Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge commit '5427cbcc19cfd1ce9f3af1ae22207852cc5740fa' into codex/workflow-runs-chat-node-f6

Browse Source
This commit is contained in:
pku-xht
2026-08-11 18:09:43 +08:00
parent 791d0b7233 1d12ae62e7
commit b38e02462b
3060 changed files with 45805 additions and 34331 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/headless-agent/README.i18n.yaml
View File

@@ -2,5 +2,5 @@
# side as of the last confirmed-consistent state. Both languages carry equal authority;
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write examples/headless-agent/README.md
README.md: f12a56920c79f3a7e257c4e56163f323e4312d11
README.zh.md: 9e409735f03afc62cd788fa2a5d1afdef0fa6c2a
README.md: 2f854924d4bfd2bf66b3d6f47433136098d7b762
README.zh.md: 4128645da8a0f8a84b17d819fc614051b68f2a11

4
examples/headless-agent/README.md
View File

@@ -10,10 +10,10 @@ This directory owns the replay and real-model test composition for a headless co
# repo root .env (gitignored) or exported env:
# DEEPSEEK_API_KEY=sk-…
# DEEPSEEK_BASE_URL=https://… # optional; defaults to the public API
pnpm run dsh run "fix the failing test in this workspace"
pnpm dsh --profile headless "fix the failing test in this workspace"
```
The product command is [`dsh run`](../../apps/cli/README.md): it accepts one nonblank task, creates and persists a fresh session, prints the final assistant text, and exits. The root `demo:headless` script is only an alias of that command.
The product command is [`dsh --profile headless`](../../apps/cli/README.md): it accepts one nonblank task, creates and persists a fresh session, prints the final assistant text, and exits.
Snapshot suites run this directory's configuration through [`tests/fixtures/headless-driver.ts`](tests/fixtures/headless-driver.ts), an unexported test-only process that emits canonical session events as JSONL before its result record. That stream is test infrastructure, not a supported CLI output format. Child sessions surface only through parent tool events and results.

4
examples/headless-agent/README.zh.md
View File

@@ -10,10 +10,10 @@
# repo root .env (gitignored) or exported env:
# DEEPSEEK_API_KEY=sk-…
# DEEPSEEK_BASE_URL=https://… # optional; defaults to the public API
pnpm run dsh run "fix the failing test in this workspace"
pnpm dsh --profile headless "fix the failing test in this workspace"
```
产品命令是 [`dsh run`](../../apps/cli/README.md)：它接受一项非空任务，创建并持久化新会话，打印最终 assistant 文本，然后退出。根目录的 `demo:headless` 脚本只是该命令的别名。
产品命令是 [`dsh --profile headless`](../../apps/cli/README.md)：它接受一项非空任务，创建并持久化新会话，打印最终 assistant 文本，然后退出。
快照套件通过 [`tests/fixtures/headless-driver.ts`](tests/fixtures/headless-driver.ts) 运行本目录的配置。这个未导出且仅供测试使用的进程会在结果记录之前，以 JSONL 发出规范会话事件。该事件流属于测试基础设施，不是受支持的 CLI（命令行界面）输出格式。子会话只通过父会话的工具事件和结果对外显示。

2
examples/headless-agent/advanced.cordis.snapshot.yml
View File

@@ -8,7 +8,7 @@
# disables the key-requiring DeepSeek adapter and inserts `llm-replay` to serve
# recorded JSONL without a key or network.
- id: base
name: '@cordisjs/plugin-include'
name: '@deepseek-ai/cordis-plugin-include'
config:
path: ./cordis.yml
patches:

2
examples/headless-agent/advanced.cordis.yml
View File

@@ -1,6 +1,6 @@
# Add Code Mode and Cordis tools to the headless spawn/workflow stack.
- id: base
name: '@cordisjs/plugin-include'
name: '@deepseek-ai/cordis-plugin-include'
config:
path: ./cordis.yml
patches:

2
examples/headless-agent/compaction.cordis.snapshot.yml
View File

@@ -1,6 +1,6 @@
# Keyless context-overflow composition for the assembled compaction snapshot.
- id: base
name: '@cordisjs/plugin-include'
name: '@deepseek-ai/cordis-plugin-include'
config:
path: ./cordis.yml
patches:

6
examples/headless-agent/cordis.yml
View File

@@ -118,12 +118,16 @@
backgroundMode: continuable
maxDepth: 1
# Fork stays one-shot because a continuable child's `report` tool and prompt
# section precede the inherited history a fork reuses; `run_in_background` is off
# because this example mounts no task service. See .agents/notes/implemented/architecture/2026-08-10-fork-children-stay-one-shot.md.
- id: tool-subagent-fork
name: '@deepseek-ai/dsh-tool-subagent'
config:
provider: fork
toolName: subagent_fork
backgroundMode: continuable
backgroundMode: one-shot
enableRunInBackground: false
maxDepth: 1
# The worker-thread workflow engine fans a model-written JavaScript script's

2
examples/headless-agent/credentials.cordis.snapshot.yml
View File

@@ -3,7 +3,7 @@
# the deepseek-official route still registers — so the prompt fails with the actionable
# MISSING_CREDENTIAL guidance this snapshot pins as first-run UX.
- id: base
name: '@cordisjs/plugin-include'
name: '@deepseek-ai/cordis-plugin-include'
config:
path: ./cordis.yml
patches:

2
examples/headless-agent/e2b.cordis.yml
View File

@@ -8,7 +8,7 @@
# falls back to /home/user/workspace while Bash and PTY keep targeting the
# host path, so every tool call fails with a remote spawn error.
- id: base
name: '@cordisjs/plugin-include'
name: '@deepseek-ai/cordis-plugin-include'
config:
path: ./advanced.cordis.yml
patches:

2
examples/headless-agent/goal.cordis.snapshot.yml
View File

@@ -2,7 +2,7 @@
# a config patch cannot target an entry behind a nested include, then restates
# the goal overlay while replacing the live model with keyless replay.
- id: base
name: '@cordisjs/plugin-include'
name: '@deepseek-ai/cordis-plugin-include'
config:
path: ./cordis.yml
patches:

2
examples/headless-agent/goal.cordis.yml
View File

@@ -1,6 +1,6 @@
# Add the persisted goal domain and its model-facing tools to the real one-shot app.
- id: base
name: '@cordisjs/plugin-include'
name: '@deepseek-ai/cordis-plugin-include'
config:
path: ./cordis.yml
patches:

2
examples/headless-agent/pty.cordis.snapshot.yml
View File

@@ -1,6 +1,6 @@
# Keyless opt-in PTY composition for the headless stream-json snapshot.
- id: base
name: '@cordisjs/plugin-include'
name: '@deepseek-ai/cordis-plugin-include'
config:
path: ./cordis.yml
patches:

2
examples/headless-agent/ralph.cordis.snapshot.yml
View File

@@ -1,6 +1,6 @@
# Replay counterpart to cordis.yml for the shipped Ralph-loop snapshot.
- id: base
name: '@cordisjs/plugin-include'
name: '@deepseek-ai/cordis-plugin-include'
config:
path: ./cordis.yml
patches:

2
examples/headless-agent/retry.cordis.snapshot.yml
View File

@@ -1,6 +1,6 @@
# Keyless provider-retry composition for the headless stream-json snapshot.
- id: base
name: '@cordisjs/plugin-include'
name: '@deepseek-ai/cordis-plugin-include'
config:
path: ./cordis.yml
patches:

21
examples/headless-agent/subagent-settlement.cordis.snapshot.yml Normal file
View File

@@ -0,0 +1,21 @@
# Keyless assembled-app coverage for continuable child settlement delivery. The
# replay child deliberately never calls report; the parent can reach its final
# answer only if the continuation manager places the child's closing message in
# the parent turn without list_agents, send_message, or a Task collector.
- id: base
name: '@deepseek-ai/cordis-plugin-include'
config:
path: ./cordis.yml
patches:
- id: llm-deepseek
name: '@deepseek-ai/dsh-llm-deepseek'
disabled: true
- insert:
- id: llm-replay
name: '@deepseek-ai/dsh-llm-replay'
# Prevent platform scheduling from choosing a streamed-chunk interleave. The
# fence releases only after the real manager notice enters the parent inbox.
- id: settlement-fence
name: './tests/fixtures/subagent-settlement-fence.ts'

2
examples/headless-agent/tests/code-mode.e2e.ts
View File

@@ -2,7 +2,7 @@ import { mkdtemp, mkdir, readFile, rm, writeFile } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { afterEach, describe, expect, it, vi } from 'vitest'
import { Context } from 'cordis'
import { Context } from '@deepseek-ai/cordis'
import LlmService, { createUserMessage, CallId, HarnessError } from '@deepseek-ai/dsh-llm'
import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
import type { SessionEvent } from '@deepseek-ai/dsh-session'

2
examples/headless-agent/tests/coding-task.e2e.ts
View File

@@ -4,7 +4,7 @@ import { mkdtemp, readFile, rm, writeFile } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { afterEach, describe, expect, it } from 'vitest'
import type { Context } from 'cordis'
import type { Context } from '@deepseek-ai/cordis'
import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts'
import { SessionId } from '@deepseek-ai/dsh-session'

2
examples/headless-agent/tests/compaction.e2e.ts
View File

@@ -3,7 +3,7 @@ import { mkdtemp, rm, writeFile } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { afterEach, describe, expect, it } from 'vitest'
import type { Context } from 'cordis'
import type { Context } from '@deepseek-ai/cordis'
import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts'
import { SessionId } from '@deepseek-ai/dsh-session'

2
examples/headless-agent/tests/fixtures/cli-mock-llm.ts vendored
View File

@@ -1,4 +1,4 @@
import type { Context } from 'cordis'
import type { Context } from '@deepseek-ai/cordis'
import {
CallId,
LlmAdapter,

5
examples/headless-agent/tests/fixtures/cli.cordis.yml vendored
View File

@@ -1,11 +1,8 @@
- id: cli-mock-llm
name: './cli-mock-llm.ts'
- id: repository-plugin-fixture
name: './repository-plugin/load.mjs'
- id: base
name: '@cordisjs/plugin-include'
name: '@deepseek-ai/cordis-plugin-include'
config:
path: ../../cordis.yml
patches:

2
examples/headless-agent/tests/fixtures/deepseek-defaults.cordis.yml vendored
View File

@@ -1,5 +1,5 @@
- id: base
name: '@cordisjs/plugin-include'
name: '@deepseek-ai/cordis-plugin-include'
config:
path: ../../cordis.yml
patches:

2
examples/headless-agent/tests/fixtures/goal-domain/seed-goal.ts vendored
View File

@@ -1,6 +1,6 @@
/** Test-only Loader plugin that creates a goal at the first real step edge. */
import type { Context } from 'cordis'
import type { Context } from '@deepseek-ai/cordis'
import type {} from '@deepseek-ai/dsh-goal'
export const name = 'seed-goal'

2
examples/headless-agent/tests/fixtures/headless-driver.ts vendored
View File

@@ -1,7 +1,7 @@
#!/usr/bin/env node
/** Snapshot-only Loader driver: stream one fixture turn as canonical JSONL. */
import type { Context } from 'cordis'
import type { Context } from '@deepseek-ai/cordis'
import { boot, installFailLoud, loadEnv, resolveConfigPath } from '@deepseek-ai/dsh-app-boot'
import { runFixtureTurn } from '@deepseek-ai/dsh-loader-smoke'
import type { SessionEvent } from '@deepseek-ai/dsh-session'

0
examples/headless-agent/tests/fixtures/dsh-run.cordis.yml → examples/headless-agent/tests/fixtures/headless-profile.cordis.yml vendored
View File

6
examples/headless-agent/tests/fixtures/repository-plugin/dsh-plugin-assets/skills/0/repository-fixture/SKILL.md vendored
View File

@@ -1,6 +0,0 @@
---
name: repository-fixture
description: Repository fixture skill.
---
Static instructions from a prepared repository plugin.

19
examples/headless-agent/tests/fixtures/repository-plugin/dsh-plugin.mjs vendored
View File

@@ -1,19 +0,0 @@
// Generated by dsh-plugin-prepare. Do not edit.
const manifest = {"name":"headless-repository-fixture","skills":["dsh-plugin-assets/skills/0"]}
// Value mirror: Cordis const enum FiberState.ACTIVE; keep aligned with dsh-repository-plugin source.ts.
const FIBER_ACTIVE = 2
export const name = "headless-repository-fixture"
export const inject = ["loader","skills"]
async function mount(ctx, plugin, label, config) {
const fiber = ctx.plugin(plugin, config)
await fiber
if (fiber.state !== FIBER_ACTIVE) {
const missing = Object.keys(fiber.inject).filter(service => fiber.ctx.get(service) === undefined)
throw new Error(`${label} did not activate (waiting for services: ${missing.join(', ') || 'unknown'})`)
}
}
export async function apply(ctx) {
const runtime = ctx.loader.builtins["dsh-repository-plugin"]
if (runtime === undefined) throw new Error("missing Cordis builtin dsh-repository-plugin")
await mount(ctx, runtime, 'repository Plugin runtime', { baseUrl: import.meta.url, manifest })
}

13
examples/headless-agent/tests/fixtures/repository-plugin/load.mjs vendored
View File

@@ -1,13 +0,0 @@
/**
* Keyless fixture owner that mounts the runtime before its prepared wrapper.
* Cordis starts sibling Loader entries concurrently, so row order is not a dependency edge.
*/
import * as RepositoryPlugin from '@deepseek-ai/dsh-repository-plugin'
import * as PreparedPlugin from './dsh-plugin.mjs'
export const name = 'headless-repository-fixture-loader'
export async function apply(ctx) {
await ctx.plugin(RepositoryPlugin)
await ctx.plugin(PreparedPlugin)
}

