId('agent-created-barrier-s'))).toBeUndefined()
     await ctx.fiber.dispose()
   })
@@ -715,22 +713,21 @@ describe('agent scope lifecycle', () => {
     let creating!: ReturnType<typeof ctx.agents.create>
     ctx.on('agent/session-start', agent => void starts.push(agent.id))
     ctx.on('agent/created', (agent) => {
-      if (agent.id === AgentId('listener-dispose')) void ownerCtx.fiber.dispose()
+      if (agent.id === SessionId('listener-dispose-s')) void ownerCtx.fiber.dispose()
     })
 
     const owner = await ctx.plugin(Object.assign((inner: Context) => {
       ownerCtx = inner
       creating = inner.agents.create({
-        agentId: AgentId('listener-dispose'),
         sessionId: SessionId('listener-dispose-s'),
-        agentOptions: { model: 'mock' },
+        agentOptions: { provider: 'mock', model: 'mock' },
       })
     }, { inject: ['agents'] }))
 
     await expect(creating).rejects.toThrow(/owner disposed during setup/)
     await owner.dispose()
     expect(starts).toEqual([])
-    expect(ctx.agents.get(AgentId('listener-dispose'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('listener-dispose-s'))).toBeUndefined()
     expect(ctx.sessions.get(SessionId('listener-dispose-s'))).toBeUndefined()
     await ctx.fiber.dispose()
   })
@@ -739,20 +736,20 @@ describe('agent scope lifecycle', () => {
     const ctx = await harness()
     let ownerCtx!: Context
     let creating!: ReturnType<typeof ctx.agents.create>
-    let announced!: ReactLoopAgent
+    let announced!: Agent
     const statuses: string[] = []
     let scopeDisposed = false
     let observerSawLive = false
     ctx.on('agent/status', (agent, status) => {
-      if (agent.id === AgentId('session-start-dispose')) statuses.push(status)
+      if (agent.id === SessionId('session-start-dispose-s')) statuses.push(status)
     })
     ctx.on('agent/session-start', (agent) => {
-      if (agent.id !== AgentId('session-start-dispose')) return
-      announced = agent as ReactLoopAgent
+      if (agent.id !== SessionId('session-start-dispose-s')) return
+      announced = agent
       disposeCurrentLifecycle(ownerCtx)
     })
     ctx.on('agent/session-start', (agent) => {
-      if (agent.id !== AgentId('session-start-dispose')) return
+      if (agent.id !== SessionId('session-start-dispose-s')) return
       expect(ctx.agents.get(agent.id)).toBe(agent)
       expect(ctx.sessions.get(agent.session.id)).toBe(agent.session)
       agent.ctx.effect(() => () => { scopeDisposed = true })
@@ -762,9 +759,8 @@ describe('agent scope lifecycle', () => {
     const owner = await ctx.plugin(Object.assign((inner: Context) => {
       ownerCtx = inner
       creating = inner.agents.create({
-        agentId: AgentId('session-start-dispose'),
         sessionId: SessionId('session-start-dispose-s'),
-        agentOptions: { model: 'mock' },
+        agentOptions: { provider: 'mock', model: 'mock' },
       })
     }, { inject: ['agents'] }))
 
@@ -775,7 +771,7 @@ describe('agent scope lifecycle', () => {
     expect(observerSawLive).toBe(true)
     expect(scopeDisposed).toBe(true)
     expect(announced.session.events).toEqual([])
-    expect(ctx.agents.get(AgentId('session-start-dispose'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('session-start-dispose-s'))).toBeUndefined()
     expect(ctx.sessions.get(SessionId('session-start-dispose-s'))).toBeUndefined()
     await ctx.fiber.dispose()
   })
@@ -787,9 +783,8 @@ describe('agent scope lifecycle', () => {
     ctx.on('agent/created', () => void published.push('agent/created'))
     ctx.on('agent/session-start', () => void published.push('agent/session-start'))
     await expect(ctx.agents.create({
-      agentId: AgentId('bad'),
       sessionId: SessionId('bad-s'),
-      agentOptions: { model: 'mock' },
+      agentOptions: { provider: 'mock', model: 'mock' },
       setup: async () => {
         await Promise.resolve()
         throw new Error('boom setup')
@@ -798,13 +793,13 @@ describe('agent scope lifecycle', () => {
 
     // Nothing leaked: no agent, no session, and the ids are reusable.
     expect(published).toEqual([])
-    expect(ctx.agents.get(AgentId('bad'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('bad-s'))).toBeUndefined()
     expect(ctx.sessions.get(SessionId('bad-s'))).toBeUndefined()
-    const retry = await ctx.agents.create({ agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' } })
+    const retry = await ctx.agents.create({ sessionId: SessionId('bad-s'), agentOptions: { provider: 'mock', model: 'mock' } })
     await retry.dispose()
   })
 
-  it('rejects an exotic durable seed before publishing either identity', async () => {
+  it('rejects an exotic durable seed before publishing either object', async () => {
     const ctx = await harness()
     const published: string[] = []
     ctx.on('session/created', () => { published.push('session') })
@@ -817,19 +812,17 @@ describe('agent scope lifecycle', () => {
     }] as unknown as SessionEvent[]
 
     await expect(ctx.agents.create({
-      agentId: AgentId('exotic-seed'),
       sessionId: SessionId('exotic-seed-session'),
-      agentOptions: { model: 'mock' },
+      agentOptions: { provider: 'mock', model: 'mock' },
       seed,
     })).rejects.toThrow(/seed event at index 0 is not losslessly JSON-serializable/)
 
