Files
deepseek-harness/examples/headless-agent/tests/subagent-inheritance.snapshot.ts
T
_Kerman e0988abc74 Merge remote-tracking branch 'origin/master' into xtr/react-loop-simplification
# Conflicts:
#	.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml
#	.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml
#	.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md
#	.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md
#	.agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml
#	.agents/notes/implemented/feature/2026-07-06-sandbox.md
#	.agents/notes/implemented/feature/2026-07-06-sandbox.zh.md
#	.agents/notes/implemented/feature/2026-07-27-tmux-location-context.i18n.yaml
#	.agents/notes/implemented/simplification/2026-06-20-public-agent-stop-surface.i18n.yaml
#	.agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.i18n.yaml
#	.agents/notes/implemented/simplification/2026-07-30-private-agent-send.i18n.yaml
#	docs/architecture.i18n.yaml
#	docs/architecture.md
#	docs/architecture.zh.md
#	docs/config-catalog.md
#	docs/cordis-catalog/events.md
#	docs/cordis-catalog/services.md
#	docs/core-data-structures/compaction.i18n.yaml
#	docs/core-data-structures/core.i18n.yaml
#	docs/core-data-structures/core.md
#	docs/core-data-structures/core.zh.md
#	docs/core-data-structures/llm-streaming.i18n.yaml
#	docs/core-data-structures/llm-streaming.md
#	docs/core-data-structures/llm-streaming.zh.md
#	docs/core-data-structures/session.i18n.yaml
#	docs/event-producer-consumer.md
#	docs/module-graph.md
#	docs/persistence-catalog.md
#	examples/acp-agent/tests/goal-snapshots/goal-session/session.expected.jsonl
#	examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl
#	examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl
#	examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl
#	examples/acp-agent/tests/snapshots/bash-spill/session.jsonl
#	examples/acp-agent/tests/snapshots/bash-tool-turn/session.jsonl
#	examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl
#	examples/acp-agent/tests/snapshots/cancel-tool-calls/session.jsonl
#	examples/acp-agent/tests/snapshots/cancel/session.jsonl
#	examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl
#	examples/acp-agent/tests/snapshots/code-mode-workspace-context/session.jsonl
#	examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl
#	examples/acp-agent/tests/snapshots/empty-response-retry/session.jsonl
#	examples/acp-agent/tests/snapshots/error-finish/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/fs-edit/session.jsonl
#	examples/acp-agent/tests/snapshots/fs-escalation-approved/session.jsonl
#	examples/acp-agent/tests/snapshots/fs-glob-sampling/session.jsonl
#	examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl
#	examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl
#	examples/acp-agent/tests/snapshots/fs-read/session.jsonl
#	examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl
#	examples/acp-agent/tests/snapshots/fs-write/session.jsonl
#	examples/acp-agent/tests/snapshots/hook-cc-invalid-matcher/session.jsonl
#	examples/acp-agent/tests/snapshots/hook-cc-posttool-block/session.jsonl
#	examples/acp-agent/tests/snapshots/hook-cc-posttool-context/session.jsonl
#	examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl
#	examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/session.jsonl
#	examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/session.jsonl
#	examples/acp-agent/tests/snapshots/hook-cc-stop-continue/session.jsonl
#	examples/acp-agent/tests/snapshots/hook-codex-invalid-matcher/session.jsonl
#	examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl
#	examples/acp-agent/tests/snapshots/hook-codex-posttool-context/session.jsonl
#	examples/acp-agent/tests/snapshots/hook-codex-pretool-block/session.jsonl
#	examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/session.jsonl
#	examples/acp-agent/tests/snapshots/hook-codex-stop-continue/session.jsonl
#	examples/acp-agent/tests/snapshots/lsp-definition/session.jsonl
#	examples/acp-agent/tests/snapshots/multi-turn/session.jsonl
#	examples/acp-agent/tests/snapshots/packed-chunks/session.jsonl
#	examples/acp-agent/tests/snapshots/parallel-tool-calls/session.jsonl
#	examples/acp-agent/tests/snapshots/pty-tools/session.jsonl
#	examples/acp-agent/tests/snapshots/repeat-tool-guard/session.jsonl
#	examples/acp-agent/tests/snapshots/session-query-spill/session.jsonl
