Remove the stdio agent

examples/headless-agent/tests/code-mode.e2e.ts

@@ -0,0 +1,169 @@
+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 } from 'vitest'
+import { Context } from 'cordis'
+import LlmService from '@deepseek-ai/dsh-llm'
+import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
+import type { SessionEvent } from '@deepseek-ai/dsh-session'
+import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
+import ToolRegistry, { RUN_CODE_NAME } from '@deepseek-ai/dsh-tools'
+import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
+
+import AgentLoop from '@deepseek-ai/dsh-agent-loop'
+import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
+import * as ToolBash from '@deepseek-ai/dsh-tool-bash'
+import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
+import { WorkerCodeRuntime } from '@deepseek-ai/dsh-code-runtime-worker'
+import LocalFileSystem from '@deepseek-ai/dsh-fs-local'
+import * as ToolFs from '@deepseek-ai/dsh-tool-fs'
+import * as WorkspaceContext from '@deepseek-ai/dsh-workspace-context'
+
+/**
+ * With-key Code Mode proof: a real model receives only `run_code`, composes two
+ * sub-calls, writes a file, and returns curated output while the log records
+ * each `tool/code-dispatch`. The keyless Loader smoke is in the sibling test.
+ */
+
+const PERSONA = 'You are a coding agent. You work by writing TypeScript programs for run_code: '
+  + 'batch related tool work into one program and print or return ONLY the findings that matter.'
+const WORKSPACE_PROBE = 'dragonfruit-8675309'
+
+let ctx: Context | undefined
+let workdir: string | undefined
+
+afterEach(async () => {
+  // Always dispose, even on failure/retry/timeout: agent-loop teardown stops
+  // the loop, the executor kills stray processes, and the code runtime's
+  // dispose awaits worker exits.
+  await ctx?.fiber.dispose()
+  ctx = undefined
+  if (workdir !== undefined) await rm(workdir, { recursive: true, force: true })
+  workdir = undefined
+})
+
+async function codeModeHarness(cwd: string): Promise<Context> {
+  const harness = new Context()
+  await harness.plugin(LlmService)
+  await harness.plugin(SessionStore)
+  await harness.plugin(SystemPrompt, { persona: PERSONA })
+  await harness.plugin(ToolRegistry, { mode: 'code' })
+  await harness.plugin(AgentRegistry)
+  await harness.plugin(AgentLoop, { agents: [] })
+  await harness.plugin(LlmDeepSeek)
+  await harness.plugin(LocalBashExecutor, { cwd, timeoutMs: 30_000 })
+  await harness.plugin(ToolBash)
+  await harness.plugin(WorkerCodeRuntime, {})
+  return harness
+}
+
+async function workspaceCodeModeHarness(): Promise<Context> {
+  const harness = new Context()
+  await harness.plugin(LlmService)
+  await harness.plugin(SessionStore)
+  await harness.plugin(SystemPrompt, { persona: PERSONA })
+  await harness.plugin(ToolRegistry, { mode: 'code' })
+  await harness.plugin(AgentRegistry)
+  await harness.plugin(LocalFileSystem, { cwd: '/' })
+  await harness.plugin(ToolFs)
+  await harness.plugin(WorkspaceContext, { maxBytes: 65536 })
+  await harness.plugin(AgentLoop, { agents: [] })
+  await harness.plugin(LlmDeepSeek, { models: [{ id: 'deepseek-v4-flash' }] })
+  await harness.plugin(WorkerCodeRuntime, {})
+  return harness
+}
+
+function waitForIdle(harness: Context, agent: Agent): Promise<void> {
+  return new Promise((resolve) => {
+    const dispose = harness.on('agent/status', (subject, status) => {
+      if (subject === agent && status === 'idle') {
+        dispose()
+        resolve()
+      }
+    })
+  })
+}
+
+describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a program over real tools', () => {
+  it('collapses the wire tool list to [run_code], bridges sub-calls, and returns curated output', async () => {
+    workdir = await mkdtemp(join(tmpdir(), 'dsh-code-mode-e2e-'))
+    ctx = await codeModeHarness(workdir)
+    const agent = ctx.agentLoop.create(SessionId('e2e-code-mode'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
+
+    agent.send([{
+      type: 'text',
+      text: 'Using one run_code program: run `echo alpha-7` with the bash tool, run `echo beta-9` with the bash tool, '