2
examples/headless-agent/tests/fixtures/retry-snapshot-backend.mjs vendored
View File

@@ -46,7 +46,7 @@ export const inject = ['llm']
/**
* Register the deterministic provider adapter.
* @param {import('cordis').Context} ctx - plugin context carrying the LLM service.
* @param {import('@deepseek-ai/cordis').Context} ctx - plugin context carrying the LLM service.
*/
export function apply(ctx) {
ctx.llm.registerAdapter(['deepseek-official'], new RetrySnapshotAdapter())

2
examples/headless-agent/tests/fixtures/semantic-checkpoint-agent.ts vendored
View File

@@ -3,7 +3,7 @@
* @module semantic-checkpoint-agent
*/
import type { Context } from 'cordis'
import type { Context } from '@deepseek-ai/cordis'
import type { SessionId } from '@deepseek-ai/dsh-session'
/** Fixture plugin name. */

2
examples/headless-agent/tests/fixtures/subagent-diagnostic-agent.ts vendored
View File

@@ -4,7 +4,7 @@
* @module subagent-diagnostic-agent
*/
import type { Context } from 'cordis'
import type { Context } from '@deepseek-ai/cordis'
import type { SessionId } from '@deepseek-ai/dsh-session'
/** Fixture plugin name. */

2
examples/headless-agent/tests/fixtures/subagent-inheritance-agent.ts vendored
View File

@@ -3,7 +3,7 @@
* @module subagent-inheritance-agent
*/
import type { Context } from 'cordis'
import type { Context } from '@deepseek-ai/cordis'
import type { SessionId } from '@deepseek-ai/dsh-session'
/** Fixture plugin name. */

43
examples/headless-agent/tests/fixtures/subagent-settlement-fence.ts vendored Normal file
View File

@@ -0,0 +1,43 @@
/**
* Loader fixture that holds the parent's second step until settlement delivery.
* @module subagent-settlement-fence
*/
import type { Context } from '@deepseek-ai/cordis'
import type {} from '@deepseek-ai/dsh-agent-loop'
import type {} from '@deepseek-ai/dsh-subagent'
/** Fixture plugin name. */
export const name = 'subagent-settlement-fence'
/**
* Fence the parent's post-spawn request behind admission of the manager notice.
*
* This pins content order, not step placement: the held pre-step runs after its
* own `Inbox.claim()`, so the notice lands after step 2's claim and is claimed at
* step 3 because the child's settlement pipeline is strictly longer than the
* parent's claim path, not because a barrier forces it.
* @param ctx - assembled headless-agent context.
*/
export function apply(ctx: Context): void {
const delivered = Promise.withResolvers<undefined>()
let hasDelivered = false
ctx.effect(() => {
const disposeInbox = ctx.root.on('agent/inbox/inserted', ({ agent, message }) => {
if (agent.session.header.parentSession !== undefined || message.source.kind !== 'subagent-settled') return
hasDelivered = true
delivered.resolve(undefined)
})
const disposeStep = ctx.root.on('agent/pre-step', async ({ agent, turn, step }, next) => {
if (agent.session.header.parentSession === undefined && turn === 1 && step === 2 && !hasDelivered) {
await delivered.promise
}
return next()
})
return () => {
disposeStep()
disposeInbox()
}
}, 'subagent-settlement-fence.listeners')
}

2
examples/headless-agent/tests/fixtures/telemetry-otel.cordis.yml vendored
View File

@@ -3,7 +3,7 @@
# The redact-rule entry models a deployment mounting its own scrub rule on the
# telemetry/record waterfall — the seam itself ships no rules.
- id: logger-console
name: '@cordisjs/plugin-logger-console'
name: '@deepseek-ai/cordis-plugin-logger-console'
config:
colors: false
levels:

2
examples/headless-agent/tests/fixtures/telemetry-redact-rule.ts vendored
View File

@@ -1,4 +1,4 @@
import type { Context } from 'cordis'
import type { Context } from '@deepseek-ai/cordis'
/**
* Deployment-style redaction rule for the telemetry e2e: scrubs the fixture

2
examples/headless-agent/tests/fixtures/time-context-mock-llm.ts vendored
View File

@@ -1,4 +1,4 @@
import type { Context } from 'cordis'
import type { Context } from '@deepseek-ai/cordis'
import { LlmAdapter, type StreamChunk } from '@deepseek-ai/dsh-llm'
/** Deterministic one-step adapter for the time-context Loader fixture. */

2
examples/headless-agent/tests/fixtures/workspace-context-resume-agent.ts vendored
View File

@@ -3,7 +3,7 @@
* @module workspace-context-resume-agent
*/
import type { Context } from 'cordis'
import type { Context } from '@deepseek-ai/cordis'
import type { SessionId } from '@deepseek-ai/dsh-session'
/** Fixture plugin name. */

2
examples/headless-agent/tests/full-loop.e2e.ts
View File

@@ -3,7 +3,7 @@ import { mkdtemp, rm } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { afterEach, describe, expect, it } from 'vitest'
import type { Context } from 'cordis'
import type { Context } from '@deepseek-ai/cordis'
import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts'
import { SessionId } from '@deepseek-ai/dsh-session'

2
examples/headless-agent/tests/harness.ts
View File

@@ -1,4 +1,4 @@
import { Context } from 'cordis'
import { Context } from '@deepseek-ai/cordis'
import type { SessionEvent } from '@deepseek-ai/dsh-session'
import type { Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'