     expect(published).toEqual([])
-    expect(ctx.agents.get(AgentId('exotic-seed'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('exotic-seed-session'))).toBeUndefined()
     expect(ctx.sessions.get(SessionId('exotic-seed-session'))).toBeUndefined()
     const retry = await ctx.agents.create({
-      agentId: AgentId('exotic-seed'),
       sessionId: SessionId('exotic-seed-session'),
-      agentOptions: { model: 'mock' },
+      agentOptions: { provider: 'mock', model: 'mock' },
     })
     await retry.dispose()
   })
@@ -843,13 +836,13 @@ describe('agent scope lifecycle', () => {
       if (boom) { boom = false; throw new Error('boom created') }
     })
     await expect(ctx.agents.create({
-      agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' },
+      sessionId: SessionId('bad-s'), agentOptions: { provider: 'mock', model: 'mock' },
     })).rejects.toThrow('boom created')
-    expect(ctx.agents.get(AgentId('bad'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('bad-s'))).toBeUndefined()
     expect(ctx.sessions.get(SessionId('bad-s'))).toBeUndefined()
     expect(disposed).toEqual([]) // inserted but never announced: no impossible disposed edge
     // The rollback also disposed the scope fiber: re-creating works cleanly.
-    const retry = await ctx.agents.create({ agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' } })
+    const retry = await ctx.agents.create({ sessionId: SessionId('bad-s'), agentOptions: { provider: 'mock', model: 'mock' } })
     expect(scopeOf(retry.agent.ctx)).toBe(retry.agent)
     await retry.dispose()
   })
@@ -866,18 +859,17 @@ describe('agent scope lifecycle', () => {
     ctx.on('agent/disposed', (agent) => { lifecycle.push(`agent-disposed:${agent.id}`) })
 
     await expect(ctx.agents.create({
-      agentId: AgentId('partial-agent'),
       sessionId: SessionId('partial-session'),
-      agentOptions: { model: 'mock' },
+      agentOptions: { provider: 'mock', model: 'mock' },
     })).rejects.toThrow('agent observer failed')
 
     expect(lifecycle).toEqual([
       'session-created:partial-session',
-      'agent-created:partial-agent',
-      'agent-disposed:partial-agent',
+      'agent-created:partial-session',
+      'agent-disposed:partial-session',
       'session-disposed:partial-session',
     ])
-    expect(ctx.agents.get(AgentId('partial-agent'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('partial-session'))).toBeUndefined()
     expect(ctx.sessions.get(SessionId('partial-session'))).toBeUndefined()
   })
 
@@ -892,23 +884,23 @@ describe('agent scope lifecycle', () => {
       }
     })
 
-    expect(() => ctx.agentLoop.create(AgentId('config-bad'), { model: 'mock' }))
+    expect(() => ctx.agentLoop.create(SessionId('config-bad'), { provider: 'mock', model: 'mock' }))
       .toThrow('config publish failed')
-    expect(ctx.agents.get(AgentId('config-bad'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('config-bad'))).toBeUndefined()
     expect(ctx.sessions.list()).toHaveLength(sessionsBefore)
   })
 
   it('registrations through a disposed agent ctx throw INACTIVE_EFFECT', async () => {
     const ctx = await harness()
-    const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), agentOptions: { model: 'mock' } })
+    const handle = await ctx.agents.create({ sessionId: SessionId('s1'), agentOptions: { provider: 'mock', model: 'mock' } })
     await handle.dispose()
     expect(() => handle.agent.ctx.on('agent/status', () => {})).toThrow(/inactive context/)
   })
 
   it('agentEvents fuses carrier and subject for custom drivers', async () => {
     const ctx = await harness()
-    const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
-    const other = ctx.agentLoop.create(AgentId('a2'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
+    const other = ctx.agentLoop.create(SessionId('a2'), { provider: 'mock', model: 'mock' })
     const heard: string[] = []
     agent.ctx.on('agent/error', (subject: Agent, turn: number) => void heard.push(`${subject.id}:${turn}`))
 
@@ -921,7 +913,7 @@ describe('agent scope lifecycle', () => {
     const ctx = await harness()
     let handle!: Awaited<ReturnType<typeof ctx.agents.create>>
     const owner = await ctx.plugin(Object.assign(async (inner: Context) => {
-      handle = await inner.agents.create({ agentId: AgentId('o1'), sessionId: SessionId('o1-s'), agentOptions: { model: 'mock' } })
+      handle = await inner.agents.create({ sessionId: SessionId('o1-s'), agentOptions: { provider: 'mock', model: 'mock' } })
     }, { inject: ['agents'] }))
     const { agent } = handle
 
@@ -930,7 +922,7 @@ describe('agent scope lifecycle', () => {
       if (event.type === 'turn/end') order.push('turn-end')
     })
     ctx.on('agent/disposed', () => {
-      order.push(`disposed(listed=${ctx.agents.get(AgentId('o1')) !== undefined})`)
+      order.push(`disposed(listed=${ctx.agents.get(SessionId('o1-s')) !== undefined})`)
       order.push(`session-still-stored=${ctx.sessions.get(SessionId('o1-s')) !== undefined}`)
     })
 
@@ -953,7 +945,7 @@ describe('agent scope lifecycle', () => {
     const ctx = await harness()
     let handle!: Awaited<ReturnType<typeof ctx.agents.create>>
     const owner = await ctx.plugin(Object.assign(async (inner: Context) => {
-      handle = await inner.agents.create({ agentId: AgentId('h1'), sessionId: SessionId('h1-s'), agentOptions: { model: 'mock' } })
+      handle = await inner.agents.create({ sessionId: SessionId('h1-s'), agentOptions: { provider: 'mock', model: 'mock' } })
     }, { inject: ['agents'] }))
 
     const teardownDone: string[] = []
@@ -965,23 +957,22 @@ describe('agent scope lifecycle', () => {
     // actually finished (the raw wrapper returns undefined on a repeat call).
     await handle.dispose()
     expect(teardownDone).toContain('unregistered')
-    expect(ctx.agents.get(AgentId('h1'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('h1-s'))).toBeUndefined()
     expect(ctx.sessions.get(SessionId('h1-s'))).toBeUndefined()
     await unload
   })
 
   it('successful handle disposal retires its caller ownership effect', async () => {
     const ctx = await harness()
-    const agentId = AgentId('retired-owner-effect')
+    const sessionId = SessionId('retired-owner-effect')
     const handle = await ctx.agents.create({
-      agentId,
-      sessionId: SessionId('retired-owner-effect-s'),
-      agentOptions: { model: 'mock' },
+      sessionId,
+      agentOptions: { provider: 'mock', model: 'mock' },
     })
 