+        + 'then write both outputs joined by a plus sign into combined.txt (bash heredoc or redirect), '
+        + 'and return only the joined string.',
+    }])
+    await waitForIdle(ctx, agent)
+    const events: SessionEvent[] = [...agent.session.events]
+
+    // The wire contract: every request this session made offered EXACTLY ONE
+    // tool — run_code (the logged header snapshots the assembled list).
+    const headers = events.filter(event => event.type === 'request/header')
+    expect(headers.length).toBeGreaterThan(0)
+    for (const header of headers) {
+      expect(header.data.header.tools?.map(tool => tool.name)).toEqual([RUN_CODE_NAME])
+    }
+    // The model actually went through run_code…
+    const calls = events.filter(event => event.type === 'tool/call')
+    expect(calls.length).toBeGreaterThan(0)
+    expect(calls.every(event => event.data.name === RUN_CODE_NAME)).toBe(true)
+    // …and the program's tool calls landed as dispatch events under it.
+    const dispatches = events.filter(event => event.type === 'tool/code-dispatch')
+    expect(dispatches.length).toBeGreaterThanOrEqual(2)
+    expect(dispatches.every(event => event.data.name === 'bash')).toBe(true)
+    const parents = new Set(calls.map(event => event.data.callId))
+    expect(dispatches.every(event => parents.has(event.data.parentCallId))).toBe(true)
+
+    // World verification: the file the program wrote, and the curated answer.
+    const combined = await readFile(join(workdir, 'combined.txt'), 'utf8')
+    expect(combined).toContain('alpha-7')
+    expect(combined).toContain('beta-9')
+    const finalMessage = events.findLast(event => event.type === 'assistant/message')
+    const finalText = finalMessage !== undefined
+      ? finalMessage.data.content.filter(block => block.type === 'text').map(block => block.text).join('')
+      : ''
+    expect(finalText).toContain('alpha-7')
+    expect(finalText).toContain('beta-9')
+  }, 180_000)
+
+  it('delivers nested workspace instructions discovered by an fs sub-call after the outer result', async () => {
+    workdir = await mkdtemp(join(tmpdir(), 'dsh-code-mode-workspace-e2e-'))
+    await mkdir(join(workdir, '.git'), { recursive: true })
+    await mkdir(join(workdir, 'pkg/deep'), { recursive: true })
+    await writeFile(join(workdir, 'pkg/AGENTS.md'), `If asked for the Code Mode workspace handshake, reply with exactly ${WORKSPACE_PROBE} and nothing else.\n`)
+    await writeFile(join(workdir, 'pkg/deep/task.txt'), 'Touch this file to discover the nested instructions.\n')
+    ctx = await workspaceCodeModeHarness()
+    const handle = await ctx.agents.create({
+      sessionId: SessionId('e2e-code-mode-workspace-session'),
+      meta: { cwd: workdir },
+      agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' },
+    })
+
+    handle.agent.send([{
+      type: 'text',
+      text: 'Use one run_code program to call tools.read on pkg/deep/task.txt. After it finishes, answer: Code Mode workspace handshake?',
+    }])
+    await waitForIdle(ctx, handle.agent)
+
+    const events: SessionEvent[] = [...handle.agent.session.events]
+    const dispatch = events.find(event => event.type === 'tool/code-dispatch' && event.data.name === 'read')
+    const outerResult = events.find(event => event.type === 'tool/result')
+    const workspaceContext = events.find(event => event.type === 'context/message'
+      && typeof event.data.meta === 'object'
+      && event.data.meta !== null
+      && !Array.isArray(event.data.meta)
+      && event.data.meta.kind === 'workspace-instructions')
+    expect(dispatch).toBeDefined()
+    expect(outerResult).toBeDefined()
+    expect(workspaceContext).toBeDefined()
+    expect(workspaceContext!.seq).toBeGreaterThan(outerResult!.seq)
+    const finalMessage = events.findLast(event => event.type === 'assistant/message')
+    const answer = finalMessage?.type === 'assistant/message'
+      ? finalMessage.data.content.filter(block => block.type === 'text').map(block => block.text).join('')
+      : ''
+    expect(answer).toContain(WORKSPACE_PROBE)
+  }, 180_000)
+})

