Merge remote-tracking branch 'origin/master' into feat/adr0016-type-build-check

This commit is contained in:
imccyu
2026-06-22 00:35:51 +08:00
365 changed files with 13601 additions and 7241 deletions

13
packages/ui/README.md Normal file
View File

@@ -0,0 +1,13 @@
# ui/ — editor/client integration surfaces
Integrations that expose the agent to an external editor or client. These are **product** packages: a real surface a user drives the harness through.
| Package | Role | ctx key |
|---|---|---|
| `acp/` | Agent Client Protocol bridge: serves the agent to an ACP editor (Zed) over JSON-RPC stdio | (drives `ctx.agents`/`ctx.sessions`) |
| `stdio-agent/` | Terminal stdio chat APP: the agent-core spine + console logger + readline UI + a pre-created `main` agent, with a `bin` | (composition + `bin`) |
| `acp-agent/` | ACP server APP: the agent-core spine + JSONL persistence + the `acp` bridge (no stdout logger), with a `bin` | (composition + `bin`) |
A UI integration is a client-driver plugin, not a loop change and not a capability seam: it consumes the existing `agent/*` event taxonomy and the `dsh-agent` factory. The readline `ui-stdio` plugin is the unstructured analogue but lives in `support/` because it exists chiefly for the examples and the coverage gate — `ui/` is reserved for surfaces shipped as product.
`stdio-agent` and `acp-agent` are the two **app packages**: each composes the [`core/agent-core`](../core/agent-core/README.md) spine with its coupled front-door cluster (and owns the boot `bin`), so a leaf `cordis.yml` is just the swappable backends plus one app entry. They live in `ui/` because each IS a user-facing front door; the stdout-purity coupling (logger vs. no logger) becomes a property of the artifact rather than a leaf convention.

View File

@@ -0,0 +1,41 @@
# @deepseek-ai/dsh-acp-agent
The **ACP server app**: a Cordis app plugin that composes the providerless agent spine ([`@deepseek-ai/dsh-agent-core`](../../core/agent-core/README.md)) with the front-door cluster an [Agent Client Protocol](../acp/README.md) server needs, and a `bin` that boots a leaf `cordis.yml` speaking ACP JSON-RPC on stdio.
It is the structured counterpart to [`@deepseek-ai/dsh-stdio-agent`](../stdio-agent/README.md): both consume the same spine, but this one bakes in the OPPOSITE front-door cluster.
## What it bakes in — and what it deliberately omits
stdout is the ACP JSON-RPC channel, so the cluster is defined as much by what it LEAVES OUT as what it includes:
| Plugin | Why |
|---|---|
| `@deepseek-ai/dsh-agent-core` | the spine, pre-creating **no** agents (ACP `session/new` creates them on demand) |
| `@deepseek-ai/dsh-session-persistence-jsonl` | durable JSONL session log (the bridge advertises `loadSession`) |
| `@deepseek-ai/dsh-acp` | the bridge that owns stdout for JSON-RPC |
| ~~console logger~~ | **omitted** — it writes to stdout and would corrupt the protocol frames ([the stdout-purity footgun](../acp/README.md)) |
| ~~`hmr`~~ | **omitted** — the editor owns the subprocess |
Because the package wires no logger entry, an ACP leaf has **nothing to get wrong by default**: it only picks backends, so the common mistake — copying a console-logger entry from the stdio config — has no place here. (A leaf author technically *can* still add `@cordisjs/plugin-logger-console` as a sibling entry; the package can't forbid that. So the rule stands: never add a stdout logger to an ACP leaf — stdout is the JSON-RPC channel. Use a stderr exporter if you need logs.)
## Config
| Key | Default | Routed to |
|---|---|---|
| `model` | (required) | the per-session agent template the bridge creates agents from |
| `systemPrompt` | (required) | the per-session agent's system prompt |
| `persistenceRoot` | `./.sessions` | the JSONL backend's root directory |
The leaf supplies the swappable backends: an LLM adapter (`llm-deepseek` for the real model, `llm-replay` for keyless snapshot replay) and a bash executor (`bash-local`).
## The bin
`dsh-acp-agent [path-to-cordis.yml]` (default `./cordis.yml`):
- loads a gitignored `.env` from the cwd — **skipped** in snapshot REPLAY so a stray key can never trigger a live call;
- honors `DSH_SNAPSHOT=replay` by booting the sibling `cordis.snapshot.yml` (the keyless replay tree, `llm-replay` in place of `llm-deepseek`);
- in a snapshot run, disposes the context on stdin EOF so the session log is fully flushed before exit.
Run it under `node --expose-internals`: the cordis Loader resolves the config's bare plugin specifiers through its internal module loader, active only under that flag. (`demo:acp` runs under tsx, whose tsconfig `paths` map resolves them instead.)
All diagnostics go to **stderr** — stdout is the protocol.

View File

@@ -0,0 +1,47 @@
{
"name": "@deepseek-ai/dsh-acp-agent",
"description": "ACP server app: the agent-core spine + JSONL persistence + the ACP bridge (no stdout logger, no hmr, no pre-created agents), with a bin to boot a leaf cordis.yml over JSON-RPC stdio",
"version": "0.0.1",
"private": true,
"type": "module",
"main": "lib/index.js",
"types": "lib/index.d.ts",
"bin": {
"dsh-acp-agent": "lib/bin.js"
},
"exports": {
".": {
"types": "./lib/index.d.ts",
"default": "./lib/index.js"
},
"./bin": {
"types": "./lib/bin.d.ts",
"default": "./lib/bin.js"
},
"./src/*": "./src/*",
"./package.json": "./package.json"
},
"files": [
"lib",
"src"
],
"license": "BSD-3-Clause",
"peerDependencies": {
"@cordisjs/plugin-include": "^1.0.4",
"@cordisjs/plugin-loader": "^1.0.0-rc.4",
"@deepseek-ai/dsh-acp": "^0.0.1",
"@deepseek-ai/dsh-agent-core": "^0.0.1",
"@deepseek-ai/dsh-session-persistence-jsonl": "^0.0.1",
"cordis": "^4.0.0-rc.6",
"schemastery": "^3.17.0"
},
"devDependencies": {
"@cordisjs/plugin-include": "workspace:^",
"@cordisjs/plugin-loader": "workspace:^",
"@deepseek-ai/dsh-acp": "workspace:^",
"@deepseek-ai/dsh-agent-core": "workspace:^",
"@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^",
"cordis": "^4.0.0-rc.6",
"schemastery": "^3.17.0"
}
}

View File

@@ -0,0 +1,168 @@
#!/usr/bin/env node
/**
* The `dsh-acp-agent` bin: boot the ACP server from a leaf `cordis.yml` that
* loads the {@link @deepseek-ai/dsh-acp-agent} app plugin (plus an LLM adapter
* and a bash executor), speaking ACP JSON-RPC on stdio.
*
* Owns the ACP-specific boot glue the example's `start.ts` once held:
* - `.env` loading (`DEEPSEEK_API_KEY` / `DEEPSEEK_BASE_URL`) — SKIPPED in
* snapshot REPLAY so a stray key can never trigger a live model call.
* - snapshot-mode config selection: `DSH_SNAPSHOT=replay` swaps the given
* `cordis.yml` for its sibling `cordis.snapshot.yml` (the keyless replay
* tree: `llm-replay` in place of `llm-deepseek`).
* - the stdin-dispose lifecycle: in a snapshot run the harness closes stdin
* when done, so dispose the context (flushing persistence) and exit cleanly.
*
* IMPORTANT: stdout is the ACP JSON-RPC channel. This bin writes diagnostics to
* STDERR only; the app plugin loads no stdout logger. A stray stdout write
* corrupts the protocol frames.
*
* Usage: `dsh-acp-agent [path-to-cordis.yml]` (default `./cordis.yml`).
*
* @module @deepseek-ai/dsh-acp-agent/bin
*/
import { pathToFileURL } from 'node:url'
import { basename, dirname, resolve } from 'node:path'
import { Context } from 'cordis'
import Loader from '@cordisjs/plugin-loader'
/**
* Resolve the config to boot, honoring snapshot REPLAY. Given the requested
* path, replay mode swaps a `cordis.yml` basename for `cordis.snapshot.yml` in
* the SAME directory (the keyless replay tree). Other modes use the path as-is.
* Returns an absolute path resolved from the cwd.
*/
export function resolveConfigPath(configPath: string, snapshotMode: string | undefined): string {
const absolute = resolve(process.cwd(), configPath)
if (snapshotMode !== 'replay') return absolute
const dir = dirname(absolute)
const replayName = basename(absolute).replace(/cordis\.ya?ml$/, 'cordis.snapshot.yml')
return resolve(dir, replayName)
}
/**
* Load `DEEPSEEK_API_KEY` / `DEEPSEEK_BASE_URL` from a gitignored `.env` in the
* cwd (Node native). Diagnostics go to STDERR (stdout is the protocol). In
* REPLAY mode the caller skips this entirely — replay must never reach the
* network, so a present `.env` must not enable a live call.
*/
function loadEnv(): void {
try {
process.loadEnvFile(resolve(process.cwd(), '.env'))
} catch (error) {
if ((error as NodeJS.ErrnoException | null)?.code !== 'ENOENT') {
process.stderr.write(`dsh-acp-agent: failed to load .env: ${String(error)}\n`)
}
// ENOENT (no .env) is fine — rely on the ambient environment.
}
}
/**
* Make a load failure fail loud with a clear message on stderr. Covers the
* failure path the entry-tree check below cannot: when the include's
* `[Service.init]` throws (e.g. a config FILE missing in a real directory), the
* cordis Loader surfaces it as an unhandled promise rejection AFTER `boot()`
* resolves — `loader.await()` does NOT rethrow it (`EntryTree.await()` uses
* `Promise.allSettled`, which swallows rejections). Node's default handler
* already exits non-zero on an unhandled rejection, so this does not change the
* exit code; it replaces the noisy stack dump with a single labelled line (on
* STDERR — stdout is the ACP JSON-RPC channel) and guarantees `process.exit(1)`.
* Install before `boot()`.
*/
export function installFailLoud(): void {
process.on('unhandledRejection', (err: unknown) => {
process.stderr.write(`dsh-acp-agent: fatal load failure: ${err instanceof Error ? err.stack ?? err.message : String(err)}\n`)
process.exit(1)
})
}
/**
* After the tree settles, assert every loader entry actually started. This is
* the load-bearing guard against the SILENT-exit-0 bug: a plugin module that
* fails to IMPORT (e.g. a config path in a non-existent directory) is caught and
* only LOGGED by the cordis Loader (`entry._init`), leaving the entry with no
* `fiber` and producing no rejection — so the process would otherwise exit 0. A
* started entry has a `fiber`; throw on any entry still missing one so `boot()`
* rejects.
*
* A `disabled` entry is the one legitimate fiber-less state: `Entry.refresh()`
* deliberately skips `init()` for it, so it settles without a fiber by design —
* a valid "plugin turned off" config, not a failed import. Exclude it.
*/
function assertEntriesLoaded(ctx: Context): void {
const failed = [...ctx.loader.entries()].filter(entry => entry.fiber === undefined && !entry.disabled)
if (failed.length > 0) {
const names = failed.map(entry => entry.options.name).join(', ')
throw new Error(`dsh-acp-agent: plugin(s) failed to load: ${names} (see the error(s) logged above)`)
}
}
/**
* Boot the Loader against `absoluteConfigPath`. The include is handed the
* config's ABSOLUTE `file://` URL as its `path`, so resolution never depends on
* `ctx.baseUrl` (an absolute URL ignores the base) and can never fall back to
* the cwd. `baseUrl` is still pinned to the config's directory so the config's
* OWN relative plugin/include paths resolve against it. Returns the root context
* once the whole tree has settled.
*
* The `await ctx.loader.await()` is load-bearing: `loader.create()` returns once
* the include ENTRY is registered, but the include then loads its child plugins
* asynchronously. Without awaiting the tree, `boot()` would resolve while the ACP
* bridge is still mounting — the process would have no stdin handle attached yet
* and could exit 0 silently. Awaiting keeps the process alive until the bridge
* is up.
*
* `loader.await()` does NOT rethrow load errors (`EntryTree.await()` uses
* `Promise.allSettled`), so failures are surfaced two ways: a plugin that fails
* to IMPORT leaves an entry with no fiber, caught here by
* {@link assertEntriesLoaded} (this `boot()` rejects); a plugin whose init THROWS
* surfaces as an unhandled rejection caught by {@link installFailLoud} (installed
* by `main()` before this runs). Together any load failure exits non-zero.
*
* Bare plugin specifiers in the config (`@deepseek-ai/dsh-*`, npm packages) are
* resolved by the cordis Loader's internal module loader, which is only active
* under `node --expose-internals`. The `demo:acp` script runs under tsx (whose
* tsconfig `paths` map resolves the workspace plugins instead), but a consumer
* running the built bin under plain node must pass `--expose-internals` so the
* Loader resolves the config's plugins from the config directory rather than
* relative to its own module.
*/
export async function boot(absoluteConfigPath: string): Promise<Context> {
const ctx = new Context()
ctx.baseUrl = pathToFileURL(dirname(absoluteConfigPath)).href + '/'
await ctx.plugin(Loader)
await ctx.loader.create({
name: '@cordisjs/plugin-include',
config: { path: pathToFileURL(absoluteConfigPath).href },
})
await ctx.loader.await()
assertEntriesLoaded(ctx)
return ctx
}
/**
* Entry point. Installs the fail-loud guard, selects the config (snapshot-aware),
* loads `.env` outside replay, boots, and — in a snapshot run — disposes the
* context on stdin EOF so the session log is fully flushed before exit and the
* harness's `waitForExit` resolves. In a normal editor session stdin stays open
* for the connection's lifetime (the editor kills the process), so the EOF
* handler never fires.
*/
export async function main(argv: string[] = process.argv.slice(2)): Promise<void> {
installFailLoud()
const snapshotMode = process.env.DSH_SNAPSHOT
const configPath = resolveConfigPath(argv[0] ?? './cordis.yml', snapshotMode)
if (snapshotMode !== 'replay') loadEnv()
const ctx = await boot(configPath)
if (snapshotMode !== undefined) {
process.stdin.on('end', () => {
void ctx.fiber.dispose().then(() => { process.exit(0) })
})
}
}
/* v8 ignore start -- top-level CLI invocation; the testable core is
resolveConfigPath()/boot()/main(), driven by the keyless snapshot + Loader-path tests */
await main()
/* v8 ignore stop */