-    expect(ctx.fiber.getEffects().map(effect => effect.label)).toContain(`agentLoop.owner(${agentId})`)
+    expect(ctx.fiber.getEffects().map(effect => effect.label)).toContain(`agentLoop.owner(${sessionId})`)
     await handle.dispose()
-    expect(ctx.fiber.getEffects().filter(effect => effect.label === `agentLoop.owner(${agentId})`)).toEqual([])
+    expect(ctx.fiber.getEffects().filter(effect => effect.label === `agentLoop.owner(${sessionId})`)).toEqual([])
     await ctx.fiber.dispose()
   })
 
@@ -992,9 +983,8 @@ describe('agent scope lifecycle', () => {
     let handle!: Awaited<ReturnType<typeof ctx.agents.create>>
     const owner = await ctx.plugin(Object.assign(async (inner: Context) => {
       handle = await inner.agents.create({
-        agentId: AgentId('manual-first'),
         sessionId: SessionId('manual-first-s'),
-        agentOptions: { model: 'mock' },
+        agentOptions: { provider: 'mock', model: 'mock' },
         setup(agentCtx) {
           agentCtx.effect(() => async () => {
             cleanupStarted.resolve(undefined)
@@ -1012,7 +1002,7 @@ describe('agent scope lifecycle', () => {
     expect(ownerSettled).toBe(false)
     gate.resolve(undefined)
     await Promise.all([disposing, unloading])
-    expect(ctx.agents.get(AgentId('manual-first'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('manual-first-s'))).toBeUndefined()
     expect(ctx.sessions.get(SessionId('manual-first-s'))).toBeUndefined()
     await ctx.fiber.dispose()
   })
@@ -1022,15 +1012,13 @@ describe('agent scope lifecycle', () => {
     const gate = Promise.withResolvers<undefined>()
     const cleanupStarted = Promise.withResolvers<undefined>()
     const sessionDisposed = Promise.withResolvers<undefined>()
-    const agentId = AgentId('quiescent-reuse')
-    const sessionId = SessionId('quiescent-reuse-s')
+    const sessionId = SessionId('quiescent-reuse')
     ctx.on('session/disposed', (session) => {
       if (session.id === sessionId) sessionDisposed.resolve(undefined)
     })
     const first = await ctx.agents.create({
-      agentId,
       sessionId,
-      agentOptions: { model: 'mock' },
+      agentOptions: { provider: 'mock', model: 'mock' },
       setup(agentCtx) {
         agentCtx.effect(() => async () => {
           cleanupStarted.resolve(undefined)
@@ -1041,10 +1029,10 @@ describe('agent scope lifecycle', () => {
 
     const disposing = first.dispose()
     await Promise.all([sessionDisposed.promise, cleanupStarted.promise])
-    expect(ctx.agents.get(agentId)).toBeUndefined()
+    expect(ctx.agents.get(sessionId)).toBeUndefined()
     expect(ctx.sessions.get(sessionId)).toBeUndefined()
-    const replacement = await ctx.agents.create({ agentId, sessionId, agentOptions: { model: 'mock' } })
-    expect(ctx.agents.get(agentId)).toBe(replacement.agent)
+    const replacement = await ctx.agents.create({ sessionId, agentOptions: { provider: 'mock', model: 'mock' } })
+    expect(ctx.agents.get(sessionId)).toBe(replacement.agent)
     expect(ctx.sessions.get(sessionId)).toBe(replacement.agent.session)
 
     gate.resolve(undefined)
@@ -1056,9 +1044,8 @@ describe('agent scope lifecycle', () => {
   it('handle.dispose() awaits an idle-injection flush before unregistering or detaching', async () => {
     const ctx = await harness()
     const handle = await ctx.agents.create({
-      agentId: AgentId('idle-flush'),
       sessionId: SessionId('idle-flush-s'),
-      agentOptions: { model: 'mock' },
+      agentOptions: { provider: 'mock', model: 'mock' },
     })
     const gate = Promise.withResolvers<undefined>()
     let flushStarted = false
@@ -1075,12 +1062,12 @@ describe('agent scope lifecycle', () => {
     const disposal = handle.dispose().then(() => { disposed = true })
     await new Promise(resolve => setTimeout(resolve, 0))
     expect(disposed).toBe(false)
-    expect(ctx.agents.get(AgentId('idle-flush'))).toBe(handle.agent)
+    expect(ctx.agents.get(SessionId('idle-flush-s'))).toBe(handle.agent)
     expect(ctx.sessions.get(SessionId('idle-flush-s'))).toBe(handle.agent.session)
 
     gate.resolve(undefined)
     await disposal
-    expect(ctx.agents.get(AgentId('idle-flush'))).toBeUndefined()
+    expect(ctx.agents.get(SessionId('idle-flush-s'))).toBeUndefined()
     expect(ctx.sessions.get(SessionId('idle-flush-s'))).toBeUndefined()
   })
 })