109
examples/headless-agent/tests/headless.snapshot.ts
View File

@@ -45,6 +45,8 @@ const credentialsConfigPath = fileURLToPath(new URL('../credentials.cordis.snaps
const invalidCredentialScenarioDir = join(snapshotsDir, 'invalid-credential')
const ralphScenarioDir = join(snapshotsDir, 'ralph-loop')
const ralphConfigPath = fileURLToPath(new URL('../ralph.cordis.snapshot.yml', import.meta.url))
const settlementScenarioDir = join(snapshotsDir, 'subagent-settlement')
const settlementConfigPath = fileURLToPath(new URL('../subagent-settlement.cordis.snapshot.yml', import.meta.url))
const startupFailureConfigPath = fileURLToPath(new URL('./fixtures/startup-activation-error/cordis.yml', import.meta.url))
const startupFailureExpected = join(snapshotsDir, 'startup-activation-error', 'stderr.expected.txt')
const binScript = fileURLToPath(new URL('./fixtures/headless-driver.ts', import.meta.url))
@@ -52,9 +54,9 @@ const dshBinScript = fileURLToPath(new URL('../../../apps/cli/src/bin.ts', impor
const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
const reasoningConfigPath = fileURLToPath(new URL('./fixtures/cli.cordis.yml', import.meta.url))
const deepseekDefaultsConfigPath = fileURLToPath(new URL('./fixtures/deepseek-defaults.cordis.yml', import.meta.url))
const dshRunOverlayPath = fileURLToPath(new URL('./fixtures/dsh-run.cordis.yml', import.meta.url))
const dshRunSessionExpected = join(snapshotsDir, 'dsh-run', 'session.expected.jsonl')
const dshRunFailureExpected = join(snapshotsDir, 'dsh-run', 'stderr.expected.txt')
const headlessOverlayPath = fileURLToPath(new URL('./fixtures/headless-profile.cordis.yml', import.meta.url))
const headlessSessionExpected = join(snapshotsDir, 'headless-profile', 'session.expected.jsonl')
const headlessFailureExpected = join(snapshotsDir, 'headless-profile', 'stderr.expected.txt')
const cliMockLlmPluginPath = fileURLToPath(new URL('./fixtures/cli-mock-llm.ts', import.meta.url))
const refreshing = process.env.DSH_SNAPSHOT === 'refresh'
@@ -217,14 +219,14 @@ async function prepareCliMockFixture(cwd: string): Promise<void> {
}
describe('headless stream-json snapshots', () => {
it('runs one task through the product dsh run command', async () => {
const task = 'Prove the product dsh run path with one real tool round trip.'
it('runs one task through the product headless profile command', async () => {
const task = 'Prove the product headless profile path with one real tool round trip.'
const result = await runLoaderSmoke({
label: 'product dsh run snapshot',
tempDirPrefix: 'headless-snapshot-dsh-run-',
label: 'product headless profile snapshot',
tempDirPrefix: 'headless-snapshot-profile-',
binScript: dshBinScript,
configPath: dshRunOverlayPath,
binArgs: ['run', '--patch', dshRunOverlayPath, task],
configPath: headlessOverlayPath,
binArgs: ['--profile', 'headless', '--patch', headlessOverlayPath, task],
tsconfigPath,
env: {
DSH_PERMISSION_MODE: 'danger-full-access',
@@ -236,11 +238,11 @@ describe('headless stream-json snapshots', () => {
const logs = await persistedLogs(cwd, join(cwd, '.dsh', 'sessions'))
expect(logs).toHaveLength(1)
const actual = logs[0]
if (actual === undefined) throw new Error('dsh run did not persist its session')
if (actual === undefined) throw new Error('the headless profile did not persist its session')
const context = contextFromLogs([actual.content])
const session = scrubRequestHeaders(normalizeSessionLog(actual.content, context))
if (refreshing) await writeFile(dshRunSessionExpected, session)
expect(session).toBe(await readFile(dshRunSessionExpected, 'utf8'))
if (refreshing) await writeFile(headlessSessionExpected, session)
expect(session).toBe(await readFile(headlessSessionExpected, 'utf8'))
expect(session).toContain(task)
expect(session).toContain('CLI tool round trip complete: CLI_TOOL_ROUND_TRIP')
},
@@ -250,13 +252,13 @@ describe('headless stream-json snapshots', () => {
expect(result.stderr).toBe('')
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
it('prints a terminal model failure through the product dsh run command', async () => {
it('prints a terminal model failure through the product headless profile command', async () => {
const result = await runLoaderSmoke({
label: 'product dsh run model failure snapshot',
tempDirPrefix: 'headless-snapshot-dsh-run-failure-',
label: 'product headless profile model failure snapshot',
tempDirPrefix: 'headless-snapshot-profile-failure-',
binScript: dshBinScript,
configPath: dshRunOverlayPath,
binArgs: ['run', '--patch', dshRunOverlayPath, 'Trigger the keyless model failure.'],
configPath: headlessOverlayPath,
binArgs: ['--profile', 'headless', '--patch', headlessOverlayPath, 'Trigger the keyless model failure.'],
tsconfigPath,
expectedExitCode: 1,
env: {
@@ -268,7 +270,7 @@ describe('headless stream-json snapshots', () => {
})
expect(result.stdout).toBe('\n')
await expect(result.stderr).toMatchFileSnapshot(dshRunFailureExpected)
await expect(result.stderr).toMatchFileSnapshot(headlessFailureExpected)
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
it('prints the original Loader activation error through the assembled one-shot app', async () => {
@@ -777,6 +779,77 @@ describe('headless stream-json snapshots', () => {
expect(normalized).toBe(await readFile(streamExpected, 'utf8'))
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
it('delivers a continuable child result without parent polling', async () => {
const parentReplay = join(settlementScenarioDir, 'parent.replay.jsonl')
const parentOverride = join(settlementScenarioDir, 'parent.override.json')
const childReplay = join(settlementScenarioDir, 'child.replay.jsonl')
const childExpected = join(settlementScenarioDir, 'child.expected.jsonl')
const streamExpected = join(settlementScenarioDir, 'stream-json.expected.jsonl')
const task = 'Start one continuable background subagent and answer from its completion notice. Do not call list_agents, send_message, task_output, or task_list.'
let runCwd = ''
const result = await runLoaderSmoke({
label: 'continuable settlement headless stream-json snapshot',
tempDirPrefix: 'headless-snapshot-subagent-settlement-',
binScript,
libBinScript: binScript,
configPath: settlementConfigPath,
binArgs: [settlementConfigPath, task],
tsconfigPath,
env: {
// The override fully supplies the parent script; the child fixture
// remains separate so replay binds it to the fresh child Session.
DSH_SNAPSHOT_FILE: parentReplay,
DSH_SNAPSHOT_OVERRIDE: parentOverride,
DSH_SNAPSHOT_CHILD_FILES: childReplay,
NODE_OPTIONS: [process.env.NODE_OPTIONS, '--disable-warning=ExperimentalWarning'].filter(Boolean).join(' '),
},
prepare: (cwd) => { runCwd = cwd },
inspect: async (cwd) => {
const logs = await persistedLogs(cwd)
expect(logs).toHaveLength(2)
const parent = logs.find(log => typeof log.header.parentSession !== 'string')
const child = logs.find(log => typeof log.header.parentSession === 'string')
if (parent === undefined || child === undefined) throw new Error('missing persisted parent or child log')
const parentRecords = parseJsonl(parent.content)
const calls = parentRecords.filter(record => record.type === 'tool/call')
expect(calls.map(record => (record.data as JsonObject | undefined)?.name)).toEqual(['subagent'])
const callArguments = (calls[0]?.data as JsonObject | undefined)?.arguments
if (typeof callArguments !== 'string') throw new Error('subagent call did not persist its arguments')
expect(JSON.parse(callArguments)).toMatchObject({ run_in_background: true })
const notices = parentRecords.flatMap((record) => {
if (record.type !== 'agent/inbox/spliced') return []
const inserted = (record.data as JsonObject | undefined)?.inserted
if (!Array.isArray(inserted)) return []
return (inserted as JsonObject[]).filter((message) => {
const source = message.source as JsonObject | undefined
return source?.kind === 'subagent-settled'
})
})
expect(notices).toHaveLength(1)
expect(JSON.stringify(notices[0])).toContain('CHILD_RESULT')
const context = contextFromLogs([parent.content, child.content])
const normalizedChild = scrubRequestHeaders(normalizeSessionLog(child.content, context))
if (refreshing) await writeFile(childExpected, normalizedChild)
expect(normalizedChild).toBe(await readFile(childExpected, 'utf8'))
expect(normalizedChild).toContain('CHILD_RESULT')
expect(normalizedChild).not.toContain('"name":"report"')
},
})
expect(result.stderr).toBe('')
const records = parseJsonl(result.stdout)
expect(records.at(-1)).toMatchObject({
type: 'result',
output: 'PARENT_RECEIVED_CHILD_RESULT',
})
const normalized = normalizeHeadlessStream(result.stdout, runCwd)
if (refreshing) await writeFile(streamExpected, normalized)
expect(normalized).toBe(await readFile(streamExpected, 'utf8'))
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
it('replays persistent PTY tools through the one-shot app', async () => {
const input = JSON.parse(await readFile(join(ptyScenarioDir, 'input.json'), 'utf8')) as {
steps?: { op?: unknown; text?: unknown }[]