#	examples/acp-agent/tests/snapshots/session-sandbox-root/session.jsonl
#	examples/acp-agent/tests/snapshots/session-title-after-turn/session.jsonl
#	examples/acp-agent/tests/snapshots/skill-load/session.jsonl
#	examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.1.jsonl
#	examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.2.jsonl
#	examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.jsonl
#	examples/acp-agent/tests/snapshots/subagent-fork/session.1.jsonl
#	examples/acp-agent/tests/snapshots/subagent-fork/session.jsonl
#	examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl
#	examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl
#	examples/acp-agent/tests/snapshots/subagent-mixed/session.jsonl
#	examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl
#	examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl
#	examples/acp-agent/tests/snapshots/subagent-multi/session.jsonl
#	examples/acp-agent/tests/snapshots/subagent-spawn/session.1.jsonl
#	examples/acp-agent/tests/snapshots/subagent-spawn/session.jsonl
#	examples/acp-agent/tests/snapshots/text-turn/session.jsonl
#	examples/acp-agent/tests/snapshots/todo-write/session.jsonl
#	examples/acp-agent/tests/snapshots/tool-call-turn/session.jsonl
#	examples/acp-agent/tests/snapshots/web-fetch/session.jsonl
#	examples/acp-agent/tests/snapshots/workflow-run/session.1.jsonl
#	examples/acp-agent/tests/snapshots/workflow-run/session.jsonl
#	examples/acp-agent/tests/snapshots/workspace-context/session.jsonl
#	examples/acp-agent/tests/snapshots/workspace-edit/session.jsonl
#	examples/headless-agent/tests/semantic-checkpoint-snapshots/tool-outcome-unknown/session.expected.jsonl
#	examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl
#	examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl
#	examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl
#	examples/headless-agent/tests/snapshots/advanced-toolchain/stream-json.expected.jsonl
#	examples/headless-agent/tests/snapshots/goal-tools/stream-json.expected.jsonl
#	examples/headless-agent/tests/snapshots/missing-credential/stream-json.expected.jsonl
#	examples/headless-agent/tests/snapshots/provider-retry/stream-json.expected.jsonl
#	examples/headless-agent/tests/snapshots/pty-tools/session.jsonl
#	examples/headless-agent/tests/snapshots/pty-tools/stream-json.expected.jsonl
#	examples/headless-agent/tests/snapshots/ralph-loop/stream-json.expected.jsonl
#	examples/headless-agent/tests/subagent-inheritance-snapshots/parent-override/child.expected.jsonl
#	examples/headless-agent/tests/subagent-inheritance-snapshots/parent-override/parent.expected.jsonl
#	examples/jsonrpc-agent/tests/snapshots/bash-tool/notifications.expected.jsonl
#	examples/jsonrpc-agent/tests/snapshots/bash-tool/session.jsonl
#	examples/jsonrpc-agent/tests/snapshots/persistent-tools/notifications.expected.jsonl
#	examples/jsonrpc-agent/tests/snapshots/persistent-tools/session.jsonl
#	examples/jsonrpc-agent/tests/snapshots/subagent-spawn/notifications.expected.jsonl
#	examples/jsonrpc-agent/tests/snapshots/subagent-spawn/session.1.jsonl
#	examples/jsonrpc-agent/tests/snapshots/subagent-spawn/session.jsonl
#	examples/jsonrpc-agent/tests/snapshots/text-turn/notifications.expected.jsonl
#	examples/jsonrpc-agent/tests/snapshots/text-turn/session.jsonl
#	packages/client/runtime/README.i18n.yaml
#	packages/client/runtime/src/client/sessions/request-inspection.ts
#	packages/compact/compact-basic/README.i18n.yaml
#	packages/compact/compact-basic/README.md
#	packages/compact/compact-basic/README.zh.md
#	packages/compact/compact-basic/src/index.ts
#	packages/context/time-context/tests/time-context.spec.ts
#	packages/context/tmux-context/README.i18n.yaml
#	packages/context/tmux-context/tests/tmux-context.spec.ts
#	packages/context/workspace-context/tests/workspace-context.spec.ts
#	packages/cordis/tool-cordis/src/api-catalog.ts
#	packages/core/agent-loop/README.i18n.yaml
#	packages/core/agent-loop/README.md
#	packages/core/agent-loop/README.zh.md
#	packages/core/agent-loop/src/agent.ts
#	packages/core/agent/README.i18n.yaml
#	packages/core/agent/README.md
#	packages/core/agent/README.zh.md
#	packages/core/agent/src/types.ts
#	packages/core/session/README.i18n.yaml
#	packages/core/session/README.md
#	packages/core/session/README.zh.md
#	packages/fs/tool-str-replace-editor/tests/tools.spec.ts
#	