Files
deepseek-harness/packages/pty/tool-bash-persistent/tests/loader-composition.spec.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

160 lines
6.1 KiB
TypeScript

import { mkdtemp, rm, writeFile } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { pathToFileURL } from 'node:url'
import { afterEach, describe, expect, it } from 'vitest'
import { Context } from 'cordis'
import Loader from '@cordisjs/plugin-loader'
import Include from '@cordisjs/plugin-include'
import { CallId } from '@deepseek-ai/dsh-llm'
import { Session, SessionId } from '@deepseek-ai/dsh-session'
import AgentRegistry, { Inbox } from '@deepseek-ai/dsh-agent'
import type { Agent } from '@deepseek-ai/dsh-agent'
import PtyService from '@deepseek-ai/dsh-pty'
import * as PtyLocal from '@deepseek-ai/dsh-pty-local'
import SandboxProvider from '@deepseek-ai/dsh-sandbox'
import type { ConfinedArgv, SandboxPolicy } from '@deepseek-ai/dsh-sandbox'
import SandboxPolicyService from '@deepseek-ai/dsh-sandbox-policy'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry from '@deepseek-ai/dsh-tools'
import * as ToolBashPersistent from '@deepseek-ai/dsh-tool-bash-persistent'
let root: string | undefined
let context: Context | undefined
afterEach(async () => {
await context?.fiber.dispose()
context = undefined
if (root !== undefined) await rm(root, { recursive: true, force: true })
root = undefined
})
class PassthroughSandbox extends SandboxProvider {
confine(argv: readonly string[], _policy: SandboxPolicy): ConfinedArgv {
return { argv: [...argv], enforcement: 'full', denialSignatures: [], runnerFailureSignatures: [] }
}
}
function agent(ctx: Context, cwd: string): Agent {
const id = SessionId('persistent-bash-loader-agent')
const scope = ctx.plugin(() => {})
const session = new Session(id, [], { version: 0, id, createdAt: 0, cwd })
const value: Agent = {
id,
options: {},
session,
inbox: new Inbox(session, { inserted: () => {}, discarded: () => {} }),
status: 'idle',
ctx: scope.ctx,
send: () => {},
followup: () => {},
steer: () => {},
inject: () => {},
updateInbox: () => 'not-found',
reserveTurnAdmission: () => undefined,
cancel() {},
whenIdle: () => Promise.resolve(),
}
ctx.agents.register(value)
return value
}
function text(result: { content: { type: string; text?: string }[] }): string {
return result.content.filter(block => block.type === 'text').map(block => block.text).join('')
}
const suite = process.platform === 'linux' || process.platform === 'darwin' ? describe : describe.skip
suite('persistent Bash through a real cordis.yml Loader composition', () => {
it('preserves cwd and environment across calls', async () => {
root = await mkdtemp(join(tmpdir(), 'dsh-persistent-bash-loader-'))
const configPath = join(root, 'cordis.yml')
await writeFile(configPath, [
"- name: '@deepseek-ai/dsh-agent'",
"- name: '@deepseek-ai/dsh-system-prompt'",
"- name: '@deepseek-ai/dsh-tools'",
"- name: '@deepseek-ai/dsh-pty'",
"- name: '@deepseek-ai/dsh-test-sandbox'",
"- name: '@deepseek-ai/dsh-sandbox-policy'",
' config:',
' mode: danger-full-access',
` workspaceRoot: ${JSON.stringify(root)}`,
"- name: '@deepseek-ai/dsh-pty-local'",
' config:',
' pollIntervalMs: 10',
' exactProbeAfterMs: 20',
' idleSilenceMs: 100',
' handoffGraceMs: 100',
' scrollbackLines: 20000',
' timeoutMs: 2000',
' disposeGraceMs: 500',
"- name: '@deepseek-ai/dsh-tool-bash-persistent'",
' config:',
' timeoutMs: 5000',
'',
].join('\n'))
context = new Context()
context.baseUrl = pathToFileURL(root).href + '/'
await context.plugin(Loader)
context.loader.builtins.include = Include
const modules = new Map<string, unknown>([
['@deepseek-ai/dsh-agent', AgentRegistry],
['@deepseek-ai/dsh-system-prompt', SystemPrompt],
['@deepseek-ai/dsh-tools', ToolRegistry],
['@deepseek-ai/dsh-pty', PtyService],
['@deepseek-ai/dsh-test-sandbox', PassthroughSandbox],
['@deepseek-ai/dsh-sandbox-policy', SandboxPolicyService],
['@deepseek-ai/dsh-pty-local', PtyLocal],
['@deepseek-ai/dsh-tool-bash-persistent', ToolBashPersistent],
])
context.loader.internal = {
version: 'v2',
async import(specifier: string) {
if (!modules.has(specifier)) throw new Error(`unexpected Loader import: ${specifier}`)
return modules.get(specifier)
},
} as unknown as NonNullable<typeof context.loader.internal>
await context.loader.create({ name: 'cordis:include', config: { path: pathToFileURL(configPath).href } })
await context.loader.await()
const owner = agent(context, root)
const signal = new AbortController().signal
const execute = (id: string, command: string) => context!.tools.execute({
signal,
callId: CallId(id),
name: 'bash',
arguments: { command },
agent: owner,
})
expect(context.tools.schemas().map(schema => schema.name)).toEqual(['bash'])
await execute('state', 'export KEEP=loader; mkdir -p nested; cd nested')
const observed = text(await execute('observe', 'printf "cwd=%s keep=%s\\n" "$PWD" "$KEEP"'))
expect(observed).toContain(`cwd=${join(root, 'nested')} keep=loader`)
expect(observed).not.toContain('DSH_PERSISTENT_BASH')
const multiline = text(await execute(
'multiline',
'value="line one"\nprintf "%s:%s\\n" "$value" "it\'s fine"',
))
expect(multiline).toBe("line one:it's fine")
expect(multiline).not.toContain('DSH_PERSISTENT_BASH')
const heredoc = text(await execute(
'heredoc',
"cat <<'EOF'\nalpha\nbeta\nEOF",
))
expect(heredoc).toBe('alpha\nbeta')
const large = text(await execute('large-output', 'seq 1 12050'))
expect(large.startsWith('1\n2\n3\n')).toBe(true)
expect(large).toContain('<response clipped>')
expect(large).not.toContain('beginning of this command output was dropped')
const exited = text(await execute('exit', 'exit'))
expect(exited).toContain('next bash call starts from the workspace')
expect(text(await execute('after-exit', 'printf "%s\\n" "$PWD"'))).toBe(root)
}, 20_000)
})