examples/headless-agent/tests/coding-task.e2e.ts

@@ -0,0 +1,84 @@
+import { spawnSync } from 'node:child_process'
+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 { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts'
+import { SessionId } from '@deepseek-ai/dsh-session'
+
+/**
+ * The swebench-style smoke test: a real model fixes a real bug in a temp
+ * directory using only the bash tool, and the fix is verified OUTSIDE the
+ * agent by re-running the test script. Key-gated.
+ */
+
+const TEST_FILE = [
+  "const assert = require('node:assert');",
+  "const { add } = require('./add.js');",
+  'assert.strictEqual(add(2, 3), 5);',
+  'assert.strictEqual(add(-1, 1), 0);',
+  "console.log('PASS');",
+  '',
+].join('\n')
+
+const BUGGY_ADD = [
+  '// A tiny module with an obvious bug.',
+  'function add(a, b) {',
+  '  return a - b;',
+  '}',
+  'module.exports = { add };',
+  '',
+].join('\n')
+
+let workdir: string | undefined
+let ctx: Context | undefined
+
+afterEach(async () => {
+  // Dispose the harness even on failure/retry: agent-loop teardown stops the
+  // loop and LocalBashExecutor teardown kills anything the model left running.
+  await ctx?.fiber.dispose()
+  ctx = undefined
+  if (workdir !== undefined) await rm(workdir, { recursive: true, force: true })
+  workdir = undefined
+})
+
+describe.skipIf(!process.env.DEEPSEEK_API_KEY)('coding task: fix a failing test via bash', () => {
+  it('repairs add.js so node add.test.js passes', async () => {
+    workdir = await mkdtemp(join(tmpdir(), 'dsh-coding-task-'))
+    await writeFile(join(workdir, 'add.js'), BUGGY_ADD)
+    await writeFile(join(workdir, 'add.test.js'), TEST_FILE)
+
+    // Confirm the fixture actually fails before the agent touches it.
+    const before = spawnSync('node', ['add.test.js'], { cwd: workdir })
+    expect(before.status).not.toBe(0)
+
+    ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT })
+    const agent = ctx.agentLoop.create(SessionId('e2e-task'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
+
+    agent.send([{
+      type: 'text',
+      text: 'In the current directory, `node add.test.js` fails because add.js has a bug. '
+        + 'Fix add.js so the test passes, run `node add.test.js` to verify, and report the result. '
+        + 'Do not modify add.test.js.',
+    }])
+    await waitForIdle(ctx, agent)
+
+    // The agent claims success…
+    const summary = finalText([...agent.session.events]).toLowerCase()
+    expect(summary.length).toBeGreaterThan(0)
+
+    // …and the world agrees: the test passes when WE run it, and the test
+    // file is byte-identical (an agent that neutered the test instead of
+    // fixing the bug fails here, not just on a keyword probe).
+    const untouchedTest = await readFile(join(workdir, 'add.test.js'), 'utf8')
+    expect(untouchedTest).toBe(TEST_FILE)
+
+    const after = spawnSync('node', ['add.test.js'], { cwd: workdir, encoding: 'utf8' })
+    expect(after.stdout).toContain('PASS')
+    expect(after.status).toBe(0)
+
+    const fixed = await readFile(join(workdir, 'add.js'), 'utf8')
+    expect(fixed).not.toMatch(/a\s*-\s*b/)
+  }, 180_000)
+})