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

@@ -0,0 +1,588 @@
+/**
+ * Exercises scheduler ordering and cancellation with deterministic gated tools.
+ * ACP expected outputs own transcript-facing coverage.
+ */
+
+import { describe, expect, it } from 'vitest'
+import { Context } from 'cordis'
+import { CallId, StreamChunk } from '@deepseek-ai/dsh-llm'
+import SessionStore, { SessionEvent, SessionId } from '@deepseek-ai/dsh-session'
+import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
+import LlmService from '@deepseek-ai/dsh-llm'
+import ToolRegistry, { defineTool, type PostToolDecision, type PreToolDecision } from '@deepseek-ai/dsh-tools'
+import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
+import AgentLoop from '@deepseek-ai/dsh-agent-loop'
+import { MockAdapter, textResponse } from './mock-adapter.ts'
+
+async function harness(adapter: MockAdapter, maxParallelToolCalls?: number) {
+  const ctx = new Context()
+  await ctx.plugin(LlmService)
+  await ctx.plugin(SessionStore)
+  await ctx.plugin(SystemPrompt, { persona: '' })
+  await ctx.plugin(ToolRegistry)
+  await ctx.plugin(AgentRegistry)
+  await ctx.plugin(AgentLoop, {
+    agents: [],
+    ...maxParallelToolCalls === undefined ? {} : { maxParallelToolCalls },
+  })
+  ctx.llm.registerAdapter(['mock'], adapter)
+  return ctx
+}
+
+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') { dispose(); resolve() }
+    })
+  })
+}
+
+function events(agent: Agent): SessionEvent[] {
+  return [...agent.session.events]
+}
+
+/** Build one assistant response containing the supplied tool calls. */
+function multiCall(calls: { id: string; name: string; args: object }[]): StreamChunk[] {
+  const chunks: StreamChunk[] = []
+  calls.forEach((call, index) => {
+    chunks.push(
+      { type: 'block-start', index, blockType: 'tool-call' },
+      { type: 'block-end', index, block: { type: 'tool-call', id: CallId(call.id), name: call.name, arguments: JSON.stringify(call.args) } },
+    )
+  })
+  chunks.push(
+    { type: 'usage', usage: { inputTokens: 5, outputTokens: 5 } },
+    { type: 'finish', reason: { kind: 'tool-calls' } },
+  )
+  return chunks
+}
+
+/** A tool whose calls block until the test releases them by callId. */
+function gatedTool(name: string, parallel: boolean) {
+  const gates = new Map<string, () => void>()
+  const started: string[] = []
+  const tool = defineTool({
+    name,
+    description: `gated ${name}`,
+    parameters: { id: { type: 'string', required: true } },
+    ...parallel ? { isConcurrencySafe: () => true } : {},
+    async execute(args) {
+      started.push(args.id)
+      await new Promise<void>((resolve) => { gates.set(args.id, resolve) })
+      return [{ type: 'text', text: `done-${args.id}` }]
+    },
+  })
+  return {
+    tool,
+    started,
+    release(id: string) { gates.get(id)?.(); gates.delete(id) },
+    pending() { return [...gates.keys()] },
+  }
+}
+
+function gatedParallelTool(name: string) {
+  return gatedTool(name, true)
+}
+
+function gatedExclusiveTool(name: string) {
+  return gatedTool(name, false)
+}
+
+/** Poll until `predicate` holds, letting microtasks/timers drain between checks. */
+async function until(predicate: () => boolean): Promise<void> {
+  for (let i = 0; i < 1000 && !predicate(); i++) await new Promise(r => setTimeout(r, 0))
+  if (!predicate()) throw new Error('until: condition never held')
+}
+
+describe('tool-call scheduler: grouping and barriers', () => {
+  it('runs parallel-safe siblings concurrently (all start before any completes)', async () => {
+    const adapter = new MockAdapter([
+      multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }, { id: 'c3', name: 'p', args: { id: '3' } }]),
+      textResponse('done'),
+    ])
+    const ctx = await harness(adapter)
+    const gated = gatedParallelTool('p')
+    ctx.tools.register(gated.tool)
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
+
+    agent.send([{ type: 'text', text: 'go' }])
+    await until(() => gated.started.length === 3)
+    expect(gated.started).toEqual(['1', '2', '3'])
+    gated.release('1'); gated.release('2'); gated.release('3')
+    await waitForIdle(ctx, agent)
+  })
+
+  it('an exclusive call between two parallel-safe calls forms a barrier (3 groups)', async () => {
+    const order: string[] = []
+    const adapter = new MockAdapter([
+      multiCall([
+        { id: 'c1', name: 'r', args: { id: 'A1' } },
+        { id: 'c2', name: 'w', args: { id: 'A2' } },
+        { id: 'c3', name: 'r', args: { id: 'A3' } },
+      ]),
+      textResponse('done'),
+    ])
+    const ctx = await harness(adapter)
+    ctx.tools.register(defineTool({
+      name: 'r', description: 'read', parameters: { id: { type: 'string', required: true } },
+      isConcurrencySafe: () => true,
+      async execute(args) { order.push(`r-start-${args.id}`); order.push(`r-end-${args.id}`); return [{ type: 'text', text: 'r' }] },
+    }))
+    ctx.tools.register(defineTool({
+      name: 'w', description: 'write', parameters: { id: { type: 'string', required: true } },
+      async execute(args) { order.push(`w-${args.id}`); return [{ type: 'text', text: 'w' }] },
+    }))
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+
+    expect(order).toEqual(['r-start-A1', 'r-end-A1', 'w-A2', 'r-start-A3', 'r-end-A3'])
+  })
+
+  it('reclassifies pending calls after an exclusive barrier replaces their tool', async () => {
+    const adapter = new MockAdapter([
+      multiCall([
+        { id: 'c1', name: 'replace', args: { id: '0' } },
+        { id: 'c2', name: 'x', args: { id: '1' } },
+        { id: 'c3', name: 'x', args: { id: '2' } },
+      ]),
+      textResponse('done'),
+    ])
+    const ctx = await harness(adapter)
+    const replacement = gatedExclusiveTool('x')
+    const disposeSafe = ctx.tools.register(defineTool({
+      name: 'x',
+      description: 'initially safe',
+      parameters: { id: { type: 'string', required: true } },
+      isConcurrencySafe: () => true,
+      async execute(args) { return [{ type: 'text', text: `old-${args.id}` }] },
+    }))
+    ctx.tools.register(defineTool({
+      name: 'replace',
+      description: 'replace x',