45
examples/headless-agent/tests/keyless-smoke.e2e.ts
View File

@@ -1,17 +1,10 @@
import { cp, mkdir, mkdtemp, readFile, readdir, rm, writeFile } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { readFile, readdir } from 'node:fs/promises'
import { zstdDecompress } from 'node:zlib'
import { promisify } from 'node:util'
import { join } from 'node:path'
import { fileURLToPath } from 'node:url'
import { describe, expect, it } from 'vitest'
import { LOADER_SMOKE_TEST_TIMEOUT_MS, runLoaderSmoke } from '@deepseek-ai/dsh-loader-smoke'
import {
PREPARED_ENTRY_FILENAME,
REPOSITORY_PLUGIN_PREPARE_COMMAND,
REPOSITORY_PLUGIN_PACKAGE_NAME,
prepareDshPlugin,
} from '@deepseek-ai/dsh-repository-plugin'
import type { SessionEvent } from '@deepseek-ai/dsh-session'
const binScript = fileURLToPath(new URL('./fixtures/headless-driver.ts', import.meta.url))
@@ -44,16 +37,6 @@ describe('headless-agent keyless smoke', () => {
const result = lines.at(-1)
expect(stderr).toBe('')
expect(events.some(event => event.type === 'tool/call' && event.data.name === 'bash')).toBe(true)
const catalogMessage = events.find(event => event.type === 'user/message'
&& event.data.source.kind === 'skill-catalog')
const catalog = catalogMessage?.type === 'user/message'
? catalogMessage.data.content.filter(block => block.type === 'text').map(block => block.text).join('\n')
: ''
expect(catalog.split('\n').find(line => line.includes('repository-fixture'))).toMatchInlineSnapshot(
`
"- \`repository-fixture\`: Repository fixture skill."
`,
)
const toolResult = events.find(event => event.type === 'tool/result')
expect(JSON.stringify(toolResult)).toContain('CLI_TOOL_ROUND_TRIP')
expect(result).toMatchObject({
@@ -63,30 +46,4 @@ describe('headless-agent keyless smoke', () => {
expect(String(result?.['output'])).toContain('CLI_TOOL_ROUND_TRIP')
expect(persistedHeader).toMatchObject({ type: 'session' })
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
it('keeps the checked-in prepared wrapper identical to the generator output for its manifest', async () => {
// The fixture claims "Generated by dsh-plugin-prepare"; this pin makes the
// claim true — a wrapper-template change fails here until the fixture is
// regenerated, so the assembled smoke can never exercise stale generated fields.
const fixture = fileURLToPath(new URL('./fixtures/repository-plugin/', import.meta.url))
const root = await mkdtemp(join(tmpdir(), 'dsh-fixture-drift-'))
try {
const plugin = join(root, '.dsh-plugin')
await mkdir(plugin, { recursive: true })
await cp(join(fixture, 'dsh-plugin-assets/skills/0'), join(root, 'skills'), { recursive: true })
await writeFile(join(plugin, 'package.json'), `${JSON.stringify({
name: 'headless-repository-fixture',
version: '0.0.0',
scripts: { prepack: REPOSITORY_PLUGIN_PREPARE_COMMAND },
devDependencies: { [REPOSITORY_PLUGIN_PACKAGE_NAME]: '0.0.1' },
dsh: { skills: ['../skills'] },
}, undefined, 2)}\n`)
await prepareDshPlugin(plugin)
const generated = await readFile(join(plugin, PREPARED_ENTRY_FILENAME), 'utf8')
const checkedIn = await readFile(join(fixture, PREPARED_ENTRY_FILENAME), 'utf8')
expect(checkedIn).toBe(generated)
} finally {
await rm(root, { recursive: true, force: true })
}
})
})

2
examples/headless-agent/tests/resume.e2e.ts
View File

@@ -3,7 +3,7 @@ import { mkdtemp, rm } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { afterEach, describe, expect, it } from 'vitest'
import type { Context } from 'cordis'
import type { Context } from '@deepseek-ai/cordis'
import { SessionId } from '@deepseek-ai/dsh-session'
import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts'

2
examples/headless-agent/tests/semantic-checkpoint.snapshot.ts
View File

@@ -1,7 +1,7 @@
import { readFile, writeFile } from 'node:fs/promises'
import { dirname, join } from 'node:path'
import { fileURLToPath } from 'node:url'
import { Context } from 'cordis'
import { Context } from '@deepseek-ai/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, CallId , createMessage } from '@deepseek-ai/dsh-llm'

107
examples/headless-agent/tests/session-format-guard.snapshot.ts Normal file
View File