examples/headless-agent/tests/compaction.e2e.ts

@@ -0,0 +1,88 @@
+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 { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts'
+import { SessionId } from '@deepseek-ai/dsh-session'
+
+/**
+ * Key-gated smoke for mid-session compaction. It verifies the compact event
+ * pair, replacement of older surface nodes, and a final answer after compaction.
+ */
+// FIXME(compaction-snapshot): this is the only full compaction coverage because
+// replay cannot serve the summarizer's unlogged model call.
+
+let workdir: string | undefined
+let ctx: Context | undefined
+
+afterEach(async () => {
+  await ctx?.fiber.dispose()
+  ctx = undefined
+  if (workdir !== undefined) await rm(workdir, { recursive: true, force: true })
+  workdir = undefined
+})
+
+describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compacts mid-flight and keeps running', () => {
+  it('summarizes older history into a checkpoint without breaking the task', async () => {
+    workdir = await mkdtemp(join(tmpdir(), 'dsh-compaction-'))
+    for (let i = 1; i <= 4; i++) {
+      await writeFile(join(workdir, `file${i}.txt`), `This is file number ${i}. `.repeat(50))
+    }
+
+    // Reasoning tokens require a larger generation cap than the retained checkpoint.
+    ctx = await codingHarness(workdir, {
+      persona: SYSTEM_PROMPT,
+      tokenMeter: {
+        contextWindow: 2000,
+      },
+      compact: {
+        thresholdRatio: 0.5,
+        retainTokens: 400,
+        summarizationProvider: '',
+        summarizationModel: '',
+        maxTokens: 1024,
+        compactionRetries: 1,
+      },
+      persistenceRoot: join(workdir, '.sessions'),
+    })
+    const agent = ctx.agentLoop.create(SessionId('e2e-compaction'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
+
+    agent.send([{
+      type: 'text',
+      text: 'Read file1.txt, file2.txt, file3.txt, and file4.txt one at a '
+        + 'time using cat (a separate bash command for each). After reading all four, tell me how '
+        + 'many files you read and the number mentioned in file1.txt.',
+    }])
+    await waitForIdle(ctx, agent)
+
+    const events = [...agent.session.events]
+
+    // A compaction ran: the start…end bracket landed in the real log.
+    const starts = events.filter(e => e.type === 'compact/start')
+    const ends = events.filter(e => e.type === 'compact/end')
+    expect(starts.length).toBeGreaterThan(0)
+    expect(ends.length).toBe(starts.length) // every start was released
+
+    // It succeeded at least once: a compact/summary provenance event and a
+    // replace-op user/message (the surface mutation) both landed.
+    const summaries = events.filter(e => e.type === 'compact/summary')
+    expect(summaries.length).toBeGreaterThan(0)
+    const replaceNode = events.find((e) => {
+      const se = e as unknown as { type: string; surfaceOp?: unknown }
+      return se.type === 'user/message' && typeof se.surfaceOp === 'object' && se.surfaceOp !== null
+    })
+    expect(replaceNode).toBeDefined()
+
+    // The summary shadowed real older nodes (the surface shrank vs. the raw
+    // message-producing event count).
+    const summaryData = summaries[0]!.data as { shadowedSeqs: number[] }
+    expect(summaryData.shadowedSeqs.length).toBeGreaterThan(0)
+
+    // The conversation survived compaction: the agent produced a final answer
+    // that reflects the work (it read four files).
+    const answer = finalText(events).toLowerCase()
+    expect(answer.length).toBeGreaterThan(0)
+    expect(answer).toMatch(/\b(4|four)\b/)
+  }, 240_000)
+})