+      parameters: { id: { type: 'string', required: true } },
+      async execute() {
+        disposeSafe()
+        ctx.tools.register(replacement.tool)
+        return [{ type: 'text', text: 'replaced' }]
+      },
+    }))
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
+
+    agent.send([{ type: 'text', text: 'go' }])
+    await until(() => replacement.started.length === 1)
+    await new Promise(r => setTimeout(r, 5))
+    expect(replacement.started).toEqual(['1'])
+    replacement.release('1')
+    await until(() => replacement.started.length === 2)
+    expect(replacement.started).toEqual(['1', '2'])
+    replacement.release('2')
+    await waitForIdle(ctx, agent)
+  })
+
+  it('stops replenishing when a result observer makes the next call exclusive', async () => {
+    const adapter = new MockAdapter([
+      multiCall([
+        { id: 'c1', name: 'x', args: { id: '1' } },
+        { id: 'c2', name: 'x', args: { id: '2' } },
+        { id: 'c3', name: 'x', args: { id: '3' } },
+      ]),
+      textResponse('done'),
+    ])
+    const ctx = await harness(adapter, 2)
+    const initial = gatedParallelTool('x')
+    const replacement = gatedExclusiveTool('x')
+    const disposeInitial = ctx.tools.register(initial.tool)
+    ctx.on('tools/result', (exec) => {
+      if (exec.callId !== CallId('c1')) return
+      disposeInitial()
+      ctx.tools.register(replacement.tool)
+    })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
+
+    agent.send([{ type: 'text', text: 'go' }])
+    await until(() => initial.started.length === 2)
+    initial.release('1')
+    await until(() => events(agent).some(event =>
+      event.type === 'tool/result' && event.data.callId === CallId('c1')))
+    await new Promise(r => setTimeout(r, 5))
+    expect(replacement.started).toEqual([])
+    initial.release('2')
+    await until(() => replacement.started.length === 1)
+    expect(replacement.started).toEqual(['3'])
+    replacement.release('3')
+    await waitForIdle(ctx, agent)
+  })
+})
+
+describe('tool-call scheduler: model-order results despite out-of-order settlement', () => {
+  it('commits tool/result in model order even when a later call settles first', async () => {
+    const adapter = new MockAdapter([
+      multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }]),
+      textResponse('done'),
+    ])
+    const ctx = await harness(adapter)
+    const gated = gatedParallelTool('p')
+    ctx.tools.register(gated.tool)
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
+
+    agent.send([{ type: 'text', text: 'go' }])
+    await until(() => gated.started.length === 2)
+    gated.release('2')
+    await new Promise(r => setTimeout(r, 5))
+    const beforeFirst = events(agent).filter(e => e.type === 'tool/result')
+    expect(beforeFirst).toEqual([])
+    gated.release('1')
+    await waitForIdle(ctx, agent)
+
+    const results = events(agent).filter(e => e.type === 'tool/result')
+    expect(results.map(e => e.data.callId)).toEqual([CallId('c1'), CallId('c2')])
+  })
+
+  it('derived history pairs calls in model order regardless of tool/call log interleaving', async () => {
+    const adapter = new MockAdapter([
+      multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }]),
+      textResponse('done'),
+    ])
+    const ctx = await harness(adapter)
+    const gated = gatedParallelTool('p')
+    ctx.tools.register(gated.tool)
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await until(() => gated.started.length === 2)
+    gated.release('2'); gated.release('1')
+    await waitForIdle(ctx, agent)
+
+    const messages = agent.session.deriveMessages()
+    const toolResults = messages.flatMap(m => m.content.filter(b => b.type === 'tool-result'))
+    expect(toolResults.map(b => b.toolCallId)).toEqual([CallId('c1'), CallId('c2')])
+  })
+})
+
+describe('tool-call scheduler: rolling pool honors maxParallelToolCalls', () => {
+  it('rejects invalid global maxParallelToolCalls config at plugin load', async () => {
+    await expect(harness(new MockAdapter([]), 0)).rejects.toThrow()
+    await expect(harness(new MockAdapter([]), 1.5)).rejects.toThrow()
+  })
+
+  it('defensively rejects invalid caps when direct construction bypasses the config schema', () => {
+    expect(() => new AgentLoop(new Context(), { agents: [], maxParallelToolCalls: 0 }))
+      .toThrow('maxParallelToolCalls must be a positive integer')
+    expect(() => new AgentLoop(new Context(), { agents: [], maxParallelToolCalls: 1.5 }))
+      .toThrow('maxParallelToolCalls must be a positive integer')
+  })
+
+  it('defaults the cap when direct construction bypasses the config schema', async () => {
+    const ctx = new Context()
+    await ctx.plugin(LlmService)
+    await ctx.plugin(SessionStore)
+    await ctx.plugin(SystemPrompt, { persona: '' })
+    await ctx.plugin(ToolRegistry)
+    await ctx.plugin(AgentRegistry)
+
+    expect(() => new AgentLoop(ctx, { agents: [] })).not.toThrow()
+    await ctx.fiber.dispose()
+  })
+
+  it('starts at most the cap, replenishing as calls settle', async () => {
+    const adapter = new MockAdapter([
+      multiCall([1, 2, 3, 4].map(n => ({ id: `c${n}`, name: 'p', args: { id: String(n) } }))),
+      textResponse('done'),
+    ])
+    const ctx = await harness(adapter, 2)
+    const gated = gatedParallelTool('p')
+    ctx.tools.register(gated.tool)
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
+
+    agent.send([{ type: 'text', text: 'go' }])
+    await until(() => gated.started.length === 2)
+    await new Promise(r => setTimeout(r, 5))
+    expect(gated.started).toEqual(['1', '2'])
+    gated.release('1')
+    await until(() => gated.started.length === 3)
+    expect(gated.started).toEqual(['1', '2', '3'])
+    expect(events(agent)
+      .filter(e => e.type === 'tool/call' || e.type === 'tool/result')
+      .map(e => `${e.type}:${String(e.data.callId)}`)
+      .slice(0, 4))
+      .toEqual(['tool/call:c1', 'tool/call:c2', 'tool/result:c1', 'tool/call:c3'])
+    gated.release('2'); gated.release('3')
+    await until(() => gated.started.length === 4)
+    gated.release('4')
+    await waitForIdle(ctx, agent)
