Merge latest agent execution context base

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

@@ -7,7 +7,7 @@ import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
 import ToolRegistry from '@deepseek-ai/dsh-tools'
 import AgentRegistry from '@deepseek-ai/dsh-agent'
 import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution'
-import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
+import AgentLoop, { DEFAULT_MAX_PARALLEL_TOOL_CALLS, ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
 import { bindReactLoopAgentContext, prepareReactLoopAgent } from '../src/agent.ts'
 import { MockAdapter, textResponse } from './mock-adapter.ts'
 
@@ -56,10 +56,14 @@ describe('ReactLoopAgent', () => {
     await ctx.plugin(AgentExecutionProvider)
     await ctx.plugin(SessionStore)
     const session = ctx.sessions.create(SessionId('exclusive-driver'))
-    const prepared = prepareReactLoopAgent(ctx, AgentId('first-driver'), { provider: 'mock', model: 'mock' }, session)
+    const prepared = prepareReactLoopAgent(
+      ctx, AgentId('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'), { provider: 'mock', model: 'mock' }, session))
+    expect(() => prepareReactLoopAgent(
+      ctx, AgentId('second-driver'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
+    ))
       .toThrow('already has a concrete agent driver')
 
     await prepared.dispose()
@@ -258,7 +262,9 @@ describe('ReactLoopAgent', () => {
     await ctx.plugin(AgentExecutionProvider)
     await ctx.plugin(SessionStore)
     const session = ctx.sessions.create(SessionId('test'))
-    const prepared = prepareReactLoopAgent(ctx, AgentId('bare'), { provider: 'mock', model: 'mock' }, session)
+    const prepared = prepareReactLoopAgent(
+      ctx, AgentId('bare'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
+    )
     const { agent } = prepared
 
     prepared.markPublished()
@@ -276,7 +282,9 @@ 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'), { provider: 'mock', model: 'mock' }, session)
+    const prepared = prepareReactLoopAgent(
+      ctx, AgentId('pre-start-dispose'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
+    )
 
     await prepared.dispose()
     expect(prepared.agent.status).toBe('disposed')
@@ -374,7 +382,9 @@ 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'), { provider: 'mock', model: 'mock' }, session)
+    const prepared = prepareReactLoopAgent(
+      ctx, AgentId('bare'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
+    )
     const { agent } = prepared
     prepared.markPublished()
     const dispose = prepared.startDriver()

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

@@ -3,10 +3,10 @@ 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 ToolRegistry, { defineTool, type PostToolDecision } from '@deepseek-ai/dsh-tools'
 import AgentRegistry, { AgentId, type ContinuationDecision } from '@deepseek-ai/dsh-agent'
 import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution'
-import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
+import AgentLoop, { DEFAULT_MAX_PARALLEL_TOOL_CALLS, ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
 import { prepareReactLoopAgent } from '../src/agent.ts'
 import * as Invariants from '@deepseek-ai/dsh-invariants'
 import { maxTokensResponse, MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts'
@@ -247,6 +247,190 @@ describe('abort during tool execution ends the turn', () => {
     expect(adapter.requests).toHaveLength(1)        // no follow-up model call
     expect(reasons).toEqual([{ kind: '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(AgentId('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.cancel({ kind: 'user' })
+        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(AgentId('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.cancel({ kind: 'user' })
+        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!: ReactLoopAgent
+    const fiber = await ctx.plugin(Object.assign((inner: Context) => {
+      agent = inner.agentLoop.create(AgentId('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(AgentId('a-historical-tool-pair'), { provider: 'mock', model: 'mock' })
+    ctx.tools.register(defineTool({
+      name: 'aborter',
+      description: '',
+      parameters: {},
+      async execute() {
+        agent.cancel({ kind: 'user' })
+        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')
+  })
 })
 
 describe('steering from late extension points is never stranded', () => {
@@ -631,7 +815,9 @@ 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'), { provider: 'mock', model: 'mock' }, seeded)
+    const prepared = prepareReactLoopAgent(
+      ctx2, AgentId('forked-agent'), { provider: 'mock', model: 'mock' }, seeded, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
+    )
     const forked = prepared.agent
     prepared.markPublished()
     ctx2.effect(() => prepared.startDriver())

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

@@ -412,22 +412,30 @@ 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'), { provider: 'mock', 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.
+    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' }]
       },
     }))
@@ -435,13 +443,67 @@ 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(AgentId('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 () => {