packages/goal/command-goal/tests/command-goal.spec.ts
#	packages/goal/goal/tests/goal.spec.ts
#	packages/host/apiproxy/README.i18n.yaml
#	packages/host/apiproxy/README.md
#	packages/host/apiproxy/README.zh.md
#	packages/host/apiproxy/src/api/index.ts
#	packages/host/apiproxy/tests/api-proxy-workspace.spec.ts
#	packages/llm/llm/README.i18n.yaml
#	packages/llm/llm/README.md
#	packages/llm/llm/README.zh.md
#	packages/llm/llm/src/index.ts
#	packages/pty/pty-local/tests/index.spec.ts
#	packages/pty/pty-local/tests/local.spec.ts
#	packages/pty/pty/tests/service.spec.ts
#	packages/pty/tool-bash-persistent/tests/loader-composition.spec.ts
#	packages/pty/tool-bash-persistent/tests/tools.spec.ts
#	packages/pty/tool-pty/tests/loader-composition.spec.ts
#	packages/pty/tool-pty/tests/tools.spec.ts
#	packages/session-persistence/session-checkpoint-policy/tests/crash-recovery.e2e.ts
#	packages/skill/tool-skill/tests/tool-skill.spec.ts
#	packages/tasks/tasks-local/tests/tasks.spec.ts
#	packages/ui/tui/README.i18n.yaml
#	packages/ui/tui/tests/tui.spec.ts
#	packages/ui/user-approval/src/index.ts
#	packages/ui/user-approval/tests/approval.spec.ts
2026-07-31 22:16:40 +08:00

143 lines
7.3 KiB
TypeScript

/**
* Assembled-app regression: a parent-only read-only override is seeded into
* its child log and confines a real write under a wider deployment default.
*/
import { readFile, readdir, writeFile } from 'node:fs/promises'
import { join } from 'node:path'
import { fileURLToPath } from 'node:url'
import { Context } from 'cordis'
import { normalizeSessionLog, scrubRequestHeaders, type NormalizeContext } from '@deepseek-ai/dsh-acp-snapshot'
import { LOADER_SMOKE_TEST_TIMEOUT_MS, runLoaderSmoke } from '@deepseek-ai/dsh-loader-smoke'
import { createUserMessage } from '@deepseek-ai/dsh-llm'
import SessionStore, { SESSION_FORMAT_VERSION, SessionId, type SessionEvent, type SessionHeader } from '@deepseek-ai/dsh-session'
import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
import { describe, expect, it } from 'vitest'
const fixtureDir = fileURLToPath(new URL('./subagent-inheritance-snapshots/parent-override', import.meta.url))
const replayOverride = join(fixtureDir, 'replay.override.json')
const childReplay = join(fixtureDir, 'child.replay.jsonl')
const parentExpected = join(fixtureDir, 'parent.expected.jsonl')
const childExpected = join(fixtureDir, 'child.expected.jsonl')
const configPath = fileURLToPath(new URL('../subagent-inheritance.cordis.snapshot.yml', import.meta.url))
const binScript = fileURLToPath(new URL('../../../packages/examples/cli-demo/src/bin.ts', import.meta.url))
const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
const sessionId = SessionId('subagent-inheritance-parent')
const refreshing = process.env.DSH_SNAPSHOT === 'refresh'
const task = 'Delegate the write probe to a subagent.'
/** Seed a completed parent turn with the only read-only fact in the app. */
async function seedReadOnlyParent(root: string, cwd: string): Promise<void> {
const ctx = new Context()
await ctx.plugin(SessionStore)
await ctx.plugin(SessionPersistenceJsonl, { root, compression: 'none' })
const meta: SessionHeader = {
version: SESSION_FORMAT_VERSION,
id: sessionId,
createdAt: 1,
cwd,
delegationDepth: 0,
}
const events: SessionEvent[] = [
{ type: 'turn/start', seq: 0, time: 10, data: { turn: 1 } },
{ type: 'user/message', seq: 1, time: 11, data: createUserMessage({ content: [{ type: 'text', text: 'Tighten this session to read-only.' }], source: { kind: 'user' } }), surfaceOp: 'append' },
{ type: 'sandbox/mode', seq: 2, time: 12, data: { mode: 'read-only' } },
{ type: 'turn/end', seq: 3, time: 13, data: { turn: 1, reason: { kind: 'completed' } } },
]
try {
await ctx.sessionPersistence.create(meta)
await ctx.sessionPersistence.append(sessionId, events)
} finally {
await ctx.fiber.dispose()
}
}
describe('parent-only override inheritance snapshot', () => {
it('confines a delegated child through the assembled headless app', async () => {
let cwd = ''
const result = await runLoaderSmoke({
label: 'subagent inheritance headless stream-json snapshot',
tempDirPrefix: 'dsh-subagent-inherit-',
binScript,
configPath,
binArgs: ['--config', configPath, '--output-format', 'stream-json', task],
tsconfigPath,
env: {
// The primary fixture path must exist for llm-replay's config guard;
// the override sidecar fully replaces the derived parent script.