+    expect(events(agent).filter(e => e.type === 'tool/result').map(e => e.data.callId))
+      .toEqual([CallId('c1'), CallId('c2'), CallId('c3'), CallId('c4')])
+  })
+
+  it('maxParallelToolCalls: 1 is fully serial (no second start before the first settles)', async () => {
+    const adapter = new MockAdapter([
+      multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }]),
+      textResponse('done'),
+    ])
+    const ctx = await harness(adapter, 1)
+    const gated = gatedParallelTool('p')
+    ctx.tools.register(gated.tool)
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await until(() => gated.started.length === 1)
+    await new Promise(r => setTimeout(r, 5))
+    expect(gated.started).toEqual(['1'])
+    gated.release('1')
+    await until(() => gated.started.length === 2)
+    gated.release('2')
+    await waitForIdle(ctx, agent)
+  })
+
+  it('applies the configured cap to every factory-created agent', async () => {
+    const adapter = new MockAdapter([
+      multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }]),
+      textResponse('done'),
+    ])
+    const ctx = new Context()
+    await ctx.plugin(LlmService)
+    await ctx.plugin(SessionStore)
+    await ctx.plugin(SystemPrompt, { persona: '' })
+    await ctx.plugin(ToolRegistry)
+    await ctx.plugin(AgentRegistry)
+    await ctx.plugin(AgentLoop, { agents: [], maxParallelToolCalls: 1 })
+    ctx.llm.registerAdapter(['mock'], adapter)
+    const gated = gatedParallelTool('p')
+    ctx.tools.register(gated.tool)
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await until(() => gated.started.length === 1)
+    await new Promise(r => setTimeout(r, 5))
+    expect(gated.started).toEqual(['1'])
+    gated.release('1')
+    await until(() => gated.started.length === 2)
+    gated.release('2')
+    await waitForIdle(ctx, agent)
+  })
+
+})
+
+describe('tool-call scheduler: ordered middleware and additional contexts', () => {
+  it('tools/pre-execute and tools/post-execute observe model call order', async () => {
+    const adapter = new MockAdapter([
+      multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }, { id: 'c3', name: 'p', args: { id: '3' } }]),
+      textResponse('done'),
+    ])
+    const ctx = await harness(adapter)
+    const gated = gatedParallelTool('p')
+    ctx.tools.register(gated.tool)
+    const pre: string[] = []
+    const post: string[] = []
+    ctx.on('tools/pre-execute', async (exec, next): Promise<PreToolDecision> => { pre.push(String(exec.callId)); return next() })
+    ctx.on('tools/post-execute', async (exec, _result, next): Promise<PostToolDecision> => { post.push(String(exec.callId)); return next() })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
+
+    agent.send([{ type: 'text', text: 'go' }])
+    await until(() => gated.started.length === 3)
+    gated.release('3'); gated.release('2'); gated.release('1')
+    await waitForIdle(ctx, agent)
+
+    expect(pre).toEqual([CallId('c1'), CallId('c2'), CallId('c3')].map(String))
+    expect(post).toEqual([CallId('c1'), CallId('c2'), CallId('c3')].map(String))
+  })
+
+  it('injects additional contexts in model call order, not settlement order', async () => {
+    const adapter = new MockAdapter([
+      multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }]),
+      textResponse('done'),
+    ])
+    const ctx = await harness(adapter, 2)
+    const gated = gatedParallelTool('p')
+    ctx.tools.register(gated.tool)
+    ctx.on('tools/post-execute', async (exec, _result): Promise<PostToolDecision> =>
+      ({ kind: 'accept', additionalContexts: [{ content: [{ type: 'text', text: `ctx-${exec.callId}` }], source: { kind: 'plugin', plugin: 'p' } }] }))
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
+
+    agent.send([{ type: 'text', text: 'go' }])
+    await until(() => gated.started.length === 2)
+    gated.release('2'); gated.release('1')
+    await waitForIdle(ctx, agent)
+
+    const log = events(agent)
+    const contextTexts = log.filter(e => e.type === 'context/message')
+      .map(e => (e.data.content[0] as { text: string }).text)
+    expect(contextTexts).toEqual(['ctx-c1', 'ctx-c2'])
+    const lastResult = log.findLastIndex(e => e.type === 'tool/result')
+    const firstContext = log.findIndex(e => e.type === 'context/message')
+    expect(lastResult).toBeLessThan(firstContext)
+  })
+
+  it('orders pre-execute denials and errors without dispatching them', async () => {
+    const adapter = new MockAdapter([
+      multiCall([
+        { id: 'c1', name: 'p', args: { id: '1' } },
+        { id: 'c2', name: 'p', args: { id: '2' } },
+        { id: 'c3', name: 'p', args: { id: '3' } },
+      ]),
+      textResponse('done'),
+    ])
+    const ctx = await harness(adapter)
+    const gated = gatedParallelTool('p')
+    ctx.tools.register(gated.tool)
+    const post: string[] = []
+    ctx.on('tools/pre-execute', async (exec, next): Promise<PreToolDecision> => {
+      if (exec.callId === CallId('c2')) return { kind: 'deny', reason: 'blocked by policy' }
+      if (exec.callId === CallId('c3')) throw new Error('pre exploded')
+      return next()
+    })
+    ctx.on('tools/post-execute', async (exec, _result, next): Promise<PostToolDecision> => {
+      post.push(String(exec.callId))
+      return next()
+    })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
+
+    agent.send([{ type: 'text', text: 'go' }])
+    await until(() => gated.started.length === 1)
+    gated.release('1')
+    await waitForIdle(ctx, agent)
+
+    expect(gated.started).toEqual(['1'])
+    expect(post).toEqual(['c1', 'c2'])
+    const results = events(agent).filter(e => e.type === 'tool/result')
+    expect(results.map(e => e.data.callId)).toEqual([CallId('c1'), CallId('c2'), CallId('c3')])
+    expect((results[1]!.data.content[0] as { text: string }).text).toContain('blocked by policy')
+    expect((results[2]!.data.content[0] as { text: string }).text).toContain('pre exploded')
+  })
+})
+
+describe('tool-call scheduler: abort handling', () => {
+  it('starts no calls when the signal is already aborted before a parallel group', async () => {
+    const adapter = new MockAdapter([