View File

@@ -0,0 +1,72 @@
/**
* The ACP server app: the providerless agent spine ({@link
* @deepseek-ai/dsh-agent-core}) plus the coupled front-door cluster an ACP
* server needs — JSONL session persistence and the {@link @deepseek-ai/dsh-acp}
* bridge, and DELIBERATELY NOTHING that writes to stdout.
*
* The cluster is the OPPOSITE of {@link @deepseek-ai/dsh-stdio-agent}'s, and
* baking it in is the whole point: an ACP server speaks JSON-RPC on stdout, so
* a stray console logger would corrupt the protocol frames (the [stdout-purity
* footgun]). This package contains NO console-logger entry, NO `hmr` (the editor
* owns the subprocess), and pre-creates NO agents (ACP `session/new` creates
* them on demand) — so the default front door has no logger entry to get wrong.
* (A leaf `cordis.yml` could still add a sibling `@cordisjs/plugin-logger-console`,
* which this app does not prevent — so the rule "never add a stdout logger to an
* ACP leaf" still stands; the app just gives the leaf nothing to misconfigure.)
*
* The leaf supplies only the swappable backends: the LLM adapter (`llm-deepseek`
* for the real model, `llm-replay` for keyless snapshot replay) and the bash
* executor (`bash-local`). This app's {@link Config} (model, system prompt,
* persistence root) routes each value to where it is wired — model/prompt onto
* the bridge's per-session agent template, the root onto the JSONL backend.
*
* Plugin export shape: named `name`/`Config`/`apply`, NO default export — the
* cordis Loader's `unwrapExports` does `exports.default ?? exports`, so a stray
* default would collapse the module to the bare `apply` and drop the `Config`
* namespace (see docs/postmortem/0001 — the exact bug that shipped here once).
* The keyless ACP snapshot/Loader-path tests guard this end-to-end.
*
* @module @deepseek-ai/dsh-acp-agent
*/
import type { Context } from 'cordis'
import z from 'schemastery'
import * as acp from '@deepseek-ai/dsh-acp'
import * as agentCore from '@deepseek-ai/dsh-agent-core'
import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
export const name = 'acp-agent'
/**
* App config: the swappable per-deployment values. `model`/`systemPrompt`
* configure the agent template the ACP bridge creates each session's agent from
* (NOT a pre-created agent — ACP creates agents at `session/new`);
* `persistenceRoot` is the JSONL backend's directory.
*/
export interface Config {
/** Model name for ACP-created agents (must have a registered adapter). */
model: string
/** Per-agent system prompt for ACP-created agents. */
systemPrompt: string
/** Directory the JSONL session backend writes under. Defaults to `./.sessions`. */
persistenceRoot?: string
}
export const Config: z<Config> = z.object({
model: z.string().required(),
systemPrompt: z.string().required(),
persistenceRoot: z.string().default('./.sessions'),
})
/**
* Compose the spine with the ACP front door. The agent-core bundle pre-creates
* NO agents (its `agents` list defaults to `[]`); the JSONL backend persists
* under `persistenceRoot`; the ACP bridge owns stdout for JSON-RPC and creates
* one agent per `session/new` from `model`/`systemPrompt`. No logger, no `hmr` —
* stdout stays pure.
*/
export function apply(ctx: Context, config: Config): void {
ctx.plugin(agentCore)
ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' })
ctx.plugin(acp, { model: config.model, systemPrompt: config.systemPrompt })
}

View File

@@ -0,0 +1,73 @@
import { describe, expect, it } from 'vitest'
import { Context } from 'cordis'
import Loader from '@cordisjs/plugin-loader'
import * as acpAgent from '../src/index.ts'
/**
* In-process unit coverage for the @deepseek-ai/dsh-acp-agent composition:
* mounting it brings up the agent-core spine + JSONL persistence + the ACP
* bridge in one `ctx.plugin`. Unlike the stdio app, this one loads NO
* Loader-only plugin (no hmr), so it mounts in a plain Context.
*
* The REAL Loader-path guard (export shape via `unwrapExports`, the headline
* ACP operations end-to-end) is the keyless bin smoke in `load-path.e2e.ts`;
* this spec asserts the composition and the persistenceRoot default branch.
*/
async function mount(config: acpAgent.Config): Promise<Context> {
const ctx = new Context()
await ctx.plugin(acpAgent, config)
// The bundle mounts its children inside apply() (not awaited there); let their
// fibers settle so the spine services are ready.
await new Promise(resolve => setTimeout(resolve, 50))
return ctx
}
describe('dsh-acp-agent composition', () => {
it('brings up the spine + persistence + the ACP bridge', async () => {
const ctx = await mount({ model: 'mock', systemPrompt: 'hi', persistenceRoot: '/tmp/dsh-acp-agent-test' })
expect(ctx.get('agents')).toBeDefined()
expect(ctx.get('sessions')).toBeDefined()
expect(ctx.get('sessionPersistence')).toBeDefined()
expect(ctx.get('agentLoop')).toBeDefined()
// No pre-created agents — ACP session/new creates them on demand.
expect(ctx.get('agents')!.list()).toHaveLength(0)
await ctx.fiber.dispose()
})
it('defaults the persistence root when omitted', async () => {
// Exercises the `?? './.sessions'` fallback for a direct-apply caller that
// bypasses the schema's `.default(...)`: call `apply` directly (not via
// `ctx.plugin`, which validates+defaults the config first) with no
// persistenceRoot, so the runtime fallback is the one that fires.
const ctx = new Context()
acpAgent.apply(ctx, { model: 'mock', systemPrompt: 'hi' })
await new Promise(resolve => setTimeout(resolve, 50))
expect(ctx.get('sessionPersistence')).toBeDefined()
await ctx.fiber.dispose()
})
it('exposes its plugin shape', () => {
expect(acpAgent.name).toBe('acp-agent')
expect(acpAgent.Config).toBeDefined()
})
it('has the namespace-plugin export shape (no stray default) so the Loader keeps name/Config/apply', () => {
// Postmortem 0001 guard: a stray `export default apply` makes the Loader's
// `unwrapExports` (`exports.default ?? exports`) collapse the module to the
// bare `apply` function, DROPPING the named `name`/`Config`. This package has
// no `inject` export, so that collapse would NOT crash at load (the keyless
// bin smoke would still answer `initialize`) — it would silently lose its
// config schema. So guard the shape directly here: assert no `default`
// export, and that the real `unwrapExports` leaves `name`/`Config`/`apply`
// intact. Adding `export default` to src/index.ts fails this test.
expect('default' in acpAgent).toBe(false)
expect(typeof acpAgent.apply).toBe('function')
const loader = Object.create(Loader.prototype) as Loader
const unwrapped = loader.unwrapExports(acpAgent) as Record<string, unknown>
expect(unwrapped).toBe(acpAgent)
expect(unwrapped.name).toBe('acp-agent')
expect(unwrapped.Config).toBeDefined()
expect(typeof unwrapped.apply).toBe('function')
})
})