examples/headless-agent/tests/full-loop.e2e.ts

@@ -0,0 +1,48 @@
+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 { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts'
+import { SessionId } from '@deepseek-ai/dsh-session'
+
+/**
+ * The first place a REAL model meets the REAL bash tool: the cheap canary
+ * before the coding-task e2e. Key-gated (see vitest.e2e.config.ts).
+ */
+
+let ctx: Context | undefined
+let workdir: string | undefined
+
+afterEach(async () => {
+  // Always dispose the harness, even on failure/retry/timeout: agent-loop
+  // teardown stops the loop and LocalBashExecutor teardown kills any
+  // process the model left behind.
+  await ctx?.fiber.dispose()
+  ctx = undefined
+  if (workdir !== undefined) await rm(workdir, { recursive: true, force: true })
+  workdir = undefined
+})
+
+describe.skipIf(!process.env.DEEPSEEK_API_KEY)('full loop: real model + real bash tool', () => {
+  it('runs a bash command on request and reports its output', async () => {
+    workdir = await mkdtemp(join(tmpdir(), 'dsh-full-loop-e2e-'))
+    ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT })
+    const agent = ctx.agentLoop.create(SessionId('e2e-loop'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
+
+    agent.send([{ type: 'text', text: 'Run `echo e2e-ok` with the bash tool and tell me its exact output.' }])
+    await waitForIdle(ctx, agent)
+
+    const events = [...agent.session.events]
+    const calls = events.filter(event => event.type === 'tool/call')
+    expect(calls.length).toBeGreaterThan(0)
+    expect(calls.some(event => event.data.name === 'bash')).toBe(true)
+
+    const results = events.filter(event => event.type === 'tool/result')
+    const resultTexts = results.flatMap(event =>
+      event.data.content.filter(block => block.type === 'text').map(block => block.text))
+    expect(resultTexts.some(text => text.includes('e2e-ok'))).toBe(true)
+
+    expect(finalText(events)).toContain('e2e-ok')
+  }, 120_000)
+})