+      multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }]),
+      textResponse('should never be requested'),
+    ])
+    const ctx = await harness(adapter)
+    const gated = gatedParallelTool('p')
+    ctx.tools.register(gated.tool)
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
+    ctx.on('session/event', (session, event) => {
+      if (session === agent.session && event.type === 'assistant/message') {
+        ;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('already aborted')
+      }
+    })
+
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+
+    expect(gated.started).toEqual([])
+    expect(events(agent).filter(e => e.type === 'tool/call').map(e => e.data.callId))
+      .toEqual([CallId('c1'), CallId('c2')])
+    expect(events(agent).filter(e => e.type === 'tool/result').map(e => ({
+      callId: e.data.callId,
+      isError: e.data.isError,
+      error: e.data.error,
+    }))).toEqual([
+      { callId: CallId('c1'), isError: true, error: { name: 'AbortError', code: 'ABORTED' } },
+      { callId: CallId('c2'), isError: true, error: { name: 'AbortError', code: 'ABORTED' } },
+    ])
+  })
+
+  it('stops starting siblings when abort fires during ordered pre-execute', async () => {
+    const adapter = new MockAdapter([
+      multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }]),
+      textResponse('should never be requested'),
+    ])
+    const ctx = await harness(adapter)
+    const gated = gatedParallelTool('p')
+    ctx.tools.register(gated.tool)
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
+    ctx.on('tools/pre-execute', async (exec, next): Promise<PreToolDecision> => {
+      if (exec.callId === CallId('c1')) {
+        ;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('pre cancelled')
+      }
+      return next()
+    })
+
+    agent.send([{ type: 'text', text: 'go' }])
+    await until(() => gated.started.length === 1)
+    await new Promise(r => setTimeout(r, 5))
+    expect(gated.started).toEqual(['1'])
+    gated.release('1')
+    await waitForIdle(ctx, agent)
+
+    expect(events(agent).filter(e => e.type === 'tool/call').map(e => e.data.callId))
+      .toEqual([CallId('c1'), CallId('c2')])
+    expect(events(agent).filter(e => e.type === 'tool/result').map(e => e.data.callId))
+      .toEqual([CallId('c1'), CallId('c2')])
+    expect(events(agent).filter(e => e.type === 'tool/result').at(-1)?.data)
+      .toMatchObject({ callId: CallId('c2'), isError: true, error: { name: 'AbortError', code: 'ABORTED' } })
+  })
+
+  it('stops replenishing after abort, commits started results, and drains accepted additional contexts', async () => {
+    const adapter = new MockAdapter([
+      multiCall([1, 2, 3, 4].map(n => ({ id: `c${n}`, name: 'p', args: { id: String(n) } }))),
+      textResponse('should never be requested'),
+    ])
+    const ctx = await harness(adapter, 2)
+    const gated = gatedParallelTool('p')
+    ctx.tools.register(gated.tool)
+    ctx.on('tools/post-execute', async (exec, _result, next): Promise<PostToolDecision> => ({
+      ...await next(),
+      additionalContexts: [{ content: [{ type: 'text', text: `ctx-${exec.callId}` }], source: { kind: 'plugin', plugin: 'p' } }],
+    }))
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
+
+    agent.send([{ type: 'text', text: 'go' }])
+    await until(() => gated.started.length === 2)
+    ;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('stop now')
+    gated.release('1')
+    gated.release('2')
+    await waitForIdle(ctx, agent)
+
+    expect(gated.started).toEqual(['1', '2'])
+    expect(events(agent).filter(e => e.type === 'tool/call').map(e => e.data.callId))
+      .toEqual([CallId('c1'), CallId('c2'), CallId('c3'), CallId('c4')])
+    expect(events(agent).filter(e => e.type === 'tool/result').map(e => e.data.callId))
+      .toEqual([CallId('c1'), CallId('c2'), CallId('c3'), CallId('c4')])
+    expect(events(agent).filter(e => e.type === 'tool/result').slice(-2).map(e => e.data))
+      .toEqual([
+        expect.objectContaining({ callId: CallId('c3'), isError: true, error: { name: 'AbortError', code: 'ABORTED' } }),
+        expect.objectContaining({ callId: CallId('c4'), isError: true, error: { name: 'AbortError', code: 'ABORTED' } }),
+      ])
+    const settled = events(agent).filter(e => e.type === 'tool/result' || e.type === 'context/message')
+    expect(settled.map(e => e.type))
+      .toEqual(['tool/result', 'tool/result', 'tool/result', 'tool/result', 'context/message', 'context/message'])
+    expect(settled.filter(e => e.type === 'context/message')
+      .map(e => (e.data.content[0] as { text: string }).text))
+      .toEqual(['ctx-c1', 'ctx-c2'])
+  })
+
+  it('does not run an exclusive barrier after a parallel group aborts', async () => {
+    const adapter = new MockAdapter([
+      multiCall([
+        { id: 'c1', name: 'p', args: { id: '1' } },
+        { id: 'c2', name: 'p', args: { id: '2' } },
+        { id: 'c3', name: 'x', args: { id: '3' } },
+      ]),
+      textResponse('should never be requested'),
+    ])
+    const ctx = await harness(adapter, 2)
+    const gated = gatedParallelTool('p')
+    const exclusive: string[] = []
+    ctx.tools.register(gated.tool)
+    ctx.tools.register(defineTool({
+      name: 'x',
+      description: 'exclusive',
+      parameters: { id: { type: 'string', required: true } },
+      async execute(args) { exclusive.push(args.id); return [{ type: 'text', text: 'x' }] },
+    }))
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
+
+    agent.send([{ type: 'text', text: 'go' }])
+    await until(() => gated.started.length === 2)
+    ;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('stop before barrier')
+    gated.release('1')
+    gated.release('2')
+    await waitForIdle(ctx, agent)
+
+    expect(exclusive).toEqual([])
+    expect(events(agent).filter(e => e.type === 'tool/call').map(e => e.data.callId))
+      .toEqual([CallId('c1'), CallId('c2'), CallId('c3')])
+    expect(events(agent).filter(e => e.type === 'tool/result').at(-1)?.data)
+      .toMatchObject({ callId: CallId('c3'), isError: true, error: { name: 'AbortError', code: 'ABORTED' } })
+  })
+})