View File

@@ -0,0 +1,195 @@
import { spawn } from 'node:child_process'
import { mkdtemp, mkdir, rm, symlink, writeFile, readFile } from 'node:fs/promises'
import { existsSync } from 'node:fs'
import { tmpdir } from 'node:os'
import { dirname, join } from 'node:path'
import { fileURLToPath, pathToFileURL } from 'node:url'
import {
ClientSideConnection,
ndJsonStream,
PROTOCOL_VERSION,
type Agent as AcpAgent,
type Client,
type RequestPermissionRequest,
type RequestPermissionResponse,
type SessionNotification,
} from '@agentclientprotocol/sdk'
import { Readable, Writable } from 'node:stream'
import { afterEach, describe, expect, it } from 'vitest'
/**
* BUILT-ARTIFACT smoke for the published `dsh-acp-agent` bin. `load-path.e2e.ts`
* boots `src/bin.ts` under tsx — but the package's `bin` field points at
* `lib/bin.js`, run under plain `node` by a real consumer. This runs the REAL
* `lib/bin.js` under `node` (NOT tsx) and asserts it answers an `initialize`
* JSON-RPC frame, so a regression in the published entry (a settle race that
* exits before the bridge attaches, a stdout logger leaking onto the protocol)
* fails here.
*
* It build-gates: SKIPS if `lib/bin.js` is absent (suite run without
* `pnpm run build`); CI runs it after the build step. Setup mirrors a real
* install (a temp dir whose `node_modules` symlinks the built packages) and runs
* `node --expose-internals` (the cordis Loader resolves bare plugin specifiers
* via its internal module loader, active only under that flag). KEYLESS:
* `initialize` never reaches the model; a dummy key lets `llm-deepseek` boot.
*/
const repoRoot = fileURLToPath(new URL('../../../../', import.meta.url))
const acpBin = join(repoRoot, 'packages/ui/acp-agent/lib/bin.js')
const dshPackages = [
'core/agent-core', 'core/agent', 'core/session', 'core/system-prompt',
'core/tools', 'core/agent-loop', 'llm/llm', 'llm/llm-deepseek', 'bash/bash',
'bash/bash-local', 'bash/tool-bash', 'support/invariants',
'session-persistence/session-persistence',
'session-persistence/session-persistence-jsonl', 'ui/acp', 'ui/acp-agent',
]
const vendorPackages = [
'cordis', 'loader', 'include', 'timer', 'hmr', 'logger-console',
'schemastery', 'cosmokit',
]
// Third-party deps the ACP bridge needs at runtime. They are declared by
// `dsh-acp` (NOT by `acp-agent`), so they live under `packages/ui/acp/node_modules`
// and are NOT necessarily hoisted where THIS test file can resolve them — pnpm's
// strict layout only exposes a package's deps under that package. Resolve each
// from the `ui/acp` package directory (the one that declares it) so the lookup
// works regardless of hoisting, then symlink it into the consumer for plain node.
const npmDeps = ['@agentclientprotocol/sdk', 'zod']
const acpPkgDir = join(repoRoot, 'packages/ui/acp')
async function pkgName(absDir: string): Promise<string> {
const json = JSON.parse(await readFile(join(absDir, 'package.json'), 'utf8')) as { name: string }
return json.name
}
async function link(target: string, name: string, nm: string): Promise<void> {
const dest = join(nm, name)
await mkdir(dirname(dest), { recursive: true })
await symlink(target, dest)
}
/** Build a temp consumer dir + a minimal acp `cordis.yml`. Returns the dir. */
async function makeConsumer(): Promise<string> {
const dir = await mkdtemp(join(tmpdir(), 'acp-built-bin-'))
const nm = join(dir, 'node_modules')
for (const rel of dshPackages) {
const abs = join(repoRoot, 'packages', rel)
await link(abs, await pkgName(abs), nm)
}
for (const v of vendorPackages) {
const abs = join(repoRoot, 'vendor', v)
await link(abs, await pkgName(abs), nm)
}
for (const dep of npmDeps) {
// Resolve from `ui/acp`'s package.json URL (the package that declares the
// dep), not this test file's location — `acp-agent` does not depend on these.
const fromAcp = pathToFileURL(join(acpPkgDir, 'package.json')).href
const resolved = fileURLToPath(import.meta.resolve(`${dep}/package.json`, fromAcp))
await link(dirname(resolved), dep, nm)
}
await writeFile(join(dir, 'cordis.yml'), [
'- id: llm-deepseek',
' name: \'@deepseek-ai/dsh-llm-deepseek\'',
' config:',
' apiKey: !!js process.env.DEEPSEEK_API_KEY',
' models: [deepseek-v4-flash]',
'- id: bash',
' name: \'@deepseek-ai/dsh-bash-local\'',
'- id: acp-agent',
' name: \'@deepseek-ai/dsh-acp-agent\'',
' config:',
' model: deepseek-v4-flash',
' systemPrompt: \'test agent\'',
'',
].join('\n'))
return dir
}
let consumer: string | undefined
let child: ReturnType<typeof spawn> | undefined
afterEach(async () => {
if (child !== undefined) { child.kill('SIGKILL'); child = undefined }
if (consumer !== undefined) await rm(consumer, { recursive: true, force: true })
consumer = undefined
})
describe.skipIf(!existsSync(acpBin))('dsh-acp-agent BUILT bin (node lib/bin.js, no tsx)', () => {
it('boots the published bin and answers an initialize JSON-RPC frame on stdout', async () => {
consumer = await makeConsumer()
child = spawn(process.execPath, ['--expose-internals', acpBin, './cordis.yml'], {
cwd: consumer,
// Dummy key: initialize never reaches the model, so it is never used.
env: { ...process.env, DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot' },
stdio: ['pipe', 'pipe', 'pipe'],
})
const stderr: string[] = []
child.stderr!.setEncoding('utf8')
child.stderr!.on('data', (c: string) => stderr.push(c))
// Tee raw stdout for a protocol-purity check, and feed it to the SDK client.
const rawOut: string[] = []
const passthrough = new Readable({ read() {} })
child.stdout!.on('data', (buf: Buffer) => { rawOut.push(buf.toString('utf8')); passthrough.push(buf) })
child.stdout!.on('end', () => passthrough.push(null))
const stream = ndJsonStream(
Writable.toWeb(child.stdin!) as WritableStream<Uint8Array>,
Readable.toWeb(passthrough) as ReadableStream<Uint8Array>,
)
const makeClient = (_a: AcpAgent): Client => ({
sessionUpdate(_p: SessionNotification): Promise<void> { return Promise.resolve() },
requestPermission(_p: RequestPermissionRequest): Promise<RequestPermissionResponse> {
return Promise.resolve({ outcome: { outcome: 'cancelled' } })
},
})
const client = new ClientSideConnection(makeClient, stream)
const init = await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
// A response at all proves the built bin booted the bridge (the settle-race
// regression would exit before answering); loadSession proves the real app
// mounted, not a collapsed export shape.
expect(init.agentCapabilities?.loadSession).toBe(true)
expect(stderr.join('')).not.toContain('without inject')
// stdout purity: every emitted line is a JSON-RPC frame, no logger leak.
for (const line of rawOut.join('').split('\n').filter(l => l.trim().length > 0)) {
expect(() => JSON.parse(line) as unknown).not.toThrow()
}
}, 30_000)
it('fails LOUD (non-zero exit + stderr) on a config whose directory does not exist', async () => {
// A typo'd config path must fail clearly, not exit 0. The include plugin
// itself cannot be imported from a non-existent dir; the Loader logs that and
// leaves the entry with no fiber, which boot()'s entry-load check throws on.
const { code, stderr } = await runBinExpectingExit('/nonexistent/dir/cordis.yml')
expect(code).not.toBe(0)
expect(stderr).toContain('failed to load')
}, 30_000)
it('fails LOUD (non-zero exit + stderr) on a missing config file in a real directory', async () => {
// The directory exists (the include imports), but the file does not — the
// include's init throws "config file not found", which surfaces as an
// unhandled rejection the fail-loud guard turns into a non-zero exit.
consumer = await makeConsumer()
const { code, stderr } = await runBinExpectingExit('./does-not-exist.yml', consumer)
expect(code).not.toBe(0)
expect(stderr).toContain('config file not found')
}, 30_000)
})
/** Spawn the built acp bin against `configArg` and resolve with its exit code + stderr. */
function runBinExpectingExit(configArg: string, cwd: string = tmpdir()): Promise<{ code: number; stderr: string }> {
return new Promise((resolve, reject) => {
const proc = spawn(process.execPath, ['--expose-internals', acpBin, configArg], {
cwd,
env: { ...process.env, DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot' },
stdio: ['pipe', 'pipe', 'pipe'],
})
child = proc
let stderr = ''
proc.stderr.setEncoding('utf8')
proc.stderr.on('data', (c: string) => { stderr += c })
const timer = setTimeout(() => { proc.kill('SIGKILL'); reject(new Error(`bin did not exit within 25s. stderr:\n${stderr}`)) }, 25_000)
proc.on('exit', (code) => { clearTimeout(timer); resolve({ code: code ?? -1, stderr }) })
proc.on('error', (err) => { clearTimeout(timer); reject(err) })
proc.stdin.end()
})
}

View File

@@ -0,0 +1,147 @@
import { spawn, type ChildProcessWithoutNullStreams } from 'node:child_process'
import { Readable, Writable } from 'node:stream'
import { mkdtemp, rm, writeFile } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { fileURLToPath } from 'node:url'
import { afterEach, describe, expect, it } from 'vitest'
import {
ClientSideConnection,
ndJsonStream,
PROTOCOL_VERSION,
type Agent as AcpAgent,
type Client,
type RequestPermissionRequest,
type RequestPermissionResponse,
type SessionNotification,
} from '@agentclientprotocol/sdk'
/**
* REAL-load-path smoke for @deepseek-ai/dsh-acp-agent: boot the app through its
* own `bin` (the demo:acp entry) as a subprocess, driving the cordis Loader and
* `unwrapExports` over a minimal `cordis.yml` that loads THIS package. This is
* the guard a hand-built `ctx.plugin({...})` mount structurally cannot be — that
* bypasses `unwrapExports`, the exact path that once dropped the bridge's
* `inject` and shipped (docs/postmortem/0001). It exercises the headline ACP
* operations end-to-end: `initialize` → `session/new` → `session/load`.
*
* KEYLESS: `session/new` and `session/load` reach the agent FACTORY but never
* the model (no prompt is sent), so no DEEPSEEK_API_KEY is needed. A dummy key
* lets `llm-deepseek`'s `apply()` (key-PRESENT check only) boot the tree.
*
* The config is written into a temp dir whose cwd IS the session workspace, so
* the bash workdir validation passes. We point tsx at the repo-root tsconfig
* (TSX_TSCONFIG_PATH) because the child's cwd is outside the repo and the
* unbuilt `paths` map is found by searching UP from cwd.
*/
const binScript = fileURLToPath(new URL('../src/bin.ts', import.meta.url))
const tsxLoader = fileURLToPath(import.meta.resolve('tsx'))
// Repo root is four levels up from packages/ui/acp-agent/tests.
const repoTsconfig = fileURLToPath(new URL('../../../../tsconfig.json', import.meta.url))
// A minimal leaf that loads this app + the two backends — the same shape as
// examples/acp-agent/cordis.yml, inlined so the package test owns its fixture.
const CORDIS_YML = `
- id: llm-deepseek
name: '@deepseek-ai/dsh-llm-deepseek'
config:
apiKey: !!js process.env.DEEPSEEK_API_KEY
models: [deepseek-v4-flash]
- id: bash
name: '@deepseek-ai/dsh-bash-local'
- id: acp-agent
name: '@deepseek-ai/dsh-acp-agent'
config:
model: deepseek-v4-flash
systemPrompt: 'You are a test agent.'
`
interface Spawned {
child: ChildProcessWithoutNullStreams
client: ClientSideConnection
stderr: string[]
}
let spawned: Spawned | undefined
let workdir: string | undefined
afterEach(async () => {
if (spawned !== undefined) {
spawned.child.kill('SIGKILL')
spawned = undefined
}
if (workdir !== undefined) await rm(workdir, { recursive: true, force: true })
workdir = undefined
})
async function boot(): Promise<Spawned & { cwd: string }> {
workdir = await mkdtemp(join(tmpdir(), 'acp-agent-pkg-'))
const cwd = workdir
const configPath = join(cwd, 'cordis.yml')
await writeFile(configPath, CORDIS_YML)
const child = spawn(
process.execPath,
['--import', tsxLoader, binScript, configPath],
{
cwd,
env: {
...process.env,
TSX_TSCONFIG_PATH: repoTsconfig,
// Key-present check only; no prompt is sent, so the model is never called.
DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'keyless-acp-agent-smoke',
},
stdio: ['pipe', 'pipe', 'pipe'],
},
)
const stderr: string[] = []
child.stderr.setEncoding('utf8')
child.stderr.on('data', (chunk: string) => stderr.push(chunk))
const stream = ndJsonStream(
Writable.toWeb(child.stdin) as WritableStream<Uint8Array>,
Readable.toWeb(child.stdout) as ReadableStream<Uint8Array>,
)
const makeClient = (_agent: AcpAgent): Client => ({
sessionUpdate(_params: SessionNotification): Promise<void> {
return Promise.resolve()
},
requestPermission(_params: RequestPermissionRequest): Promise<RequestPermissionResponse> {
return Promise.resolve({ outcome: { outcome: 'cancelled' } })
},
})
const client = new ClientSideConnection(makeClient, stream)
spawned = { child, client, stderr }
return { ...spawned, cwd }
}
describe('dsh-acp-agent real-load-path smoke (bin + Loader, keyless)', () => {
it('boots via its bin and answers initialize → session/new → session/load', async () => {
const { client, cwd, stderr } = await boot()
// initialize: a broken export shape (collapsed bridge plugin, dropped inject)
// crashes the tree on the first service read here — see postmortem 0001.
const init = await client.initialize({
protocolVersion: PROTOCOL_VERSION,
clientCapabilities: {},
})
expect(init.agentCapabilities?.loadSession).toBe(true)
// session/new reaches the agent FACTORY (create) without the model.
const { sessionId } = await client.newSession({ cwd, mcpServers: [] })
expect(sessionId).toBeTruthy()
// session/load reaches the resume FACTORY + persistence without the model:
// load an UNKNOWN id (loading the live `sessionId` would correctly reject as
// "already loaded"). The bridge consults `sessionPersistence.list()` then
// `agents.resume()`, both of which run from the JSON-RPC read loop OUTSIDE
// the bridge's inject scope — the exact path postmortem 0001 crashed. A
// healthy tree rejects with a not-found error; a broken export shape would
// instead throw "cannot get property … without inject" before reaching it.
const unknownId = '00000000-0000-4000-8000-000000000000'
await client.loadSession({ sessionId: unknownId, cwd, mcpServers: [] }).then(
() => { throw new Error('expected session/load of an unknown id to reject') },
(error: unknown) => { expect(String(error)).not.toContain('without inject') },
)
expect(stderr.join('')).not.toContain('without inject')
}, 30_000)
})

View File

@@ -0,0 +1,30 @@
{
"extends": "../../../tsconfig.base.json",
"compilerOptions": {
"rootDir": "src",
"outDir": "lib"
},
"include": [
"src"
],
"references": [
{
"path": "../../../vendor/cordis"
},
{
"path": "../../../vendor/schemastery"
},
{
"path": "../../../vendor/loader"
},
{
"path": "../acp"
},
{
"path": "../../core/agent-core"
},
{
"path": "../../session-persistence/session-persistence-jsonl"
}
]
}

View File

@@ -0,0 +1,18 @@
import { defineConfig } from 'tsdown'
/**
* acp-agent ships TWO entries: the plugin (`index`) and the CLI `bin` (`bin`),
* the latter referenced by package.json `bin`/`exports["./bin"]`. The root
* tsdown builds only `src/index.ts`, so this override adds `bin.ts`.
* Declarations come from `tsc -b` (dts: false), matching every package.
*/
export default defineConfig({
entry: ['src/index.ts', 'src/bin.ts'],
outDir: 'lib',
format: ['esm'],
platform: 'node',
target: 'es2024',
fixedExtension: false,
dts: false,
clean: false,
})