@@ -0,0 +1,107 @@
/**
* Assembled-app regression for the session-format refusal surface: resuming a
* log written by a "newer" harness (format version ahead, or an unknown
* required event type) fails loud through the real Loader composition, and the
* error the product user sees names the direction and the raw log path.
* @module session-format-guard-snapshot
*/
import { join, dirname } from 'node:path'
import { fileURLToPath } from 'node:url'
import { Context } from '@deepseek-ai/cordis'
import { LOADER_SMOKE_TEST_TIMEOUT_MS, runLoaderSmoke } from '@deepseek-ai/dsh-loader-smoke'
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 = join(dirname(fileURLToPath(import.meta.url)), 'workspace-context-resume-snapshots/offline-edit')
const replayFixture = join(fixtureDir, 'replay.jsonl')
const configPath = fileURLToPath(new URL('../workspace-context-resume.cordis.snapshot.yml', import.meta.url))
const binScript = fileURLToPath(new URL('./fixtures/headless-driver.ts', import.meta.url))
const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
// The resumed-agent fixture in the shared config resumes exactly this id.
const sessionId = SessionId('workspace-context-resume')
/** Persist one session with the given header version and events, returning its log path. */
async function seedSession(root: string, cwd: string, version: number, events: SessionEvent[]): Promise<string> {
const ctx = new Context()
await ctx.plugin(SessionStore)
await ctx.plugin(SessionPersistenceJsonl, { root, compression: 'none' })
const meta: SessionHeader = { version, id: sessionId, createdAt: 1, cwd }
try {
await ctx.sessionPersistence.create(meta)
await ctx.sessionPersistence.append(sessionId, events)
const location = ctx.sessionPersistence.locate(meta)
if (location === undefined) throw new Error('JSONL backend did not locate the seeded session')
return location.path
} finally {
await ctx.fiber.dispose()
}
}
function closedTurn(): SessionEvent[] {
return [
{ type: 'turn/start', seq: 0, time: 1, data: { turn: 1 } },
{ type: 'turn/end', seq: 1, time: 2, data: { turn: 1, reason: { kind: 'completed' } } },
]
}
describe('session format guard through the assembled app', () => {
it('refuses to resume a newer-format log, naming the upgrade direction and the raw log path', async () => {
let sessionPath = ''
const result = await runLoaderSmoke({
label: 'newer-format resume refusal',
tempDirPrefix: 'dsh-format-guard-version-',
binScript,
libBinScript: binScript,
configPath,
binArgs: [configPath, 'Try to resume.'],
tsconfigPath,
env: { DSH_SNAPSHOT_FILE: replayFixture },
expectedExitCode: 1,
prepare: async (runCwd) => {
sessionPath = await seedSession(join(runCwd, '.sessions'), runCwd, SESSION_FORMAT_VERSION + 99, closedTurn())
},
})
expect(result.stderr).toContain(
`session "${sessionId}" uses log format v${SESSION_FORMAT_VERSION + 99}, but this harness reads only v${SESSION_FORMAT_VERSION}: the log was written by a newer harness — upgrade the harness to open it`,
)
// macOS reports the temp dir via the /private symlink parent; assert the
// stable path suffix instead of the realpath-dependent prefix.
expect(result.stderr).toContain('(raw log: ')
expect(result.stderr).toContain(sessionPath.slice(sessionPath.indexOf('/.sessions/')))
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
it('refuses to resume a log with an unknown required event type', async () => {
let sessionPath = ''
const result = await runLoaderSmoke({
label: 'unknown-event resume refusal',
tempDirPrefix: 'dsh-format-guard-event-',
binScript,
libBinScript: binScript,
configPath,
binArgs: [configPath, 'Try to resume.'],
tsconfigPath,
env: { DSH_SNAPSHOT_FILE: replayFixture },
expectedExitCode: 1,
prepare: async (runCwd) => {
sessionPath = await seedSession(join(runCwd, '.sessions'), runCwd, SESSION_FORMAT_VERSION, [
...closedTurn(),
{ type: 'future/event', seq: 2, time: 3, data: { payload: 1 } } as unknown as SessionEvent,
])
},
})
expect(result.stderr).toContain(
`session "${sessionId}" contains event type "future/event" (seq 2) unknown to this harness and not marked ignorable; refusing to interpret the log — it was likely written by a newer harness`,
)
// macOS reports the temp dir via the /private symlink parent; assert the
// stable path suffix instead of the realpath-dependent prefix.
expect(result.stderr).toContain('(raw log: ')
expect(result.stderr).toContain(sessionPath.slice(sessionPath.indexOf('/.sessions/')))
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
})

27
examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl
View File

File diff suppressed because one or more lines are too long

27
examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl
View File

File diff suppressed because one or more lines are too long

28
examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl
View File

File diff suppressed because one or more lines are too long

14
examples/headless-agent/tests/snapshots/compaction-recovery/session.jsonl
View File

File diff suppressed because one or more lines are too long

8
examples/headless-agent/tests/snapshots/dsh-run/session.expected.jsonl → examples/headless-agent/tests/snapshots/headless-profile/session.expected.jsonl
View File

@@ -2,16 +2,16 @@
{"type":"permission/preset","seq":0,"time":0,"data":{"preset":"danger-full-access"}}
{"type":"sandbox/mode","seq":1,"time":0,"data":{"mode":"danger-full-access"}}
{"type":"approval/policy","seq":2,"time":0,"data":{"policy":"never"}}
{"type":"agent/inbox/spliced","seq":3,"time":0,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Prove the product dsh run path with one real tool round trip."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"}]}}
{"type":"agent/inbox/spliced","seq":3,"time":0,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Prove the product headless profile path with one real tool round trip."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"}]}}
{"type":"turn/start","seq":4,"time":0,"data":{"turn":1}}
{"type":"agent/inbox/spliced","seq":5,"time":0,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
{"type":"step/start","seq":6,"time":0,"data":{"turn":1,"step":1}}
{"type":"user/message","seq":7,"time":0,"data":{"content":[{"type":"text","text":"Prove the product dsh run path with one real tool round trip."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
{"type":"user/message","seq":7,"time":0,"data":{"content":[{"type":"text","text":"Prove the product headless profile path with one real tool round trip."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
{"type":"user/message","seq":8,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
{"type":"session/title","seq":9,"time":0,"data":{"title":"Prove the product dsh run","messageSeqs":[7],"source":{"kind":"fallback"}}}
{"type":"session/title","seq":9,"time":0,"data":{"title":"Prove the product headless profile","messageSeqs":[7],"source":{"kind":"fallback"}}}
{"type":"request/header","seq":10,"time":0,"data":{"header":{"config":{"provider":"cli-mock","model":"cli-mock","reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
{"type":"request/context","seq":11,"time":0,"data":{"provider":"cli-mock","model":"cli-mock"}}
{"type":"session/title-llm-request","seq":12,"time":0,"data":{"titleProvider":"session-title-first-message-llm","messageSeqs":[7],"route":{"provider":"cli-mock","model":"cli-mock"},"system":"Create a concise title for an AI coding-assistant session from the supplied human messages.\nReturn only the title on one line, **in plain text of natural language**, with no quotes, prefix, explanation, Markdown, XML, or terminal control codes. No code is allowed.\nUse the language of the messages.\nAim for about 5 words in non-CJK languages or 10 CJK characters.","messages":[{"content":[{"type":"text","text":"Generate the session title from this JSON array of human messages:\n[{\"seq\":7,\"text\":\"Prove the product dsh run path with one real tool round trip.\"}]"}],"source":{"kind":"plugin","plugin":"dsh-session-title-llm"},"role":"user","id":"{{sessionId}}"}],"maxTokens":64}}
{"type":"session/title-llm-request","seq":12,"time":0,"data":{"titleProvider":"session-title-first-message-llm","messageSeqs":[7],"route":{"provider":"cli-mock","model":"cli-mock"},"system":"Create a concise title for an AI coding-assistant session from the supplied human messages.\nReturn only the title on one line, **in plain text of natural language**, with no quotes, prefix, explanation, Markdown, XML, or terminal control codes. No code is allowed.\nUse the language of the messages.\nAim for about 5 words in non-CJK languages or 10 CJK characters.","messages":[{"content":[{"type":"text","text":"Generate the session title from this JSON array of human messages:\n[{\"seq\":7,\"text\":\"Prove the product headless profile path with one real tool round trip.\"}]"}],"source":{"kind":"plugin","plugin":"dsh-session-title-llm"},"role":"user","id":"{{sessionId}}"}],"maxTokens":64}}
{"type":"assistant/chunk","seq":13,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":14,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"cli-smoke-call","name":"bash","argumentsDelta":"{\"command\":\"printf CLI_TOOL_ROUND_TRIP\",\"description\":\"Prove the CLI tool round trip.\"}"}}}
{"type":"assistant/chunk","seq":15,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"cli-smoke-call","name":"bash","arguments":"{\"command\":\"printf CLI_TOOL_ROUND_TRIP\",\"description\":\"Prove the CLI tool round trip.\"}"}}}}

