Merge latest origin/master into parallel-tool-call

# Conflicts: # docs/architecture.md # examples/acp-agent/tests/snapshots/bash-spill/session.jsonl # examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl # examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl # packages/core/agent-loop/src/loop.ts
2026-07-18 15:09:39 +08:00
parent 21ec178841 7a29676c01
commit 50f0291b93
198 changed files with 6086 additions and 4036 deletions
--- a/packages/core/agent-loop/tests/contract-regressions.spec.ts
+++ b/packages/core/agent-loop/tests/contract-regressions.spec.ts
@@ -3,12 +3,12 @@ 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 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 { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts'
+import { maxTokensResponse, MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts'

 /** Regression tests for agent-loop boundary, identity, and lifecycle contracts. */

@@ -132,6 +132,73 @@ describe('session log records what agent/step-result actually produced', () => {
  })
 })

+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(AgentId(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 () => {
    const adapter = new MockAdapter([
@@ -182,6 +249,190 @@ describe('abort during tool execution ends the turn', () => {
    expect(adapter.requests).toHaveLength(1)        // no follow-up model call
    expect(reasons).toEqual([{ kind: 'aborted', reason: 'user interrupt' }])
  })
+
+  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 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(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 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!: 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 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')
+  })
 })

 describe('steering from late extension points is never stranded', () => {
@@ -1118,9 +1369,10 @@ 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)
@@ -1137,7 +1389,7 @@ 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')
  })
--- a/packages/core/agent-loop/tests/interception.spec.ts
+++ b/packages/core/agent-loop/tests/interception.spec.ts
@@ -375,8 +375,8 @@ 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.
@@ -492,7 +492,7 @@ 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)
  })
 })

--- a/packages/core/agent-loop/tests/loop.spec.ts
+++ b/packages/core/agent-loop/tests/loop.spec.ts
@@ -410,22 +410,30 @@ 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' }]
      },
    }))
@@ -433,13 +441,67 @@ 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 () => {
@@ -743,10 +805,9 @@ describe('agent loop', () => {
    })
  })

-  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' },
@@ -770,14 +831,20 @@ 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'), { provider: 'mock', model: 'mock' })
@@ -789,7 +856,14 @@ 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' }] }])
  })

--- a/packages/core/agent-loop/tests/request-log.spec.ts
+++ b/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'
@@ -23,7 +22,7 @@ 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', () => {
@@ -53,8 +52,8 @@ 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: { provider: 'mock', model: 'm' }, system: 'a\nb', tools: [tool('t')] })
    recordRequestHeader(session, state, first)
@@ -63,12 +62,12 @@ describe('recordRequestHeader', () => {
    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: { provider: 'mock', model: 'm' }, tools: [tool('a'), tool('b')] })
    recordRequestHeader(session, state, first)
@@ -77,9 +76,7 @@ describe('recordRequestHeader', () => {
    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)
  })
 })
--- a/packages/core/agent-loop/tests/request-reconstruction.spec.ts
+++ b/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'
@@ -85,7 +84,7 @@ 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')
  })
@@ -122,8 +121,8 @@ 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]!],
      })
    })

@@ -137,7 +136,7 @@ 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'), { provider: 'mock', model: 'mock' })
@@ -147,14 +146,15 @@ describe('request stability across the loop', () => {
    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)
@@ -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()
  })
@@ -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))!
--- a/packages/core/agent-loop/tests/tool-calls.spec.ts
+++ b/packages/core/agent-loop/tests/tool-calls.spec.ts
@@ -502,7 +502,7 @@ describe('tool-call scheduler: abort handling', () => {
      .toEqual([CallId('c1')])
  })

-  it('stops replenishing after abort, commits started results, and drops buffered additional contexts', async () => {
+  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'),
@@ -528,7 +528,12 @@ describe('tool-call scheduler: abort handling', () => {
      .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 === 'context/message')).toEqual([])
+    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 () => {