88
packages/ui/acp/README.md Normal file
View File

@@ -0,0 +1,88 @@
# @deepseek-ai/dsh-acp
The **Agent Client Protocol (ACP)** bridge: exposes the DeepSeek Harness coding agent as an ACP server over JSON-RPC stdio, so editors (Zed and other ACP clients) can drive it — streaming render, tool-call display, and resumable sessions. Zed is the current target client: baseline ACP behavior should remain reasonable for other clients, but bridge capabilities and compatibility decisions are evaluated against Zed first. **N concurrent sessions per connection** (see [ACP multi-session](../../../docs/rfc/proposed/feature/2026-06-14-acp-multi-session.md)): each maps to its own `ReactLoopAgent`, and every event is demuxed strictly by session id so two sessions streaming at once never interleave.
It is a **client-driver / UI plugin**, the structured analogue of the readline `stdio-chat` plugin — NOT a loop change and NOT a [capability seam](../../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md). It consumes the existing `agent/*` event taxonomy, the `dsh-agent` create/resume factory, and `dsh-session-persistence`.
## Service / plugin
`apply(ctx, config)` — wires an `AgentSideConnection` (from `@agentclientprotocol/sdk`) to `process.stdin`/`process.stdout` and implements the ACP `Agent` method surface.
`inject: ['agents', 'sessions', 'sessionPersistence', 'tools']` — programs against the interface packages only (never `dsh-agent-loop`). `sessionPersistence` is required because `initialize` advertises `loadSession: true`; `tools` lets a tool own how its calls render (`presentCall`/`presentResult`) — the bridge looks the definition up by name and falls back to a generic presentation when a tool declares none (see Tool-call presentation).
### Config
| Key | Default | Meaning |
|---|---|---|
| `model` | — | Model name for created agents (must have a registered adapter). |
| `systemPrompt` | — | Per-agent system prompt. |
| `agentName` | `deepseek-harness-acp` | Server name reported in `initialize`. |
| `agentVersion` | `0.0.1` | Server version reported in `initialize`. |
## ACP method mapping
| ACP method | Harness seam | Notes |
|---|---|---|
| `initialize` | static | negotiate `protocolVersion`; advertise baseline prompt capabilities (`text`, plus `resource_link` rendered as text) and `loadSession: true` |
| `session/new` | `ctx.agents.create({ sessionId, meta:{cwd} })` | creates a new session/agent; N concurrent sessions are allowed, keyed by id; `cwd` must be absolute (it becomes the session's workspace — see Per-session cwd); non-empty `additionalDirectories` and `mcpServers` rejected |
| `session/load` | `ctx.agents.resume(...)` | replays the persisted event log to the client as `session/update` — the USER side (`user/message``user_message_chunk`), assistant text/reasoning (`assistant/chunk`), and tool calls/results (`tool/call` + `tool/result`). Re-loading an already-live id is rejected; the id's load slot is reserved (`loadingIds`) BEFORE the async resume so a pipelined load of the SAME id can't leak a second agent (distinct ids load concurrently). The resumed session keeps its PERSISTED header `cwd`, so its bash tools run in the original workspace; the requested `cwd` must be absolute and match the persisted `cwd`. After the async resume a `closed` re-check refuses to install a record if the bridge tore down mid-load |
| `session/prompt` | `agent.send()` | supports ACP `text` and `resource_link` blocks; rejects image/audio/embedded resource and empty prompts; one in-flight prompt PER session (independent); settles on the OWNING turn's end (a turn that ends in `error` rejects the RPC) |
| `session/cancel` | `agent.cancel()` | the queue-aware cancel: aborts a running step, clears queued + steering work, and drops a turn about to start, then settles the prompt `cancelled` — for ONLY that session (a cancel never touches another session's stream or prompt) |
| `session/update` | `session/event` | `agent_message_chunk` (text-delta), `agent_thought_chunk` (reasoning-delta), `user_message_chunk` (load replay), `tool_call`/`tool_call_update` (title/kind/rawInput/content owned by the TOOL via `presentCall`/`presentResult` — see Tool-call presentation) |
## Multi-session
The bridge multiplexes N sessions over one connection. Live sessions are held in a `Map<sessionId, SessionRecord>` (forward) with a `WeakMap<Agent, sessionId>` reverse map so `agent/*` events — which carry only the `Agent` — demux in O(1). Every `session/event` and `agent/status` is routed strictly to its owning record, so concurrent sessions never cross-settle or interleave their `session/update` notifications. State is per session: one in-flight prompt each, `session/cancel` aborts and settles only its own agent/prompt, and disposal drains every live session in parallel to quiescence. (Per-session *permission* ownership is reserved for the deferred permission gate — `TODO(rfc010-permission-gate)`.)
Background-task isolation rides on `dsh-tool-bash`: bash task ids are global and predictable, so each task carries an opaque owner token — the owning agent's `session.header.id` — stored on the task inside the executor (`dsh-bash`'s `ownerOf(id)` seam). `bash_output`/`bash_kill` reject a task whose token differs from the caller's session token, so one session's agent can't read or kill another's task. Ownership is by session TOKEN, not `Agent` object identity — a different `Agent` object on the same session may access the task — and because the token lives on the executor's task it survives a `tool-bash` HMR reload.
## Per-session cwd
Each session runs in its own workspace, recorded as the session's `SessionHeader.cwd`. On `session/new` the (absolute) request `cwd` becomes that header cwd; on `session/load` the resumed session keeps its PERSISTED header cwd and the request `cwd` must be absolute and equal to it, so the editor and bash executor agree on the workspace before an agent is constructed. A load whose persisted session has no absolute cwd is REJECTED up front via a metadata-only `list()` check, BEFORE resume constructs an agent (else bash would silently fall back to the server's launch dir, and a post-resume reject would leak the registered agent). `dsh-tool-bash` then defaults the bash workdir to the calling agent's `session.header.cwd` (an explicit model `workdir` still wins; a relative one resolves against the session cwd; with no session cwd the executor falls back to its own config / `process.cwd()`). So the server no longer has to be launched in the workspace — an editor can open any project folder, and N sessions over one connection can each target a different directory. (`additionalDirectories` is still rejected: widening the tool/filesystem scope beyond the single cwd is a separate sandbox concern.)
## Tool-call presentation
How a tool call renders in the editor is owned by the TOOL, not the bridge — the bridge never special-cases tool names. Each tool may declare `presentCall(args)` (pending state: a human-readable `title`, a `kind` for the icon, the salient `rawInput` to show in a detail view, and optional `content` blocks shown alongside) and `presentResult(args, result)` (completed state: an optional replacement `title` and reformatted `content`) on its `dsh-tools` definition. The bridge looks the definition up by name in `ctx.tools` and maps the neutral `ToolCallPresentation`/`ToolResultPresentation` to the ACP `tool_call`/`tool_call_update` wire shapes. A tool that declares neither gets a generic fallback (title = tool name, raw parsed args as `rawInput`, kind inferred from the name). For example `dsh-tool-bash` sets the title to the exact `command` ("ls -la src"), `kind: 'execute'`, the `command` as `rawInput`, the model `description` as a `content` text block, and wraps the completed output in a fenced ` ```console ` block. (The command is the title because an editor hides `rawInput` for execute-kind cards — Zed renders it only for non-terminal tools — and the reference adapters likewise use the command as an execute tool's title.)
The `tool/result` session event carries only `{ callId, content, isError }` — not the tool name or args — so to call a tool's `presentResult` the bridge keeps a small per-session map from `callId` to the in-flight call's `(name, args)`, populated on `tool/call` and removed as each result is presented (it holds only currently-in-flight calls, never finished ones). This is bridge-local state — NOT a change to the event schema or a core service. The map lives on the `SessionRecord`, so two concurrent sessions never cross their in-flight tool state; a `session/load` replay uses a throwaway presenter that pairs each `tool/call` with its `tool/result` as the log replays in order, so replayed tool cards render identically to live ones.
## Terminal card (capability-gated)
A tool whose call IS a shell command (`bash`) can render as a real **terminal card** — a working-directory header with the command's output and an exit-status pill — rather than a plain text block. The tool asks for this with the neutral `terminal` field on its presentation (`dsh-tools`: a `{ cwd?, output?, exitCode?, signal? }` shape on `ToolCallPresentation`/`ToolResultPresentation`); the bridge maps it to the Zed `_meta` convention, gated on the client advertising `clientCapabilities._meta.terminal_output` in `initialize`:
- `tool_call`: `content:[…, {type:'terminal', terminalId}]` + `_meta.terminal_info.{terminal_id, cwd}` — the terminal id is the harness `callId`; the cwd is the tool's explicit absolute `terminal.cwd`, else a relative `terminal.cwd` resolved against the session cwd, else the session's workspace cwd (the bridge fills the default, since the pure tool presenter can't see it). Any pending `content` the tool supplied (e.g. bash's `description`) renders BEFORE the terminal block, so the description sits above the card.
- `tool_call_update`: `_meta.terminal_output.{terminal_id, data}` (the captured output) plus `_meta.terminal_exit.{terminal_id, exit_code | signal}` when the tool reported a structured exit. In terminal mode the update's `content` is OMITTED — an ACP `tool_call_update.content` REPLACES the call's content, so sending the fenced text block would clobber the terminal content block from the call.
When the client does NOT advertise the capability, none of the `_meta`/terminal content is emitted: the `tool_call` shows the `description` content block and the `tool_call_update` carries the ` ```console ` text block (above) as the rendering — so a non-Zed client is never worse off. The `_meta` object is ACP's spec-blessed extensibility point; the specific `terminal_info`/`terminal_output`/`terminal_exit` keys are a Zed convention, not the ACP `terminal/create` sub-protocol (which would make the editor execute the command, bypassing `dsh-bash`'s sandbox/env-scrub/ownership/cwd). Live incremental streaming and command classification are follow-ups. See [the terminal-rendering RFC](../../../docs/rfc/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md).
## Settle-exactly-once
A `session/prompt` resolves (or rejects) exactly once, keyed off the canonical session log (the `session/event` stream), NOT the `agent/turn-start`/`agent/turn-end` events. One listener captures the prompt's owning turn from the log's `turn/start` and settles on the matching `turn/end` — the one signal that always fires (`closeTurn` appends it unconditionally, even when a boundary emit throws and the `agent/turn-end` EVENT is skipped). A prompt settles only on ITS OWN turn (`inflight.turn === turn/end.turn`), so a stale `turn/end` for a previously-cancelled turn whose end arrives late can never settle the wrong prompt. A turn that ends `error` REJECTS the RPC with an internal error carrying the failure message (ACP has no error stop reason); every other reason resolves via the codec. As a fallback, when the agent settles to `idle`/`disposed` with a prompt still pending — e.g. a `session/event` listener registered before the bridge threw and starved the bridge's listener — an `agent/status` handler reconciles the prompt from the log (the owning turn's `turn/end`, or `cancelled` if the turn was torn down without one). An empty/whitespace prompt is rejected up front — it would queue no work, so no turn would start and the RPC would hang.
## Disposal & disconnect
Teardown reaches quiescence: for EVERY live session settle any pending prompt as `cancelled`, then run that session's [`AgentHandle`](../../core/agent/README.md) `dispose()` — which stops the loop (sets `disposed` + aborts the in-flight step), `await`s the loop's exit (the final `turn/end` + `session/flush` are captured while the session is still attached), unregisters the agent, and removes its session from the store. A turn cut off mid-flight by teardown ends with reason `disposed` (not `aborted``dispose()` uses the disposed path, not `session/cancel`'s queue-aware `cancel()`). The per-session disposes run in parallel. The same teardown runs on a **client disconnect** (`conn.closed` resolves when the editor quits / the transport EOFs), so a vanished client never leaves an orphaned running — or idled-but-still-registered — agent whose `session/update` writes are silently swallowed. The two paths are idempotent and memoized (the first clears the `sessions` map; a second caller awaits the same teardown promise).
## Known limitations (tracked TODOs)
- **`TODO(rfc010-permission-gate)`** — the `tools/execute` permission gate (`session/request_permission`) is NOT implemented; tools run with the executor's full authority. The `agent→sessionId` reverse map is in place so the gate can route a permission request (which receives only `exec.agent`) back to its originating session. [ACP support](../../../docs/rfc/proposed/feature/2026-06-14-acp-agent-client-protocol.md) and [ACP multi-session](../../../docs/rfc/proposed/feature/2026-06-14-acp-multi-session.md) stay `proposed` until the gate (and per-session permission ownership) land.
- **`additionalDirectories`** — rejected. A session operates in its single `cwd` (see Per-session cwd); widening the tool/filesystem scope to extra roots is a separate sandbox concern, not yet implemented.
## stdout is the protocol
The JSON-RPC frames go on stdout, so this plugin MUST run in an example that loads **no stdout logger** (the console logger writes to stdout and would corrupt the frames). The guarantee is config-only — see `examples/acp-agent` (no console logger) and [ACP support risks](../../../docs/rfc/proposed/feature/2026-06-14-acp-agent-client-protocol.md#risks). A stderr exporter is fine for logging.
## Running
`pnpm --dir /path/to/deepseek-harness run demo:acp` boots `examples/acp-agent` (needs `DEEPSEEK_API_KEY`). Point an ACP client at it; for Zed, add to `agent_servers`:
```json
{
"agent_servers": {
"DeepSeek Harness": {
"command": "pnpm",
"args": ["--dir", "/path/to/deepseek-harness", "run", "demo:acp"]
}
}
}
```