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

@@ -0,0 +1,574 @@
+/**
+ * Exercises scheduler ordering and cancellation with deterministic gated tools.
+ * ACP goldens 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 } 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, { AgentId } from '@deepseek-ai/dsh-agent'
+import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution'
+import AgentLoop, { ReactLoopAgent } 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(AgentExecutionProvider)
+  await ctx.plugin(AgentLoop, {
+    agents: [],
+    ...maxParallelToolCalls === undefined ? {} : { maxParallelToolCalls },
+  })
+  ctx.llm.registerAdapter(['mock'], adapter)
+  return ctx
+}
+
+function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
+  return new Promise((resolve) => {
+    const dispose = ctx.on('agent/status', (subject, status) => {
+      if (subject === agent && status === 'idle') { dispose(); resolve() }
+    })
+  })
+}
+
+function events(agent: ReactLoopAgent): 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(AgentId('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-${args.id}`); return [{ type: 'text', text: 'w' }] },
+    }))
+    const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+
+    expect(order).toEqual(['r-start-A1', 'r-end-A1', 'w-A2', 'r-start-A3', 'r-end-A3'])
+  })
+
+  it('reclassifies pending calls after an exclusive barrier replaces their tool', async () => {
+    const adapter = new MockAdapter([
+      multiCall([
+        { id: 'c1', name: 'replace', args: { id: '0' } },
+        { id: 'c2', name: 'x', args: { id: '1' } },
+        { id: 'c3', name: 'x', args: { id: '2' } },
+      ]),
+      textResponse('done'),
+    ])
+    const ctx = await harness(adapter)
+    const replacement = gatedExclusiveTool('x')
+    const disposeSafe = ctx.tools.register(defineTool({
+      name: 'x',
+      description: 'initially safe',
+      parameters: { id: { type: 'string', required: true } },
+      isConcurrencySafe: () => true,
+      async execute(args) { return [{ type: 'text', text: `old-${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(AgentId('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(AgentId('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(AgentId('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(AgentId('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${n}`, name: 'p', args: { id: String(n) } }))),
+      textResponse('done'),
+    ])
+    const ctx = await harness(adapter, 2)
+    const gated = gatedParallelTool('p')
+    ctx.tools.register(gated.tool)
+    const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
+
+    agent.send([{ type: 'text', text: 'go' }])
+    await until(() => gated.started.length === 2)
+    await new Promise(r => setTimeout(r, 5))
+    expect(gated.started).toEqual(['1', '2'])
+    gated.release('1')
+    await until(() => gated.started.length === 3)
+    expect(gated.started).toEqual(['1', '2', '3'])
+    expect(events(agent)
+      .filter(e => e.type === 'tool/call' || e.type === 'tool/result')
+      .map(e => `${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(AgentId('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(AgentExecutionProvider)
+    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(AgentId('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(AgentId('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(AgentId('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(AgentId('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(AgentId('a1'), { provider: 'mock', model: 'mock' })
+    ctx.on('session/event', (session, event) => {
+      if (session === agent.session && event.type === 'assistant/message') {
+        agent.cancel({ kind: 'user' })
+      }
+    })
+
+    agent.send([{ type: 'text', text: 'go' }])
+    await waitForIdle(ctx, agent)
+
+    expect(gated.started).toEqual([])
+    expect(events(agent).filter(e => e.type === 'tool/call')).toEqual([])
+    expect(events(agent).filter(e => e.type === 'tool/result')).toEqual([])
+  })
+
+  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(AgentId('a1'), { provider: 'mock', model: 'mock' })
+    ctx.on('tools/pre-execute', async (exec, next): Promise<PreToolDecision> => {
+      if (exec.callId === CallId('c1')) {
+        agent.cancel({ kind: 'user' })
+      }
+      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')])
+    expect(events(agent).filter(e => e.type === 'tool/result').map(e => e.data.callId))
+      .toEqual([CallId('c1')])
+  })
+
+  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(AgentId('a1'), { provider: 'mock', model: 'mock' })
+
+    agent.send([{ type: 'text', text: 'go' }])
+    await until(() => gated.started.length === 2)
+    agent.cancel({ kind: 'user' })
+    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')])
+    expect(events(agent).filter(e => e.type === 'tool/result').map(e => e.data.callId))
+      .toEqual([CallId('c1'), CallId('c2')])
+    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', '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(AgentId('a1'), { provider: 'mock', model: 'mock' })
+
+    agent.send([{ type: 'text', text: 'go' }])
+    await until(() => gated.started.length === 2)
+    agent.cancel({ kind: 'user' })
+    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')])
+  })
+})