examples/headless-agent/tests/harness.ts

@@ -0,0 +1,95 @@
+import { Context } from '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'
+import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit'
+import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
+import * as ToolBash from '@deepseek-ai/dsh-tool-bash'
+import * as ToolTodo from '@deepseek-ai/dsh-tool-todo'
+import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
+import TokenMeterService from '@deepseek-ai/dsh-token-meter'
+import type { TokenMeterConfig } from '@deepseek-ai/dsh-token-meter'
+import ToolResultPruneService from '@deepseek-ai/dsh-compact-tool-result-prune'
+import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
+import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic'
+import type { BasicCompactConfig } from '@deepseek-ai/dsh-compact-basic'
+
+/**
+ * Shared harness for the headless-agent e2e suites: the full plugin stack
+ * with the real DeepSeek adapter and the real bash + todo_write tools. Lives
+ * outside the *.e2e.ts pattern so importing it never re-registers another
+ * file's tests.
+ */
+
+export const SYSTEM_PROMPT = 'You are a coding agent. Use bash for file operations '
+  + 'with cat/grep/heredocs; check [exit code: N] markers, '
+  + 'and report results briefly.'
+
+/** System prompt for the todo_write e2e: nudges the model to plan with the tool. */
+export const TODO_SYSTEM_PROMPT = 'You are a coding agent. For multi-step work, '
+  + 'use the todo_write tool to track a task list: send the WHOLE list each call, '
+  + 'keep at most one task in_progress (exactly one while work remains), and mark '
+  + 'a task completed as soon as it is done.'
+
+/** Options for {@link codingHarness}. */
+export interface CodingHarnessOptions {
+  /**
+   * Deployment persona for the tree (the system-prompt plugin's `persona`
+   * config — per-context, not per-agent). Omitted ⇒ no persona section.
+   */
+  persona?: string
+  /** Durable JSONL persistence root (the resume suite needs it; others stay file-free). */
+  persistenceRoot?: string
+  /**
+   * Load {@link BasicCompactService} with this config so the compaction e2e can
+   * trigger compaction at a small, controlled history size. Omitted ⇒ no
+   * compaction plugin (the default suites run without it).
+   */
+  compact?: BasicCompactConfig
+  /** Optional token-meter capacity loaded before compact-basic. */
+  tokenMeter?: TokenMeterConfig
+}
+
+export async function codingHarness(workdir: string, options: CodingHarnessOptions = {}): Promise<Context> {
+  const ctx = new Context()
+  await mountAgentLoopTestDependencies(ctx, {
+    systemPrompt: { persona: options.persona ?? '' },
+  })
+  await ctx.plugin(AgentLoop, { agents: [] })
+  await ctx.plugin(LlmDeepSeek)
+  await ctx.plugin(LocalBashExecutor, { cwd: workdir, timeoutMs: 30_000 })
+  await ctx.plugin(ToolBash)
+  await ctx.plugin(ToolTodo)
+  // Compaction is opt-in: only the compaction e2e loads the reusable meter and
+  // backend, with a lower context window so a short real session crosses the threshold.
+  if (options.compact !== undefined) {
+    await ctx.plugin(TokenMeterService, options.tokenMeter)
+    await ctx.plugin(ToolResultPruneService)
+    await ctx.plugin(BasicCompactService, options.compact)
+  }
+  // Durable JSONL persistence is opt-in: only the resume e2e needs it, and the
+  // other suites stay file-free. Loaded last so a resume's deferred
+  // `ctx.inject(['sessionPersistence'])` resolves once this is present.
+  if (options.persistenceRoot !== undefined) await ctx.plugin(SessionPersistenceJsonl, { root: options.persistenceRoot })
+  return ctx
+}
+
+export function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
+  return new Promise((resolve) => {
+    const dispose = ctx.on('agent/status', (subject, status) => {
+      if (subject === agent && status === 'idle') {
+        dispose()
+        resolve()
+      }
+    })
+  })
+}
+
+export function finalText(events: SessionEvent[]): string {
+  const message = events.findLast(event => event.type === 'assistant/message')
+  if (message?.type !== 'assistant/message') return ''
+  return message.data.content
+    .filter(block => block.type === 'text')
+    .map(block => block.text)
+    .join('')
+}