View File

@@ -0,0 +1,162 @@
# ACP feature support checklist
A structured inventory of [Agent Client Protocol](https://agentclientprotocol.com) (ACP) features and where the harness's ACP bridge ([`@deepseek-ai/dsh-acp`](README.md)) stands on each. The bridge exposes the harness agent as an ACP **server** (the agent side of an editor↔agent connection), so "supported" below means *the bridge implements the agent's half* — answering an agent method, advertising a capability, or calling a client method.
## Scope
This tracks the **stable** ACP v1 surface (schema `1.14.0`, `schema/v1/schema.json`) PLUS the **unstable/draft** features that the two reference adapters — [`claude-agent-acp`](https://github.com/zed-industries/claude-code-acp) (Claude Code) and [`codex-acp`](https://github.com/zed-industries/codex-acp) (OpenAI Codex) — actually ship. A purely-unstable feature that neither reference adapter uses is omitted (see [Out of scope](#out-of-scope)).
Legend: ✅ supported · ⚠️ partial / fallback · ❌ not yet · — n/a. The **Stable** column marks whether the feature is in the released v1 schema (S) or only the unstable schema (U). The **Claude** / **Codex** columns record whether each reference adapter ships it, as a maturity signal.
## At a glance
The bridge implements the **core prompt-turn loop** for N concurrent sessions: initialize, session new/load, prompt, cancel, streamed assistant/thought chunks, tool-call rendering (including Zed terminal cards), and resumable session replay. The largest **unbuilt** areas are the **permission gate** (`session/request_permission`), **MCP passthrough**, **session modes / config options / model selection**, **slash commands**, and **agent plans** — all of which both reference adapters ship — plus the client **filesystem** and **terminal** method families (which the adapters mostly do NOT drive either — see rows 43-49). See [Gap summary](#gap-summary).
## 1. Agent methods (client → agent)
| Method | Stable | Bridge | Claude | Codex | Notes |
|---|---|---|---|---|---|
| `initialize` | S | ✅ | ✅ | ✅ | Negotiates `PROTOCOL_VERSION`; advertises `loadSession` + baseline prompt caps. Snapshots the Zed `_meta.terminal_output` client cap. |
| `authenticate` | S | ⚠️ | ✅ | ✅ | No-op stub; the bridge advertises no `authMethods`, so there is nothing to authenticate. |
| `logout` | S | ❌ | ✅ | ✅ | Gated by `agentCapabilities.auth.logout`; not advertised. |
| `session/new` | S | ✅ | ✅ | ✅ | Maps to `agents.create`; requires an absolute `cwd` (becomes the session workspace); rejects non-empty `additionalDirectories` / `mcpServers`. |
| `session/load` | S | ✅ | ✅ | ✅ | Maps to `agents.resume` + full event-log replay; validates persisted `cwd` before constructing the agent. |
| `session/resume` | S | ❌ | ✅ | ✅ | Reconnect WITHOUT replay; gated by `sessionCapabilities.resume`. Not advertised. |
| `session/close` | S | ❌ | ✅ | ✅ | No `session/close` handler — the SDK dispatch returns `method_not_found`. The bridge tears sessions down on client disconnect / Cordis disposal (cross-cutting, see [§8](#8-cross-cutting)), but that is not the on-demand per-session method. |
| `session/prompt` | S | ✅ | ✅ | ✅ | Maps to `agent.send`; one in-flight prompt per session; settles on the owning turn's end. |
| `session/cancel` | S | ✅ | ✅ | ✅ | Queue-aware `agent.cancel`; settles the in-flight prompt `cancelled`, scoped to the one session. |
| `session/set_mode` | S | ❌ | ✅ | ✅ | Session modes not modeled (see [§6 Modes](#6-session-modes--config-options--models)). |
| `session/set_config_option` | S | ❌ | ✅ | ✅ | Config options not modeled. |
| model selection | S | ❌ | ✅ | ✅ | No distinct stable `session/set_model` — model is the `model`-category `session/set_config_option`. The bridge fixes the model per-bridge via config; no runtime switch. Codex still uses the legacy `unstable_setSessionModel` ext method. |
| `session/list` | S | ❌ | ✅ | ✅ | Gated by `sessionCapabilities.list`. The harness HAS `sessionPersistence.list()` (used internally for load-cwd validation) but does not expose it over ACP. |
| `session/delete` | S | ❌ | ✅ | ✅ | Gated by `sessionCapabilities.delete`. |
| `session/fork` | U | ❌ | ✅ | ❌ | Claude ships `unstable_forkSession`; Codex does not. |
## 2. Client methods the agent CALLS (agent → client)
These are capabilities the bridge would *drive* on the editor. The harness runs tools in-process (its own `dsh-bash` executor, direct file I/O), so it does not yet delegate to the editor for any of these.
| Method | Stable | Bridge | Claude | Codex | Notes |
|---|---|---|---|---|---|
| `session/update` | S | ✅ | ✅ | ✅ | The bridge's primary output channel (see [§4](#4-sessionupdate-variants)). |
| `session/request_permission` | S | ❌ | ✅ | ✅ | **The biggest gap.** Tools run with the executor's full authority; no user authorization round-trip. The `agent→sessionId` reverse map is already in place to route a future permission request. Tracked `TODO(rfc010-permission-gate)`. |
| `fs/read_text_file` | S | ❌ | ✅ | ❌ | The harness reads files directly (it does not see the editor's unsaved buffer state). Claude delegates; Codex does not. |
| `fs/write_text_file` | S | ❌ | ✅ | ❌ | Same — direct writes, no editor delegation. |
| `terminal/create` | S | ❌ | ❌ | ❌ | Neither reference adapter drives the client terminal API either — both, like the bridge, render shell output as tool-call content + a `_meta` channel (see [§5 Terminal](#terminal-rendering)). |
| `terminal/output` | S | ❌ | ❌ | ❌ | As above. |
| `terminal/wait_for_exit` | S | ❌ | ❌ | ❌ | As above. |
| `terminal/kill` | S | ❌ | ❌ | ❌ | As above. |
| `terminal/release` | S | ❌ | ❌ | ❌ | As above. |
| `elicitation/create` · `elicitation/complete` | U | ❌ | ✅ | ⚠️ | Structured user-input forms. Claude calls the `unstable_*` elicitation methods (to surface MCP server elicitations); Codex does NOT — its `CodexElicitationHandler` maps elicitations onto `session/request_permission` instead. |
## 3. Capabilities
### 3a. `agentCapabilities` (advertised by the bridge)
| Capability | Stable | Bridge | Claude | Codex | Notes |
|---|---|---|---|---|---|
| `loadSession` | S | ✅ | ✅ | ✅ | Advertised `true`; backs `session/load`. |
| `promptCapabilities.image` | S | ❌ | ✅ | ✅ | Bridge advertises `image: false`; image prompt blocks are rejected. |
| `promptCapabilities.audio` | S | ❌ | ❌ | ❌ | `audio: false`; neither adapter accepts audio either. |
| `promptCapabilities.embeddedContext` | S | ❌ | ✅ | ✅ | `embeddedContext: false`; embedded `resource` blocks rejected. |
| `mcpCapabilities.{http,sse}` | S | ❌ | ✅ | ⚠️ | No MCP passthrough; `mcpServers` is rejected. Claude advertises http+sse, Codex http only. |
| `sessionCapabilities.*` | S | ❌ | ✅ | ✅ | None advertised (list/delete/resume/close/additionalDirectories/fork all off). |
| `auth.logout` | S | ❌ | ✅ | ✅ | Not advertised. |
| `authMethods[]` | S | ⚠️ | ✅ | ✅ | Advertised as empty (no auth required to reach the model). |
| `agentInfo` (name/version) | S | ✅ | ✅ | ✅ | From `agentName` / `agentVersion` config. |
| `_meta` custom caps | S | ❌ | ✅ | — | E.g. Claude's `claudeCode.promptQueueing`. The bridge advertises no custom `_meta`. |
### 3b. `clientCapabilities` (consumed by the bridge)
| Capability | Stable | Bridge | Notes |
|---|---|---|---|
| `fs.{readTextFile,writeTextFile}` | S | ❌ | Not consulted (the bridge never calls `fs/*`). |
| `terminal` | S | ❌ | Not consulted; the bridge keys terminal rendering off the Zed `_meta.terminal_output` cap instead. |
| `_meta.terminal_output` (Zed) | S (`_meta`) | ✅ | Snapshotted per session at create/load; gates terminal-card rendering. |
## 4. `session/update` variants
| `sessionUpdate` | Stable | Bridge | Claude | Codex | Notes |
|---|---|---|---|---|---|
| `agent_message_chunk` | S | ✅ | ✅ | ✅ | From `assistant/chunk` text-delta. |
| `agent_thought_chunk` | S | ✅ | ✅ | ✅ | From `assistant/chunk` reasoning-delta. |
| `user_message_chunk` | S | ✅ | ✅ | ✅ | Emitted during `session/load` replay to reconstruct the user side. |
| `tool_call` | S | ✅ | ✅ | ✅ | Tool-owned presentation (`presentCall`); see [§5](#5-tool-call-rendering). |
| `tool_call_update` | S | ✅ | ✅ | ✅ | From `tool/result` via `presentResult`. |
| `plan` | S | ❌ | ✅ | ✅ | No agent plan emitted. Both adapters emit real plan entries (Codex's `CodexEventHandler.updatePlan` maps `turn/plan/updated``{ sessionUpdate: 'plan', entries }`). |
| `available_commands_update` | S | ❌ | ✅ | ✅ | No slash commands advertised. |
| `current_mode_update` | S | ❌ | ✅ | ✅ | No session modes. |
| `config_option_update` | S | ❌ | ✅ | ✅ | No config options. |
| `usage_update` | S | ❌ | ✅ | ✅ | Token/cost reporting not surfaced (the harness records token usage internally on `assistant/message`). |
| `session_info_update` | S | ❌ | ⚠️ | ⚠️ | Session title/metadata not pushed. |
## 5. Tool-call rendering
Tool-call presentation is **owned by each tool** (`presentCall` / `presentResult` on the `dsh-tools` definition), not special-cased in the bridge — see the [terminal-and-tool-rendering RFC](../../../docs/rfc/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md).
| Feature | Stable | Bridge | Claude | Codex | Notes |
|---|---|---|---|---|---|
| `ToolCallKind` mapping | S | ✅ | ✅ | ✅ | `execute`/`read`/`edit`/`other` inferred from the tool; richer mapping possible. |
| `ToolCallStatus` | S | ✅ | ✅ | ✅ | `in_progress``completed`/`failed`. |
| `content` blocks | S | ✅ | ✅ | ✅ | Text content; the description renders above the card. |
| `diff` content | S | ❌ | ✅ | ✅ | No structured diff rendering for edits (would need a diffing edit tool + presenter). |
| `terminal` content | S | ✅ | ✅ | ✅ | Via the Zed `_meta` terminal convention (see below), not the spec `terminal/*` sub-protocol. |
| `locations` (follow-along) | S | ❌ | ✅ | ✅ | No file-location hints emitted. |
| `rawInput` | S | ✅ | ⚠️ | ✅ | Parsed tool args surfaced as `rawInput`. |
| `rawOutput` | S | ❌ | ⚠️ | ✅ | Not emitted. |
### Terminal rendering
⚠️ Implemented via the **Zed `_meta` convention** (`terminal_info` / `terminal_output` / `terminal_exit`), gated on the client advertising `_meta.terminal_output` — NOT the spec's `terminal/create` sub-protocol (which would make the editor execute the command, bypassing `dsh-bash`'s sandbox / env-scrub / ownership / cwd). Both reference adapters take the same `_meta` approach. Live incremental streaming (`terminal_output_delta`, which Codex negotiates) is a follow-up — the bridge currently sends the full captured output once on the result.
## 6. Session modes / config options / models
❌ None modeled. Both reference adapters ship modes (Claude: a "plan" auto-mode; Codex: read-only / agent / agent-full-access mapping to its approval+sandbox policy), the newer config-option surface, and runtime model selection. The harness fixes the model per-bridge via `AcpConfig.model`. These are coupled to the unbuilt **permission gate** (a mode often selects an approval policy), so they are natural follow-ups to it.
## 7. Content blocks
| Block | Stable | In prompts | In updates | Notes |
|---|---|---|---|---|
| `text` | S | ✅ | ✅ | Baseline. |
| `resource_link` | S | ✅ | ⚠️ | Accepted in prompts and rendered into text (`acpPromptToText`); not emitted as a structured update block. |
| `image` | S | ❌ | ❌ | Rejected in prompts (`promptCapabilities.image: false`). |
| `audio` | S | ❌ | ❌ | Rejected. |
| `resource` (embedded) | S | ❌ | ❌ | Rejected (`embeddedContext: false`). |
The bridge rejects unsupported prompt blocks rather than silently dropping them (`promptHasUnsupportedContent`), per the "explicit over implicit" convention.
## 8. Cross-cutting
| Feature | Stable | Bridge | Notes |
|---|---|---|---|
| `StopReason` mapping | S | ✅ | `turnEndToStopReason` is total over harness turn-end reasons → `end_turn`/`max_tokens`/`cancelled`. |
| Multi-session (N per connection) | S | ✅ | Strict per-session demux; concurrent streams never interleave. See the [multi-session RFC](../../../docs/rfc/proposed/feature/2026-06-14-acp-multi-session.md). |
| Disconnect / disposal teardown | S | ✅ | Quiesces every live session on client disconnect or Cordis disposal. |
| `_meta` extensibility | S | ⚠️ | Consumed (Zed terminal cap) and emitted (terminal `_meta`); no other custom extensions. |
| Background-task ownership isolation | — | ✅ | `bash_output`/`bash_kill` reject another session's task via an opaque owner token. |
| stdout-is-the-protocol guarantee | S | ✅ | The bridge runs in an example with no stdout logger. |
## Gap summary
Ranked by how commonly the reference adapters ship them and how much UX they unlock:
1. **Permission gate**`session/request_permission` + permission options. Tracked `TODO(rfc010-permission-gate)`; the reverse map is already wired. Foundational, and a prerequisite for modes.
2. **Session lifecycle**`session/list` + `session/delete` (the persistence layer already lists), then `session/resume` / `session/close`.
3. **Modes / config options / model selection** — coupled to the permission gate.
4. **Agent plan** (`sessionUpdate: 'plan'`) — surface the loop's plan as structured entries.
5. **Slash commands** (`available_commands_update`).
6. **MCP passthrough** (`mcpServers` on `session/new` + `mcpCapabilities`).
7. **Richer prompt content** — image / embedded `resource` blocks (needs a multimodal model path).
8. **Diff + location tool rendering**`diff` content and `locations` for edit tools.
9. **Usage reporting** (`usage_update`) — the harness already records token usage internally (on `assistant/message`).
10. **Editor filesystem delegation** (`fs/read_text_file` / `fs/write_text_file`) — lets the agent see unsaved buffers; lower priority since the harness has direct disk access.
## Out of scope
Unstable/draft ACP features that **neither** reference adapter ships are not tracked above: `providers/*` (LLM provider selection), `mcp/connect`·`mcp/message`·`mcp/disconnect` (client-side MCP passthrough), `nes/*` (Next Edit Suggestion), `document/did*` (LSP-style document sync), the v2 plan model (`plan_update` / `plan_removed`), boolean config options, `$/cancel_request`, and the draft Streamable-HTTP transport. They can be added if a target editor adopts them.
## Sources
- Stable spec: `schema/v1/schema.json` (schema `1.14.0`) and `docs/protocol/v1/*.mdx` in the [agent-client-protocol](https://github.com/agentclientprotocol/agent-client-protocol) repo.
- Reference adapters: [`claude-agent-acp`](https://github.com/zed-industries/claude-code-acp) and [`codex-acp`](https://github.com/zed-industries/codex-acp).
- Bridge: [`README.md`](README.md), [`src/index.ts`](src/index.ts), and the ACP RFCs under [`docs/rfc/`](../../../docs/rfc/README.md).