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

@@ -9,12 +9,13 @@
 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 SessionStore, { SessionId, 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 AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
+
+import AgentLoop from '@deepseek-ai/dsh-agent-loop'
 import { MockAdapter, textResponse } from './mock-adapter.ts'
 
 async function harness(adapter: MockAdapter, toolOrder?: SystemPromptConfig['toolOrder']) {
@@ -29,7 +30,7 @@ async function harness(adapter: MockAdapter, toolOrder?: SystemPromptConfig['too
   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') {
@@ -56,7 +57,7 @@ async function runTurn(registrationOrder: string[], toolOrder?: SystemPromptConf
   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' })
+  const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
   agent.send([{ type: 'text', text: 'go' }])
   await waitForIdle(ctx, agent)
   return { ctx, agent, adapter }
@@ -98,7 +99,7 @@ describe('loop-level canonical tool order', () => {
     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' })
+    const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
     agent.send([{ type: 'text', text: 'go' }])
     await waitForIdle(ctx, agent)
     expect(adapter.requests).toHaveLength(0)

packages/core/agent-loop/tests/turn-stop.spec.ts

@@ -1,11 +1,12 @@
 import { describe, expect, it } from 'vitest'
 import { Context } from 'cordis'
 import LlmService from '@deepseek-ai/dsh-llm'
-import SessionStore, { type TurnEndReason } from '@deepseek-ai/dsh-session'
+import SessionStore, { SessionId, type TurnEndReason } from '@deepseek-ai/dsh-session'
 import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
 import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
-import AgentRegistry, { AgentId, type ContinuationStop } from '@deepseek-ai/dsh-agent'
-import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
+import AgentRegistry, { type Agent, type ContinuationStop } from '@deepseek-ai/dsh-agent'
+
+import AgentLoop from '@deepseek-ai/dsh-agent-loop'
 import * as Invariants from '@deepseek-ai/dsh-invariants'
 import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts'
 
@@ -22,7 +23,7 @@ async function harness(adapter: MockAdapter): Promise<Context> {
   return ctx
 }
 
-function send(agent: ReactLoopAgent, text = 'go'): Promise<void> {
+function send(agent: Agent, text = 'go'): Promise<void> {
   agent.send([{ type: 'text', text }])
   return agent.whenIdle()
 }
@@ -45,7 +46,7 @@ describe('agent/turn-stop', () => {
       textResponse('must not be requested'),
     ])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('terminal-steering'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('terminal-steering'), { provider: 'mock', model: 'mock' })
     agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' }))
 
     let steered = false
@@ -72,7 +73,7 @@ describe('agent/turn-stop', () => {
       textResponse('must not become a late-steering turn'),
     ])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('terminal-flush-steering'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('terminal-flush-steering'), { provider: 'mock', model: 'mock' })
     agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' }))
 
     let injected = false
@@ -98,7 +99,7 @@ describe('agent/turn-stop', () => {
       textResponse('queued follow-up answer'),
     ])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('terminal-flush-send'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('terminal-flush-send'), { provider: 'mock', model: 'mock' })
     agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' }))
 
     let queued = false
@@ -124,8 +125,8 @@ describe('agent/turn-stop', () => {
     ])
     const ctx = await harness(adapter)
     registerEcho(ctx)
-    const stopped = ctx.agentLoop.create(AgentId('stopped'), { model: 'mock' })
-    const ordinary = ctx.agentLoop.create(AgentId('ordinary'), { model: 'mock' })
+    const stopped = ctx.agentLoop.create(SessionId('stopped'), { provider: 'mock', model: 'mock' })
+    const ordinary = ctx.agentLoop.create(SessionId('ordinary'), { provider: 'mock', model: 'mock' })
     stopped.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' }))
 
     await send(stopped)
@@ -145,7 +146,7 @@ describe('agent/turn-stop', () => {
     ])
     const ctx = await harness(adapter)
     registerEcho(ctx)
-    const agent = ctx.agentLoop.create(AgentId('owned-listener'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('owned-listener'), { provider: 'mock', model: 'mock' })
     const disposeStop = agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' }))
 
     await send(agent, 'first turn')
@@ -162,7 +163,7 @@ describe('agent/turn-stop', () => {
       textResponse('healthy later turn'),
     ])
     const ctx = await harness(adapter)
-    const agent = ctx.agentLoop.create(AgentId('bad-policy'), { model: 'mock' })
+    const agent = ctx.agentLoop.create(SessionId('bad-policy'), { provider: 'mock', model: 'mock' })
     const reasons: TurnEndReason[] = []
     const errors: string[] = []
     ctx.on('session/event', (session, event) => {