DSH_SNAPSHOT_FILE: replayOverride,
DSH_SNAPSHOT_OVERRIDE: replayOverride,
DSH_SNAPSHOT_CHILD_FILES: childReplay,
},
prepare: async (runCwd) => {
cwd = runCwd
await seedReadOnlyParent(join(runCwd, '.sessions'), runCwd)
},
inspect: async (runCwd) => {
// THE physical fact: the child's write never reached the disk. Under
// the deployment default (workspace-write) alone it would succeed.
await expect(readFile(join(runCwd, 'inherited.txt'), 'utf8')).rejects.toMatchObject({ code: 'ENOENT' })
// Collect both persisted logs (parent resumed turn + child run).
const sessionsDir = join(runCwd, '.sessions')
const files = (await readdir(sessionsDir, { recursive: true })).filter(file => file.endsWith('.jsonl'))
const logs = await Promise.all(files.map(async file => readFile(join(sessionsDir, file), 'utf8')))
const headerOf = (content: string): Record<string, unknown> =>
JSON.parse(content.split('\n')[0] ?? '{}') as Record<string, unknown>
const parent = logs.find(content => content.includes('"subagent-inheritance-parent"'))
const child = logs.find(content => typeof headerOf(content).parentSession === 'string')
if (parent === undefined || child === undefined) throw new Error('missing persisted parent or child log')
const childRecords = child.trimEnd().split('\n').map(
line => JSON.parse(line) as Record<string, unknown>,
)
expect(childRecords[1]).toMatchObject({
type: 'sandbox/mode',
seq: 0,
data: { mode: 'read-only', source: 'delegation' },
})
const runtimeContexts = (content: string): string[] => content.trimEnd().split('\n').flatMap((line) => {
const record = JSON.parse(line) as {
type?: string
data?: { source?: { kind?: string; plugin?: string }; content?: Array<{ type?: string; text?: unknown }> }
}
if (record.type !== 'user/message'
|| record.data?.source?.kind !== 'plugin'
|| record.data.source.plugin !== '@deepseek-ai/dsh-system-prompt') return []
return record.data.content?.flatMap(block => block.type === 'text' && typeof block.text === 'string' ? [block.text] : []) ?? []
})
const policyContexts = [...runtimeContexts(parent), ...runtimeContexts(child)]
expect(policyContexts).toHaveLength(2)
for (const context of policyContexts) {
expect(context).toContain('Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode.')
expect(context).toContain('Do not refuse a required modification from this policy alone')
expect(context).not.toContain('write and edit tools')
expect(context).not.toContain('one-shot bash commands')
expect(context).not.toContain('terminal sessions')
}
const context: NormalizeContext = { sessionIds: [sessionId, String(headerOf(child).id)], cwd }
const normalizedParent = scrubRequestHeaders(normalizeSessionLog(parent, context))
const normalizedChild = scrubRequestHeaders(normalizeSessionLog(child, context))
if (refreshing) {
await writeFile(parentExpected, normalizedParent)
await writeFile(childExpected, normalizedChild)
}
expect(normalizedParent).toBe(await readFile(parentExpected, 'utf8'))
expect(normalizedChild).toBe(await readFile(childExpected, 'utf8'))
// The child's real write was denied by the real fence.
expect(normalizedChild).toContain('file access denied under read-only mode')
},
})
expect(result.stderr).toBe('')
const records = result.stdout.trimEnd().split('\n').map(line => JSON.parse(line) as Record<string, unknown>)
expect(records.at(-1)).toMatchObject({
type: 'result',
sessionId,
output: 'The delegated child was denied by the sandbox. PARENT_DONE',
})
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
})