View File

@@ -0,0 +1,50 @@
{
"name": "@deepseek-ai/dsh-acp",
"description": "Agent Client Protocol (ACP) bridge: drive the DeepSeek Harness coding agent from an ACP editor over JSON-RPC stdio",
"version": "0.0.1",
"private": true,
"type": "module",
"main": "lib/index.js",
"types": "lib/types/index.d.ts",
"exports": {
".": {
"types": "./lib/types/index.d.ts",
"default": "./lib/index.js"
},
"./src/*": "./src/*",
"./package.json": "./package.json"
},
"files": [
"lib/index.js",
"lib/types/**/*.d.ts",
"lib/types/**/*.d.ts.map",
"src"
],
"license": "BSD-3-Clause",
"dependencies": {
"@agentclientprotocol/sdk": "0.25.1",
"schemastery": "^3.17.0",
"zod": "^4.0.0"
},
"peerDependencies": {
"@deepseek-ai/dsh-agent": "^0.0.1",
"@deepseek-ai/dsh-llm": "^0.0.1",
"@deepseek-ai/dsh-session": "^0.0.1",
"@deepseek-ai/dsh-session-persistence": "^0.0.1",
"@deepseek-ai/dsh-tools": "^0.0.1",
"cordis": "^4.0.0-rc.6"
},
"devDependencies": {
"@deepseek-ai/dsh-agent": "workspace:^",
"@deepseek-ai/dsh-agent-loop": "workspace:^",
"@deepseek-ai/dsh-bash-local": "workspace:^",
"@deepseek-ai/dsh-llm": "workspace:^",
"@deepseek-ai/dsh-session": "workspace:^",
"@deepseek-ai/dsh-session-persistence": "workspace:^",
"@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^",
"@deepseek-ai/dsh-system-prompt": "workspace:^",
"@deepseek-ai/dsh-tool-bash": "workspace:^",
"@deepseek-ai/dsh-tools": "workspace:^",
"cordis": "^4.0.0-rc.6"
}
}

View File

@@ -0,0 +1,108 @@
/**
* Pure translation between harness vocabulary and ACP wire types. No I/O, no
* Cordis context — every function here is total and unit-testable in isolation.
* Keeping the mapping pure is deliberate: the SDK rejects an unknown
* `stopReason`, so the {@link turnEndToStopReason} total function (with its
* exhaustive test over every `TurnEndReason` kind) is the guard that a turn
* always settles to a legal wire value.
*
* @module @deepseek-ai/dsh-acp/codec
*/
import type { ContentBlock } from '@deepseek-ai/dsh-llm'
import type { TurnEndReason } from '@deepseek-ai/dsh-session'
import type { ContentBlock as AcpContentBlock, StopReason } from '@agentclientprotocol/sdk'
/**
* Map a harness {@link TurnEndReason} to the ACP `StopReason` wire enum.
*
* The mapping is total over the kinds the loop actually produces today
* (`completed`/`aborted`/`error`/`disposed`/`max-tokens`). `TurnEndReason` is
* merge-extensible, so an unknown future kind falls through to `end_turn` —
* the safest default (the turn DID end; we just lack a more specific wire
* reason) — rather than throwing into the SDK, which would reject an unknown
* `stopReason` and break the prompt RPC. When a new kind gains a dedicated ACP
* reason (e.g. a future `refusal` → `refusal`), add an explicit case here.
*
* - `completed` → `end_turn` (the model chose to stop)
* - `max-tokens` → `max_tokens` (cut off at the output-token ceiling)
* - `aborted` → `cancelled` (a step abort or a queue-aware `agent.cancel()`, e.g. from `session/cancel`)
* - `error` → `end_turn` (defensive fallback only: the bridge REJECTS the
* `session/prompt` RPC on an error turn BEFORE calling this, so
* a client sees a JSON-RPC error, not a stop reason — see
* `rejectPrompt` in index.ts. This case keeps the function total
* for any non-bridge caller / property test.)
* - `disposed` → `cancelled` (the agent was torn down mid-turn — closest to a
* cancellation from the client's perspective)
*/
export function turnEndToStopReason(reason: TurnEndReason): StopReason {
switch (reason.kind) {
case 'completed':
return 'end_turn'
case 'max-tokens':
return 'max_tokens'
case 'aborted':
return 'cancelled'
case 'disposed':
return 'cancelled'
case 'error':
return 'end_turn'
// Merge-extensible: an unknown future TurnEndReason kind still has to
// produce a legal wire value (the SDK rejects unknown stopReason), so
// default to end_turn rather than assertNever. Add an explicit case when a
// new kind gains a dedicated ACP reason.
default:
return 'end_turn'
}
}
/**
* Translate a harness {@link ContentBlock} from a prompt into ACP content for
* replay, or `undefined` for block kinds the bridge does not surface to the
* client as message content. Today only `text` maps; `resource_link` is an
* ACP prompt-only input rendered into text by {@link acpPromptToText};
* `reasoning` is surfaced via `agent_thought_chunk`
* streaming rather than as a message block, and `tool-call`/`tool-result`/
* `image` are handled by the tool-call update path or not advertised.
*/
export function harnessBlockToAcpContent(block: ContentBlock): AcpContentBlock | undefined {
switch (block.type) {
case 'text':
return { type: 'text', text: block.text }
// reasoning → streamed as agent_thought_chunk, not a message block
// tool-call / tool-result → the tool_call / tool_call_update path
// image → not advertised
default:
return undefined
}
}
/**
* Extract plain text from an ACP prompt's content blocks. Text blocks are
* concatenated verbatim; resource links become explicit textual references so
* baseline ACP clients can point at files without the bridge silently dropping
* that context.
*/
export function acpPromptToText(prompt: readonly AcpContentBlock[]): string {
return prompt
.flatMap((block): string[] => {
switch (block.type) {
case 'text':
return [block.text]
case 'resource_link':
return [`\n[resource_link name=${JSON.stringify(block.name)} uri=${JSON.stringify(block.uri)}]\n`]
default:
return []
}
})
.join('')
}
/**
* Whether an ACP prompt contains content the bridge cannot accept. Baseline ACP
* requires `text` and `resource_link`; richer inline payloads (`resource`,
* image, audio, …) are rejected rather than silently dropped.
*/
export function promptHasUnsupportedContent(prompt: readonly AcpContentBlock[]): boolean {
return prompt.some(block => block.type !== 'text' && block.type !== 'resource_link')
}

1091
packages/ui/acp/src/index.ts Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,165 @@
import { afterEach, beforeEach, describe, expect, it } from 'vitest'
import { mkdtemp, rm } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk'
import { AgentId } from '@deepseek-ai/dsh-agent'
import { makeBridgeHarness, textResponse, type BridgeHarness } from './harness'
/**
* End-to-end bridge specs over an in-memory transport: a real
* ClientSideConnection drives the bridge's AgentSideConnection, so every
* assertion exercises actual JSON-RPC framing and the harness event taxonomy.
*/
describe('acp bridge', () => {
let storageDir: string
let harness: BridgeHarness | undefined
beforeEach(async () => {
storageDir = await mkdtemp(join(tmpdir(), 'acp-test-'))
})
afterEach(async () => {
// e2e/integration tests own their resources (AGENTS.md): dispose even on
// failure so a flaky run never leaks a context or persistence dir.
if (harness) await harness.dispose()
harness = undefined
await rm(storageDir, { recursive: true, force: true })
})
it('initialize negotiates the protocol version and advertises capabilities', async () => {
harness = await makeBridgeHarness({ storageDir })
const res = await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
expect(res.protocolVersion).toBe(PROTOCOL_VERSION)
expect(res.agentCapabilities?.loadSession).toBe(true)
expect(res.agentCapabilities?.promptCapabilities).toMatchObject({ image: false, audio: false })
expect(res.agentInfo?.name).toBe('deepseek-harness-acp')
})
it('session/new creates a session and a full prompt turn streams text then settles end_turn', async () => {
harness = await makeBridgeHarness({ storageDir, script: [textResponse('hello there')] })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
expect(sessionId).toBeTruthy()
const res = await harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'hi' }] })
expect(res.stopReason).toBe('end_turn')
// The streamed text arrived as agent_message_chunk updates.
const text = harness.updates
.filter(u => u.sessionUpdate === 'agent_message_chunk')
.map(u => (u.content.type === 'text' ? u.content.text : ''))
.join('')
expect(text).toBe('hello there')
})
it('allows multiple concurrent sessions, each with a distinct id', async () => {
harness = await makeBridgeHarness({ storageDir, script: [] })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const a = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
const b = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
expect(a.sessionId).toBeTruthy()
expect(b.sessionId).toBeTruthy()
expect(a.sessionId).not.toBe(b.sessionId)
// Both agents are live and independently registered.
expect(harness.ctx.agents.get(AgentId(a.sessionId))).toBeDefined()
expect(harness.ctx.agents.get(AgentId(b.sessionId))).toBeDefined()
})
it('rejects a non-absolute cwd but accepts any absolute cwd (per-session workspace)', async () => {
harness = await makeBridgeHarness({ storageDir })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
// Relative cwd is still rejected (it becomes the session header / bash workdir).
await expect(harness.client.newSession({ cwd: 'relative/path', mcpServers: [] }))
.rejects.toThrow(/absolute/)
// An absolute cwd that differs from the server launch dir is now ACCEPTED —
// the per-session cwd is honored (routed to the bash workdir), so the server
// no longer has to launch in the workspace.
const res = await harness.client.newSession({ cwd: '/tmp', mcpServers: [] })
expect(res.sessionId).toBeTruthy()
// The session header records that cwd, so its bash tools run there.
expect(harness.ctx.agents.get(AgentId(res.sessionId))!.session.header.cwd).toBe('/tmp')
})
it('rejects non-empty additionalDirectories', async () => {
harness = await makeBridgeHarness({ storageDir })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
await expect(harness.client.newSession({ cwd: process.cwd(), mcpServers: [], additionalDirectories: ['/x'] }))
.rejects.toThrow(/additionalDirectories/)
})
it('rejects an empty prompt without hanging', async () => {
harness = await makeBridgeHarness({ storageDir, script: [] })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
await expect(harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: ' ' }] }))
.rejects.toThrow(/empty prompt/)
})
it('rejects image content in a prompt (text-only capabilities)', async () => {
harness = await makeBridgeHarness({ storageDir, script: [] })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
await expect(harness.client.prompt({
sessionId,
prompt: [{ type: 'image', mimeType: 'image/png', data: 'AA==' }],
})).rejects.toThrow(/text/)
})
it('accepts a resource_link prompt by rendering the link into the text sent to the agent', async () => {
harness = await makeBridgeHarness({ storageDir, script: [textResponse('ok')] })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
const result = await harness.client.prompt({
sessionId,
prompt: [
{ type: 'text', text: 'fix the bug in' },
{ type: 'resource_link', uri: 'file:///x.ts', name: 'x.ts' },
],
})
expect(result.stopReason).toBe('end_turn')
const user = harness.ctx.agents.get(AgentId(sessionId))!.session.events.find(event => event.type === 'user/message')
expect(JSON.stringify(user)).toContain('resource_link')
})
it('rejects a prompt for an unknown session', async () => {
harness = await makeBridgeHarness({ storageDir })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
await expect(harness.client.prompt({ sessionId: 'nope', prompt: [{ type: 'text', text: 'hi' }] }))
.rejects.toThrow(/unknown session/)
})
it('negotiates an unsupported protocol version down to the supported one', async () => {
harness = await makeBridgeHarness({ storageDir })
const res = await harness.client.initialize({ protocolVersion: 999, clientCapabilities: {} })
expect(res.protocolVersion).toBe(PROTOCOL_VERSION)
})
it('a cancel for an unknown/absent session is a silent no-op', async () => {
harness = await makeBridgeHarness({ storageDir })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
// No session created yet — cancel must not throw.
await expect(harness.client.cancel({ sessionId: 'nope' })).resolves.toBeUndefined()
})
it('authenticate is a no-op (no auth methods advertised)', async () => {
harness = await makeBridgeHarness({ storageDir })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
await expect(harness.client.authenticate({ methodId: 'whatever' })).resolves.toBeDefined()
})
it('honors agentName/agentVersion/systemPrompt config', async () => {
harness = await makeBridgeHarness({
storageDir,
script: [textResponse('ok')],
config: { agentName: 'custom-agent', agentVersion: '9.9.9', systemPrompt: 'be terse' },
})
const res = await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
expect(res.agentInfo).toMatchObject({ name: 'custom-agent', version: '9.9.9' })
// Create + prompt so the systemPrompt config flows through agentOptions and
// reaches the model request.
const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
await harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'hi' }] })
expect(harness.adapter.requests[0]?.system).toContain('be terse')
})
})