examples/headless-agent/tests/resume.e2e.ts

@@ -0,0 +1,67 @@
+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 { SessionId } from '@deepseek-ai/dsh-session'
+import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts'
+
+/**
+ * Proves durable conversation continuity end-to-end: run 1 tells the REAL model
+ * a fact and persists the turn to JSONL; run 2 is a fresh harness (new Context,
+ * same `.sessions` root) that RESUMES the persisted session id and asks the
+ * model to recall the fact. The recall can only come from the rehydrated event
+ * log — a fresh session would have no idea. Key-gated like the other e2es.
+ */
+
+const SECRET = 'plum-galaxy-1791'
+const SESSION_ID = SessionId('resume-e2e-session')
+
+let ctx: Context | undefined
+let root: string | undefined
+
+afterEach(async () => {
+  // Dispose even on failure/retry: agent-loop teardown stops the loop and the
+  // JSONL backend flushes; then drop the on-disk session log.
+  await ctx?.fiber.dispose()
+  ctx = undefined
+  if (root !== undefined) await rm(root, { recursive: true, force: true })
+  root = undefined
+})
+
+describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted session across processes', () => {
+  it('recalls a fact stored in a prior, separately-disposed session', async () => {
+    root = await mkdtemp(join(tmpdir(), 'dsh-resume-e2e-'))
+
+    // Run 1: a fresh agent on a KNOWN session id learns a secret, then we
+    // dispose the whole context (simulating process exit) so only the JSONL
+    // log on disk survives.
+    ctx = await codingHarness(process.cwd(), { persona: SYSTEM_PROMPT, persistenceRoot: root })
+    const first = (await ctx.agents.create({
+      sessionId: SESSION_ID,
+      agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' },
+    })).agent
+    first.send([{ type: 'text', text: `Remember this code for later: ${SECRET}. Just acknowledge it.` }])
+    await waitForIdle(ctx, first)
+    await ctx.fiber.dispose()
+    ctx = undefined
+
+    // Run 2: a brand-new context over the SAME root resumes the persisted
+    // session. The loaded event log seeds the live session, so the model sees
+    // run 1's exchange as conversation history.
+    ctx = await codingHarness(process.cwd(), { persona: SYSTEM_PROMPT, persistenceRoot: root })
+    const resumed = (await ctx.agents.resume({
+      resumeSessionId: SESSION_ID,
+      agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' },
+    })).agent
+    expect(resumed.session.id).toBe(SESSION_ID)
+    // The prior user turn is in the rehydrated log before the model is asked.
+    expect(JSON.stringify(resumed.session.deriveMessages())).toContain(SECRET)
+
+    resumed.send([{ type: 'text', text: 'What was the code I asked you to remember? Reply with just the code.' }])
+    await waitForIdle(ctx, resumed)
+
+    // The model recalls it — only possible from the resumed history.
+    expect(finalText([...resumed.session.events])).toContain(SECRET)
+  }, 180_000)
+})

examples/headless-agent/tests/todo-write.e2e.ts

@@ -0,0 +1,53 @@
+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 { codingHarness, TODO_SYSTEM_PROMPT, waitForIdle } from './harness.ts'
+import { SessionId } from '@deepseek-ai/dsh-session'
+
+/**
+ * A REAL model drives the REAL todo_write tool: verify the WORLD (the session
+ * log gains a todo/write event whose snapshot the model actually produced), not
+ * the agent's self-report. Key-gated (see vitest.e2e.config.ts).
+ */
+
+let ctx: Context | undefined
+let workdir: string | undefined
+
+afterEach(async () => {
+  await ctx?.fiber.dispose()
+  ctx = undefined
+  if (workdir !== undefined) await rm(workdir, { recursive: true, force: true })
+  workdir = undefined
+})
+
+describe.skipIf(!process.env.DEEPSEEK_API_KEY)('todo_write: real model records a plan', () => {
+  it('appends a todo/write event with the model-produced task list', async () => {
+    workdir = await mkdtemp(join(tmpdir(), 'dsh-todo-write-e2e-'))
+    ctx = await codingHarness(workdir, { persona: TODO_SYSTEM_PROMPT })
+    const agent = ctx.agentLoop.create(SessionId('e2e-todo'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
+
+    agent.send([{ type: 'text', text:
+      'Use the todo_write tool to record a plan of exactly two steps: first '
+      + '"inspect the failing test" (in_progress), then "apply the fix" (pending). '
+      + 'Send both in one todo_write call, then reply with the single word DONE.' }])
+    await waitForIdle(ctx, agent)
+
+    const events = [...agent.session.events]
+
+    // The model actually called the tool.
+    const calls = events.filter(event => event.type === 'tool/call')
+    expect(calls.some(event => event.data.name === 'todo_write')).toBe(true)
+
+    // And the tool wrote a todo/write event to the log — verify the WORLD.
+    const todoEvents = events.filter(event => event.type === 'todo/write')
+    expect(todoEvents.length).toBeGreaterThan(0)
+
+    const todos = (todoEvents.at(-1)!).data.todos
+    expect(todos).toEqual([
+      { content: 'inspect the failing test', status: 'in_progress' },
+      { content: 'apply the fix', status: 'pending' },
+    ])
+  }, 120_000)
+})