0
examples/headless-agent/tests/snapshots/dsh-run/stderr.expected.txt → examples/headless-agent/tests/snapshots/headless-profile/stderr.expected.txt
View File

34
examples/headless-agent/tests/snapshots/pty-tools/session.jsonl
View File

File diff suppressed because one or more lines are too long

20
examples/headless-agent/tests/snapshots/subagent-settlement/child.expected.jsonl Normal file
View File

@@ -0,0 +1,20 @@
{"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}","parentSession":"{{sessionId}}","origin":"subagent","delegationDepth":1}
{"type":"subagent/descriptor","seq":0,"time":0,"data":{"version":2,"mode":"continuable","provider":"spawn","label":"Return child result","agentProvider":"deepseek-official","agentModel":"deepseek-v4-flash"}}
{"type":"session/end-seed","seq":1,"time":0,"data":{}}
{"type":"agent/inbox/spliced","seq":2,"time":0,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Reply with exactly CHILD_RESULT and nothing else. Do not call report."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"}]}}
{"type":"turn/start","seq":3,"time":0,"data":{"turn":1}}
{"type":"agent/inbox/spliced","seq":4,"time":0,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
{"type":"step/start","seq":5,"time":0,"data":{"turn":1,"step":1}}
{"type":"user/message","seq":6,"time":0,"data":{"content":[{"type":"text","text":"Reply with exactly CHILD_RESULT and nothing else. Do not call report."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
{"type":"user/message","seq":7,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
{"type":"session/title","seq":8,"time":0,"data":{"title":"Reply with exactly CHILD_RESULT and","messageSeqs":[6],"source":{"kind":"fallback"}}}
{"type":"request/header","seq":9,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
{"type":"request/context","seq":10,"time":0,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
{"type":"assistant/chunk","seq":11,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":12,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"CHILD_RESULT"}}}
{"type":"assistant/chunk","seq":13,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"CHILD_RESULT"}}}}
{"type":"assistant/chunk","seq":14,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
{"type":"assistant/chunk","seq":15,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":16,"time":0,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"CHILD_RESULT"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{sessionId}}"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[11,12,13,14,15],"surfaceOp":"append"}
{"type":"step/end","seq":17,"time":0,"data":{"turn":1,"step":1}}
{"type":"turn/end","seq":18,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}

6
examples/headless-agent/tests/snapshots/subagent-settlement/child.replay.jsonl Normal file
View File

@@ -0,0 +1,6 @@
{"type":"session","version":0,"id":"subagent-settlement-child","createdAt":2,"delegationDepth":1}
{"type":"assistant/chunk","seq":0,"time":1,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":1,"time":2,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"CHILD_RESULT"}}}
{"type":"assistant/chunk","seq":2,"time":3,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"CHILD_RESULT"}}}}
{"type":"assistant/chunk","seq":3,"time":4,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
{"type":"assistant/chunk","seq":4,"time":5,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}

32
examples/headless-agent/tests/snapshots/subagent-settlement/parent.override.json Normal file
View File

@@ -0,0 +1,32 @@
[
{
"kind": "chunks",
"chunks": [
{ "type": "block-start", "index": 0, "blockType": "tool-call" },
{ "type": "tool-call-delta", "index": 0, "id": "start-child", "name": "subagent", "argumentsDelta": "{\"description\":\"Return child result\",\"prompt\":\"Reply with exactly CHILD_RESULT and nothing else. Do not call report.\",\"run_in_background\":true}" },
{ "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "start-child", "name": "subagent", "arguments": "{\"description\":\"Return child result\",\"prompt\":\"Reply with exactly CHILD_RESULT and nothing else. Do not call report.\",\"run_in_background\":true}" } },
{ "type": "usage", "usage": { "inputTokens": 10, "outputTokens": 5 } },
{ "type": "finish", "reason": { "kind": "tool-calls" } }
]
},
{
"kind": "chunks",
"chunks": [
{ "type": "block-start", "index": 0, "blockType": "text" },
{ "type": "text-delta", "index": 0, "text": "STARTED" },
{ "type": "block-end", "index": 0, "block": { "type": "text", "text": "STARTED" } },
{ "type": "usage", "usage": { "inputTokens": 10, "outputTokens": 5 } },
{ "type": "finish", "reason": { "kind": "stop" } }
]
},
{
"kind": "chunks",
"chunks": [
{ "type": "block-start", "index": 0, "blockType": "text" },
{ "type": "text-delta", "index": 0, "text": "PARENT_RECEIVED_CHILD_RESULT" },
{ "type": "block-end", "index": 0, "block": { "type": "text", "text": "PARENT_RECEIVED_CHILD_RESULT" } },
{ "type": "usage", "usage": { "inputTokens": 10, "outputTokens": 5 } },
{ "type": "finish", "reason": { "kind": "stop" } }
]
}
]

1
examples/headless-agent/tests/snapshots/subagent-settlement/parent.replay.jsonl Normal file
View File

@@ -0,0 +1 @@
{"type":"session","version":0,"id":"subagent-settlement-parent","createdAt":1,"delegationDepth":0}

38
examples/headless-agent/tests/snapshots/subagent-settlement/stream-json.expected.jsonl Normal file
View File