View File

@@ -0,0 +1,67 @@
import { describe, expect, it } from 'vitest'
import type { TurnEndReason } from '@deepseek-ai/dsh-session'
import type { ContentBlock as AcpContentBlock } from '@agentclientprotocol/sdk'
import {
acpPromptToText,
harnessBlockToAcpContent,
promptHasUnsupportedContent,
turnEndToStopReason,
} from '../src/codec'
describe('turnEndToStopReason', () => {
// The SDK rejects an unknown stopReason, so this must be total over every
// TurnEndReason kind and always produce a legal wire value.
it('maps every known TurnEndReason kind to a legal StopReason', () => {
expect(turnEndToStopReason({ kind: 'completed' })).toBe('end_turn')
expect(turnEndToStopReason({ kind: 'max-tokens' })).toBe('max_tokens')
expect(turnEndToStopReason({ kind: 'aborted', reason: 'x' })).toBe('cancelled')
expect(turnEndToStopReason({ kind: 'disposed' })).toBe('cancelled')
expect(turnEndToStopReason({ kind: 'error', step: 1, message: 'boom' })).toBe('end_turn')
})
it('falls back to end_turn for an unknown (merge-extensible) future kind', () => {
// A plugin-added TurnEndReason variant the bridge does not yet know about
// must still produce a legal wire value, not throw into the SDK.
const future = { kind: 'refusal' } as unknown as TurnEndReason
expect(turnEndToStopReason(future)).toBe('end_turn')
})
})
describe('harnessBlockToAcpContent', () => {
it('maps a text block to ACP text content', () => {
expect(harnessBlockToAcpContent({ type: 'text', text: 'hi' })).toEqual({ type: 'text', text: 'hi' })
})
it('returns undefined for non-text blocks (reasoning/tool/image)', () => {
expect(harnessBlockToAcpContent({ type: 'reasoning', text: 'think' })).toBeUndefined()
expect(harnessBlockToAcpContent({ type: 'image', url: 'https://x/y.png', mimeType: 'image/png' })).toBeUndefined()
})
})
describe('acpPromptToText', () => {
it('concatenates text blocks and renders resource links explicitly', () => {
const prompt: AcpContentBlock[] = [
{ type: 'text', text: 'hello ' },
{ type: 'resource_link', uri: 'file:///x', name: 'x' },
{ type: 'text', text: 'world' },
]
expect(acpPromptToText(prompt)).toBe('hello \n[resource_link name="x" uri="file:///x"]\nworld')
})
it('returns empty string for a prompt with no text blocks', () => {
expect(acpPromptToText([{ type: 'image', mimeType: 'image/png', data: 'AA==' }])).toBe('')
})
})
describe('promptHasUnsupportedContent', () => {
it('detects image, audio, and embedded resource blocks', () => {
expect(promptHasUnsupportedContent([{ type: 'image', mimeType: 'image/png', data: 'AA==' }])).toBe(true)
expect(promptHasUnsupportedContent([{ type: 'audio', mimeType: 'audio/wav', data: 'AA==' }])).toBe(true)
expect(promptHasUnsupportedContent([{ type: 'resource', resource: { uri: 'file:///x', text: 'x' } }])).toBe(true)
})
it('passes baseline text and resource_link prompt blocks', () => {
expect(promptHasUnsupportedContent([{ type: 'text', text: 'hi' }])).toBe(false)
expect(promptHasUnsupportedContent([{ type: 'resource_link', uri: 'file:///x', name: 'x' }])).toBe(false)
})
})

