Merge remote-tracking branch 'origin/master' into cross-family-fs-sandbox

# Conflicts:
#	docs/config-catalog.md
#	docs/cordis-catalog/services.md
#	docs/module-graph.md
#	docs/rfc/implemented/feature/2026-07-06-sandbox.md
#	examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md
#	examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.golden.json
#	examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md
#	examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.golden.json
#	examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md
#	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
#	examples/acp-agent/tests/snapshots/permission-switching/session.jsonl
#	examples/acp-agent/tests/snapshots/permission-switching/system-prompt.golden.md
#	examples/acp-agent/tests/snapshots/permission-switching/tool-schemas.golden.json
#	examples/acp-agent/tests/snapshots/skill-load/tool-schemas.golden.json
#	examples/acp-agent/tests/snapshots/text-turn/tool-schemas.golden.json
#	examples/acp-agent/tests/snapshots/workspace-edit/system-prompt.golden.md
#	examples/acp-agent/tests/snapshots/workspace-edit/tool-schemas.golden.json
#	packages/bash/bash-sandbox/src/index.ts
#	packages/bash/bash-sandbox/tests/bwrap.e2e.ts
#	packages/bash/bash-sandbox/tests/sandbox.spec.ts
#	packages/bash/bash-sandbox/tests/seatbelt.e2e.ts
#	packages/bash/bash/src/index.ts
#	packages/bash/tool-bash/package.json
#	packages/bash/tool-bash/src/index.ts
#	packages/bash/tool-bash/src/render.ts
#	packages/bash/tool-bash/tests/tools.spec.ts
#	packages/bash/tool-bash/tsconfig.json
#	pnpm-lock.yaml
#	scripts/verify-package-readme-model-experience.ts

packages/bash/tool-bash/tests/integration.spec.ts

@@ -7,15 +7,17 @@ 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 TaskService from '@deepseek-ai/dsh-tasks'
+import * as ToolTasks from '@deepseek-ai/dsh-tool-tasks'
 import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
-import { BashTaskId } from '@deepseek-ai/dsh-bash'
 import * as ToolBash from '@deepseek-ai/dsh-tool-bash'
 import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts'
 
 /**
  * Full-loop integration: a scripted mock model drives the REAL bash tool
  * through the agent loop, exercising the same seams a live model would
- * (tool/call + tool/result session events, agent.inject notifications).
+ * (tool/call + tool/result session events, the generic `ctx.tasks` runtime,
+ * agent.inject completion notices).
  */
 async function harness(adapter: MockAdapter) {
   const ctx = new Context()
@@ -25,6 +27,8 @@ async function harness(adapter: MockAdapter) {
   await ctx.plugin(ToolRegistry)
   await ctx.plugin(AgentRegistry)
   await ctx.plugin(AgentLoop, { agents: [] })
+  await ctx.plugin(TaskService)
+  await ctx.plugin(ToolTasks)
   await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 })
   await ctx.plugin(ToolBash)
   ctx.llm.registerAdapter(['mock'], adapter)
@@ -67,6 +71,16 @@ function resultText(event: SessionEvent): string {
     .join('')
 }
 
+/** Poll until `predicate` holds (background settlement races turn end). */
+async function pollUntil(predicate: () => boolean, timeoutMs = 5_000): Promise<void> {
+  const deadline = Date.now() + timeoutMs
+  while (Date.now() < deadline) {
+    if (predicate()) return
+    await new Promise(resolve => setTimeout(resolve, 20))
+  }
+  throw new Error(`condition not met within ${timeoutMs}ms`)
+}
+
 describe('bash tool through the agent loop', () => {
   it('foreground: model calls bash, sees the result, replies', async () => {
     const adapter = new MockAdapter([
@@ -116,46 +130,41 @@ describe('bash tool through the agent loop', () => {
     expect(resultText(toolResult)).toContain('[exit code: 9]')
   })
 
-  it('background: start → poll → completion notice lands as context/message', async () => {
+  it('background: start ack → completion notice as context/message → task_output collects it', async () => {
+    // The task id is deterministic (a fresh TaskService counts per kind from 1),
+    // so the script can name `bash-1` without threading a generated id.
     const adapter = new MockAdapter([
       toolCallResponse('call-1', 'bash', { command: 'echo bg-ok', description: 'test command', run_in_background: true }),
-      // Each harness owns a fresh BashLocal service, whose first task id is
-      // deterministically bash-1. Keep the scripted call faithful to what the
-      // model sent; tool arguments are immutable once execution policy begins.
-      toolCallResponse('call-2', 'bash_output', { task_id: 'bash-1' }, undefined),
+      textResponse('Started it in the background.'),
+      toolCallResponse('call-2', 'task_output', { task_id: 'bash-1' }),
       textResponse('Background task finished.'),
     ])
-    let taskId = ''
-
     const ctx = await harness(adapter)
     const agent = ctx.agentLoop.create(AgentId('it-bg'), { model: 'mock' })
 
-    // Capture the generated id so the deterministic fixture is checked against
-    // the real executor instead of silently assuming it.
-    ctx.on('session/event', (_session, event) => {
-      if (event.type === 'tool/result' && taskId === '') {
-        const match = /task (bash-\d+)/.exec(resultText(event))
-        if (match) taskId = match[1]!
-      }
-    })
     agent.send([{ type: 'text', text: 'run echo bg-ok in the background' }])
     await waitForIdle(ctx, agent)
 
-    expect(taskId).toBe('bash-1')
+    const firstResult = findEvent(events(agent), 'tool/result')
+    expect(firstResult.data.isError).toBe(false)
+    expect(resultText(firstResult)).toBe('started background task bash-1')
 
-    // Wait for the background task itself (completion may race turn end).
-    const task = ctx.bash.get(BashTaskId(taskId))
-    if (!task) throw new Error(`task ${taskId} not registered`)
-    await task.done
-
-    const log = events(agent)
-    const firstResult = findEvent(log, 'tool/result')
-    expect(resultText(firstResult)).toBe(`started background task ${taskId}`)
-
-    const notice = findEvent(log, 'context/message')
+    // The task settles on its own; the tool-tasks notice listener injects a
+    // durable context/message into the owning agent's session (settlement may
+    // race turn end, so poll for it).
+    await pollUntil(() => events(agent).some(event => event.type === 'context/message'))
+    const notice = findEvent(events(agent), 'context/message')
     expect(notice.data.content.some(
-      block => block.type === 'text' && block.text.includes(`background bash task ${taskId} finished`),
+      block => block.type === 'text' && block.text.includes('background task bash-1 (bash: echo bg-ok) finished'),
     )).toBe(true)
-    expect(notice.data.source).toEqual({ kind: 'plugin', plugin: 'tool-bash' })
+    expect(notice.data.source).toEqual({ kind: 'plugin', plugin: 'tool-tasks' })
+
+    // The next turn collects the output through the generic task tool.
+    agent.send([{ type: 'text', text: 'collect it' }])
+    await waitForIdle(ctx, agent)
+    const readResult = findEvent(events(agent), 'tool/result', 'last')
+    expect(readResult.data.isError).toBe(false)
+    expect(resultText(readResult)).toContain('bg-ok')
+    expect(resultText(readResult)).toContain('[status: completed, exit code: 0]')
   })
 })