@@ -0,0 +1,38 @@
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"agent/inbox/spliced","seq":0,"time":0,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Start one continuable background subagent and answer from its completion notice. Do not call list_agents, send_message, task_output, or task_list."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"}]}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/start","seq":1,"time":0,"data":{"turn":1}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"agent/inbox/spliced","seq":2,"time":0,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":4,"time":0,"data":{"content":[{"type":"text","text":"Start one continuable background subagent and answer from its completion notice. Do not call list_agents, send_message, task_output, or task_list."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"session/title","seq":5,"time":0,"data":{"title":"Start one continuable background subagen","messageSeqs":[4],"source":{"kind":"fallback"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":6,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/context","seq":7,"time":0,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":9,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"start-child","name":"subagent","argumentsDelta":"{\"description\":\"Return child result\",\"prompt\":\"Reply with exactly CHILD_RESULT and nothing else. Do not call report.\",\"run_in_background\":true}"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":10,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"start-child","name":"subagent","arguments":"{\"description\":\"Return child result\",\"prompt\":\"Reply with exactly CHILD_RESULT and nothing else. Do not call report.\",\"run_in_background\":true}"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":11,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":12,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":13,"time":0,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"start-child","name":"subagent","arguments":"{\"description\":\"Return child result\",\"prompt\":\"Reply with exactly CHILD_RESULT and nothing else. Do not call report.\",\"run_in_background\":true}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{sessionId}}"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[8,9,10,11,12],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":14,"time":0,"data":{"turn":1,"step":1,"callId":"start-child","name":"subagent","arguments":"{\"description\":\"Return child result\",\"prompt\":\"Reply with exactly CHILD_RESULT and nothing else. Do not call report.\",\"run_in_background\":true}"}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":15,"time":0,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"start-child"},"content":[{"type":"tool-result","toolCallId":"start-child","content":[{"type":"text","text":"started subagent {{sessionId}}"}],"isError":false}],"role":"user","id":"{{sessionId}}"}},"sourceEventSeqs":[14],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":16,"time":0,"data":{"turn":1,"step":1}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"agent/inbox/spliced","seq":17,"time":0,"data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"Background subagent {{sessionId}} finished and will do no further work unless you send it more."},{"type":"text","text":"Its closing message:"},{"type":"text","text":"CHILD_RESULT"}],"source":{"kind":"subagent-settled","form":"notice","summary":"Background subagent {{sessionId}} finished and will do no further work unless you send it more.","senderSessionId":"{{sessionId}}"},"role":"user","id":"{{sessionId}}"}]}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":18,"time":0,"data":{"turn":1,"step":2}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":19,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":20,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":0,"text":"STARTED"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":21,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"STARTED"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":22,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":23,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":24,"time":0,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"text","text":"STARTED"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{sessionId}}"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[19,20,21,22,23],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":25,"time":0,"data":{"turn":1,"step":2}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"agent/inbox/spliced","seq":26,"time":0,"data":{"target":"next-step","start":0,"removedCount":1,"inserted":[]}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":27,"time":0,"data":{"turn":1,"step":3}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":28,"time":0,"data":{"content":[{"type":"text","text":"Background subagent {{sessionId}} finished and will do no further work unless you send it more."},{"type":"text","text":"Its closing message:"},{"type":"text","text":"CHILD_RESULT"}],"source":{"kind":"subagent-settled","form":"notice","summary":"Background subagent {{sessionId}} finished and will do no further work unless you send it more.","senderSessionId":"{{sessionId}}"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":29,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":30,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"text-delta","index":0,"text":"PARENT_RECEIVED_CHILD_RESULT"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":31,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"PARENT_RECEIVED_CHILD_RESULT"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":32,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":33,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":34,"time":0,"data":{"turn":1,"step":3,"message":{"role":"assistant","content":[{"type":"text","text":"PARENT_RECEIVED_CHILD_RESULT"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{sessionId}}"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[29,30,31,32,33],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":35,"time":0,"data":{"turn":1,"step":3}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/end","seq":36,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}}
{"type":"result","sessionId":"{{sessionId}}","output":"PARENT_RECEIVED_CHILD_RESULT","usage":{"inputTokens":30,"outputTokens":15}}

2
examples/headless-agent/tests/subagent-diagnostic.snapshot.ts
View File

@@ -7,7 +7,7 @@
import { readFile, readdir, writeFile } from 'node:fs/promises'
import { join } from 'node:path'
import { fileURLToPath } from 'node:url'
import { Context } from 'cordis'
import { Context } from '@deepseek-ai/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'

2
examples/headless-agent/tests/subagent-inheritance-snapshots/parent-override/child.expected.jsonl
View File

@@ -6,7 +6,7 @@
{"type":"subagent/descriptor","seq":4,"time":0,"data":{"version":2,"mode":"one-shot","provider":"spawn","label":"Delegated write probe"}}
{"type":"step/start","seq":5,"time":0,"data":{"turn":1,"step":1}}
{"type":"user/message","seq":6,"time":0,"data":{"content":[{"type":"text","text":"Use the write tool exactly once with file_path set to exactly the relative path inherited.txt and content escaped. If the write is denied, reply with the single word CHILD_DENIED and the denial marker line; do not retry and do not request escalation. If it succeeds, reply CHILD_WROTE."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
{"type":"user/message","seq":7,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: read-only. Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode. Do not refuse a required modification from this policy alone: try an available tool normally and follow any denial and escalation guidance it returns."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: read-only. Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode. Do not refuse a required modification from this policy alone: try an available tool normally and follow any denial and escalation guidance it returns."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
{"type":"user/message","seq":7,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: read-only. Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode. Do not refuse a required modification from this policy alone: try an available tool normally and follow any denial and escalation guidance it returns.\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: read-only. Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode. Do not refuse a required modification from this policy alone: try an available tool normally and follow any denial and escalation guidance it returns."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
{"type":"session/title","seq":8,"time":0,"data":{"title":"Use the write tool exactly","messageSeqs":[6],"source":{"kind":"fallback"}}}
{"type":"request/header","seq":9,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
{"type":"request/context","seq":10,"time":0,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}

2
examples/headless-agent/tests/subagent-inheritance.snapshot.ts
View File

@@ -6,7 +6,7 @@
import { readFile, readdir, writeFile } from 'node:fs/promises'
import { join } from 'node:path'
import { fileURLToPath } from 'node:url'
import { Context } from 'cordis'
import { Context } from '@deepseek-ai/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'

2
examples/headless-agent/tests/todo-write.e2e.ts
View File

@@ -3,7 +3,7 @@ import { mkdtemp, rm } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { afterEach, describe, expect, it } from 'vitest'
import type { Context } from 'cordis'
import type { Context } from '@deepseek-ai/cordis'
import { codingHarness, TODO_SYSTEM_PROMPT, waitForIdle } from './harness.ts'
import { SessionId } from '@deepseek-ai/dsh-session'

2
examples/headless-agent/tests/workspace-context-resume.snapshot.ts
View File

@@ -7,7 +7,7 @@ import { createHash } from 'node:crypto'
import { mkdir, readFile, readdir, writeFile } from 'node:fs/promises'
import { dirname, join } from 'node:path'
import { fileURLToPath } from 'node:url'
import { Context } from 'cordis'
import { Context } from '@deepseek-ai/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'