View File

@@ -0,0 +1,320 @@
import { afterEach, beforeEach, describe, expect, it } from 'vitest'
import { mkdtemp, rm } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk'
import { SessionId } from '@deepseek-ai/dsh-session'
import { AgentId } from '@deepseek-ai/dsh-agent'
import { makeBridgeHarness, textResponse } from './harness'
describe('acp bridge — disposal & HMR safety', () => {
let storageDir: string
beforeEach(async () => { storageDir = await mkdtemp(join(tmpdir(), 'acp-dispose-')) })
afterEach(async () => { await rm(storageDir, { recursive: true, force: true }) })
it('disposal reaches quiescence: a running turn is aborted and awaited before dispose returns', async () => {
const harness = await makeBridgeHarness({ storageDir, script: ['hang'] })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
const agent = harness.ctx.agents.get(AgentId(sessionId))!
// Start a prompt that hangs in the model stream.
const promptDone = harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] })
await new Promise(r => setTimeout(r, 30))
expect(agent.status).toBe('running')
// Dispose the whole context. The bridge's teardown must abort the agent and
// AWAIT whenIdle() — so right after dispose resolves, the agent is settled
// (not still running). Proves disposal waited, not just requested.
await harness.ctx.fiber.dispose()
expect(agent.status).not.toBe('running')
// The in-flight prompt settled (cancelled) rather than hanging forever.
const res = await promptDone
expect(res.stopReason).toBe('cancelled')
})
it('after an ACP-only HMR dispose, a late session/new creates no orphan agent (closed guard)', async () => {
// Dispose JUST the bridge's fiber (an HMR reload) while agents/agent-loop
// stay up and the transport is still live. A late session/new must hit the
// `closed` guard and reject — NOT create an agent the disposed bridge can no
// longer stream or settle. Verify the world: no agent appeared.
const harness = await makeBridgeHarness({ storageDir, script: [] })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const before = harness.ctx.agents.list().length
await harness.acpFiber.dispose() // tear down ONLY the bridge
await expect(harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }))
.rejects.toThrow(/disposed/)
expect(harness.ctx.agents.list().length).toBe(before)
await harness.dispose()
})
it('an agent created through the bridge is unregistered when ONLY the bridge fiber is disposed', async () => {
// The factory (`ctx.agents.create`) is reached through the bridge's
// traceable service proxy, so `AgentLoop.start`'s `this.ctx.effect(...)`
// registration binds to the CALLER context — the bridge fiber — not the
// AgentLoop fiber. Disposing JUST the bridge fiber (an ACP-only HMR reload)
// must therefore reclaim the agent's registry entry, even though agents/
// agent-loop stay up. This pins the fiber-ownership the bridge's teardown
// doc comment relies on; if a refactor rebinds the registration to the
// AgentLoop fiber, the agent would survive bridge dispose and this fails.
const harness = await makeBridgeHarness({ storageDir, script: [] })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
expect(harness.ctx.agents.get(AgentId(sessionId))).toBeDefined()
await harness.acpFiber.dispose() // tear down ONLY the bridge
expect(harness.ctx.agents.get(AgentId(sessionId))).toBeUndefined()
await harness.dispose()
})
it('no agent is created by a session/new after the bridge has closed (closed guard)', async () => {
// After teardown (here a client disconnect sets `closed`), a late
// `session/new` must NOT create an orphan agent the bridge can no longer
// drive/settle. The transport is gone so the RPC rejects; assert the world:
// no new agent appeared in the registry.
const harness = await makeBridgeHarness({ storageDir, script: [] })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const before = harness.ctx.agents.list().length
await harness.closeClientTransport() // teardown → closed = true
await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }).catch(() => {})
await new Promise(r => setTimeout(r, 10))
expect(harness.ctx.agents.list().length).toBe(before)
await harness.dispose()
})
it('a client disconnect mid-prompt disposes the session (no registered agent left)', async () => {
// The ACP transport closes (editor quits) while a turn runs. The bridge must
// settle the in-flight prompt cancelled and DISPOSE the agent (the session's
// per-agent AgentHandle teardown) rather than leaving an orphaned running —
// or even idled-but-still-registered — agent whose updates are swallowed.
const harness = await makeBridgeHarness({ storageDir, script: ['hang'] })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
const agent = harness.ctx.agents.get(AgentId(sessionId))!
// Start a prompt that hangs in the model stream. The prompt RPC will never
// return (its transport is severed), so do not await it.
void harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }).catch(() => {})
await new Promise(r => setTimeout(r, 30))
expect(agent.status).toBe('running')
// Sever the transport — the bridge's conn.closed teardown runs and drives the
// agent's AgentHandle dispose to quiescence on its OWN (before any dispose()).
await harness.closeClientTransport()
await agent.whenIdle()
// The agent's loop has stopped: status `disposed`.
expect(agent.status).toBe('disposed')
// Await the bridge teardown to completion WITHOUT tearing down the root
// agents/sessions services (so we can still query them). acpFiber.dispose()
// invokes the SAME memoized quiesce() the disconnect started and awaits its
// promise — which resolves only after every rec.dispose() (loop exit +
// session removal) has finished, closing the whenIdle()/owned.dispose()
// microtask race. The AgentHandle dispose has run: the agent is unregistered
// and its session removed from the store, not merely idled (the old
// behavior). The services live on the root ctx, so they survive this.
await harness.acpFiber.dispose()
expect(harness.ctx.agents.get(AgentId(sessionId))).toBeUndefined()
expect(harness.ctx.sessions.get(SessionId(sessionId))).toBeUndefined()
await harness.dispose()
})
it('a client disconnect racing fiber dispose both reach quiescence (shared teardown)', async () => {
// conn.closed teardown and ctx.fiber.dispose() can fire near-simultaneously.
// They must share one teardown promise: dispose() must NOT return before the
// disconnect teardown's whenIdle() has settled (a `record === undefined`-only
// guard would let the second caller return early mid-teardown).
const harness = await makeBridgeHarness({ storageDir, script: ['hang'] })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
const agent = harness.ctx.agents.get(AgentId(sessionId))!
void harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }).catch(() => {})
await new Promise(r => setTimeout(r, 30))
expect(agent.status).toBe('running')
// Fire both teardown paths without awaiting the first, then await both.
const close = harness.closeClientTransport()
const dispose = harness.ctx.fiber.dispose()
await Promise.all([close, dispose])
// After BOTH settle, the agent has fully drained (not still running).
expect(agent.status).not.toBe('running')
})
it('after dispose, session/update listeners are gone (no further updates emitted)', async () => {
const harness = await makeBridgeHarness({ storageDir, script: [] })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
const session = harness.ctx.agents.get(AgentId(sessionId))!.session
await harness.ctx.fiber.dispose()
const before = harness.updates.length
// Append an event directly to the (now-detached) session: the bridge's
// session/event listener should have been disposed, so no update fires.
session.append('turn/start', { turn: 99, trigger: { kind: 'message', source: { kind: 'user' } } })
await new Promise(r => setTimeout(r, 10))
expect(harness.updates.length).toBe(before)
})
it('the final turn closing events are persisted across an AgentHandle dispose (durability)', async () => {
// The teardown-ORDER guarantee: a per-agent dispose must stop the loop,
// AWAIT its exit (so the loop's final `turn/end` + `session/flush` fire
// through the still-attached `session.onAppend` → `session/event`), and only
// THEN detach onAppend + remove the session. If the order were inverted
// (detach first), the closing events would never reach persistence. Drive a
// CLEAN turn to completion, dispose JUST the bridge, then re-load the
// persisted log from disk and assert the closing turn/end is on disk — the
// world, not the agent's self-report.
const harness = await makeBridgeHarness({ storageDir, script: [textResponse('done')] })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
await harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] })
const liveEvents = harness.ctx.agents.get(AgentId(sessionId))!.session.events.length
expect(liveEvents).toBeGreaterThan(0)
// Tear down JUST the bridge (the AgentHandle dispose runs to quiescence).
await harness.acpFiber.dispose()
expect(harness.ctx.agents.get(AgentId(sessionId))).toBeUndefined()
// Re-load the session from disk: every live event (incl. the closing
// turn/end) was flushed before the session was detached.
const reloaded = await harness.ctx.sessionPersistence.load(SessionId(sessionId))
expect(reloaded.events.length).toBe(liveEvents)
const last = reloaded.events.at(-1)!
expect(last.type).toBe('turn/end')
await harness.dispose()
})
it('a turn aborted BY the dispose still flushes its closing turn/end to disk (durability, mid-turn)', async () => {
// The teardown-order contract only earns its keep when the closing events are
// produced BY the dispose itself. Here the model stream HANGS, so the turn is
// still open when teardown runs: the composite agent effect stops the loop,
// the loop unwinds and appends `turn/end {disposed}` + runs its final
// `session/flush` — all while `onAppend` is still attached (the session
// detach is the LAST disposer in the same effect's LIFO chain) — and only
// THEN is the session detached. If the order were inverted (or the session
// were a racing SIBLING effect), the abort-produced `turn/end` would never
// reach disk and a re-load would instead show crash-recovery's synthetic
// `interrupted` closer. Re-load from disk and assert the REAL `disposed`
// reason landed — proving the loop's own closing event was captured, not a
// recovered substitute.
const harness = await makeBridgeHarness({ storageDir, script: ['hang'] })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
const agent = harness.ctx.agents.get(AgentId(sessionId))!
void harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }).catch(() => {})
await new Promise(r => setTimeout(r, 30))
expect(agent.status).toBe('running')
// The turn is OPEN in the log (turn/start appended, no turn/end yet).
const openTurnEnds = agent.session.events.filter(e => e.type === 'turn/end').length
// Dispose JUST the bridge: a fiber unload that must STILL honor the ordered
// teardown (the composite effect runs its disposer chain as a unit).
await harness.acpFiber.dispose()
expect(harness.ctx.agents.get(AgentId(sessionId))).toBeUndefined()
// The loop's own `turn/end {disposed}` is on disk (re-load: the world, not
// self-report) — NOT a crash-recovery `interrupted` substitute.
const reloaded = await harness.ctx.sessionPersistence.load(SessionId(sessionId))
const persistedTurnEnds = reloaded.events.filter(e => e.type === 'turn/end')
expect(persistedTurnEnds.length).toBe(openTurnEnds + 1)
expect(persistedTurnEnds.at(-1)!.data.reason).toMatchObject({ kind: 'disposed' })
await harness.dispose()
})
it('per-session AgentHandle dispose leaves sibling agents untouched', async () => {
// The factory returns a per-agent AgentHandle whose dispose() tears down
// EXACTLY that agent + its session — RFC 011 isolation. Create two agents
// directly through the registry factory (the same path the ACP bridge uses),
// dispose one handle, and assert the other survives, registered and
// queryable, with its session still in the store.
const harness = await makeBridgeHarness({ storageDir, script: [] })
const handleA = harness.ctx.agents.create({
agentId: AgentId('sib-a'), sessionId: SessionId('sib-a'), agentOptions: { model: 'mock' },
})
const handleB = harness.ctx.agents.create({
agentId: AgentId('sib-b'), sessionId: SessionId('sib-b'), agentOptions: { model: 'mock' },
})
expect(harness.ctx.agents.get(AgentId('sib-a'))).toBe(handleA.agent)
expect(harness.ctx.agents.get(AgentId('sib-b'))).toBe(handleB.agent)
await handleA.dispose()
// A is gone — unregistered AND its session removed from the store.
expect(harness.ctx.agents.get(AgentId('sib-a'))).toBeUndefined()
expect(harness.ctx.sessions.get(SessionId('sib-a'))).toBeUndefined()
expect(handleA.agent.status).toBe('disposed')
// B is wholly unaffected.
expect(harness.ctx.agents.get(AgentId('sib-b'))).toBe(handleB.agent)
expect(harness.ctx.sessions.get(SessionId('sib-b'))).toBeDefined()
expect(handleB.agent.status).not.toBe('disposed')
await harness.dispose()
})
it('a throwing agent/disposed listener does not prevent session removal (composite-effect containment)', async () => {
// The AgentHandle teardown folds session-detach, register, and loop-stop
// into ONE composite effect whose disposers run as a `.then()` chain. The
// register disposer emits `agent/disposed`; if a listener throws and the
// emit is UNCONTAINED, the rejected chain skips the LATER session-detach
// disposer — stranding the session in the store with `onAppend` attached (a
// leak AND a durability hole, since the new design relies on detach
// running). The emit must be contained. Register a throwing listener, drive
// a clean turn, dispose, and assert the session was STILL removed.
const harness = await makeBridgeHarness({ storageDir, script: [textResponse('ok')] })
harness.ctx.on('agent/disposed', () => { throw new Error('boom disposed listener') })
const handle = harness.ctx.agents.create({
agentId: AgentId('guard-a'), sessionId: SessionId('guard-a'), agentOptions: { model: 'mock' },
})
handle.agent.send([{ type: 'text', text: 'go' }])
await handle.agent.whenIdle()
expect(harness.ctx.sessions.get(SessionId('guard-a'))).toBeDefined()
// Dispose: the throwing listener must NOT break the chain before detach.
await handle.dispose()
expect(harness.ctx.agents.get(AgentId('guard-a'))).toBeUndefined()
expect(harness.ctx.sessions.get(SessionId('guard-a'))).toBeUndefined() // detach still ran
await harness.dispose()
})
it('concurrent AgentHandle dispose() calls all await the SAME teardown (memoized)', async () => {
// The handle's dispose() must memoize: the underlying cordis effect disposer
// is single-shot, so a second dispose() while the first is mid-teardown would
// otherwise resolve IMMEDIATELY (effect epoch already cleared) — before the
// first call's await agent.done + final flush finished. Every caller must
// observe the same quiescence boundary.
const harness = await makeBridgeHarness({ storageDir, script: ['hang'] })
const handle = harness.ctx.agents.create({
agentId: AgentId('conc-a'), sessionId: SessionId('conc-a'), agentOptions: { model: 'mock' },
})
// Drive a turn that hangs in the model stream, so the loop is mid-turn when
// disposed — its exit runs a final session/flush we can gate to hold the
// teardown observably in-flight.
handle.agent.send([{ type: 'text', text: 'go' }])
await new Promise(r => setTimeout(r, 30))
expect(handle.agent.status).toBe('running')
let releaseFlush!: () => void
const flushGate = new Promise<void>((resolve) => { releaseFlush = resolve })
harness.ctx.on('session/flush', () => flushGate)
// First dispose enters teardown (aborts the hanging step) and blocks in the
// gated final flush.
const first = handle.dispose()
let firstSettled = false
void first.then(() => { firstSettled = true })
await new Promise(r => setTimeout(r, 20))
expect(firstSettled).toBe(false)
// Second dispose MUST await the same in-flight teardown, not resolve early.
const second = handle.dispose()
let secondSettled = false
void second.then(() => { secondSettled = true })
await new Promise(r => setTimeout(r, 20))
expect(secondSettled).toBe(false) // memoized: still pending with the first
// Release the flush; both resolve together and the session is gone.
releaseFlush()
await Promise.all([first, second])
expect(harness.ctx.agents.get(AgentId('conc-a'))).toBeUndefined()
expect(harness.ctx.sessions.get(SessionId('conc-a'))).toBeUndefined()
await harness.dispose()
})
})

View File

@@ -0,0 +1,66 @@
import { afterEach, beforeEach, describe, expect, it } from 'vitest'
import { mkdtemp, rm } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk'
import { AgentId } from '@deepseek-ai/dsh-agent'
import { SessionId } from '@deepseek-ai/dsh-session'
import { makeBridgeHarness, textResponse, type BridgeHarness } from './harness'
describe('acp bridge — demux & config edges', () => {
let storageDir: string
let harness: BridgeHarness | undefined
beforeEach(async () => { storageDir = await mkdtemp(join(tmpdir(), 'acp-edge-')) })
afterEach(async () => {
if (harness) await harness.dispose()
harness = undefined
await rm(storageDir, { recursive: true, force: true })
})
it('ignores events from an agent the bridge does not own (strict id demux)', async () => {
// A second agent created directly on the registry (NOT via the bridge) runs
// a turn. Its session/event + agent/status must NOT produce ACP updates and
// must not settle anything — the bridge demuxes strictly by its own id.
harness = await makeBridgeHarness({ storageDir, script: [textResponse('foreign')] })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
const before = harness.updates.length
const { agent: foreign } = harness.ctx.agents.create({ agentId: AgentId('foreign'), sessionId: SessionId('foreign-session'), agentOptions: { model: 'mock' } })
foreign.send([{ type: 'text', text: 'hi' }])
await foreign.whenIdle()
await new Promise(r => setTimeout(r, 10))
// No update was emitted for the foreign agent's stream.
expect(harness.updates.length).toBe(before)
})
it('survives a session/update that the client rejects (best-effort notify)', async () => {
harness = await makeBridgeHarness({ storageDir, script: [textResponse('ok')] })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
// Make the client reject every update — the bridge's notify() must swallow
// the rejection and the prompt must still settle normally.
harness.onSessionUpdateError = () => { throw new Error('client update rejected') }
const res = await harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] })
expect(res.stopReason).toBe('end_turn')
})
it('accepts session/new with additionalDirectories empty', async () => {
// Exercises the defined-but-empty additionalDirectories branch (length 0 → allowed).
harness = await makeBridgeHarness({ storageDir })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const a = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [], additionalDirectories: [] })
expect(a.sessionId).toBeTruthy()
})
it('rejects non-empty mcpServers until MCP wiring is implemented', async () => {
harness = await makeBridgeHarness({ storageDir })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
await expect(harness.client.newSession({
cwd: process.cwd(),
mcpServers: [{ name: 'fs', command: 'npx', args: ['server'], env: [] }],
})).rejects.toThrow(/mcpServers/)
})
})

View File

@@ -0,0 +1,261 @@
/**
* Shared test fixtures for the ACP bridge specs. A plain module (NOT a
* *.spec.ts) so importing it does not re-register a describe block.
*
* `makeBridgeHarness` builds a full in-memory cordis context (llm + session +
* system-prompt + tools + agents + agent-loop + persistence) with the ACP
* bridge wired to an in-memory transport, plus a `ClientSideConnection` on the
* other end — so a test drives the bridge exactly as an editor would, with no
* subprocess and no real stdio.
*/
import { Context } from 'cordis'
import LlmService, { CallId, type GenerateOptions, type StreamChunk } from '@deepseek-ai/dsh-llm'
import { LlmAdapter } from '@deepseek-ai/dsh-llm'
import SessionStore from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry from '@deepseek-ai/dsh-tools'
import AgentRegistry from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
import * as ToolBash from '@deepseek-ai/dsh-tool-bash'
import {
ClientSideConnection,
ndJsonStream,
type Agent as AcpAgent,
type Client,
type RequestPermissionRequest,
type RequestPermissionResponse,
type SessionNotification,
type Stream,
} from '@agentclientprotocol/sdk'
import * as AcpPlugin from '../src/index'
import { type AcpConfig } from '../src/index'
/** A scripted mock adapter (mirrors the agent-loop test adapter). */
class MockAdapter extends LlmAdapter {
requests: GenerateOptions[] = []
constructor(private script: (StreamChunk[] | 'hang')[]) {
super()
}
async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
this.requests.push(options)
const entry = this.script.shift()
if (!entry) throw new Error('MockAdapter: script exhausted')
if (entry === 'hang') {
yield { type: 'block-start', index: 0, blockType: 'text' }
yield { type: 'text-delta', index: 0, text: 'partial' }
await new Promise<void>((_resolve, reject) => {
if (options.signal?.aborted) { reject(new Error('aborted')); return }
options.signal?.addEventListener('abort', () => { reject(new Error('aborted')) }, { once: true })
})
return
}
for (const chunk of entry) {
if (options.signal?.aborted) throw new Error('aborted')
yield chunk
}
}
}
/** Scripted text response ending in a clean `stop` finish. */
export function textResponse(text: string): StreamChunk[] {
return [
{ type: 'block-start', index: 0, blockType: 'text' },
...Array.from(text, (char): StreamChunk => ({ type: 'text-delta', index: 0, text: char })),
{ type: 'block-end', index: 0, block: { type: 'text', text } },
{ type: 'usage', usage: { inputTokens: 5, outputTokens: text.length } },
{ type: 'finish', reason: { kind: 'stop' } },
]
}
/** Scripted response ending at the output-token ceiling (max-tokens finish). */
export function maxTokensResponse(text: string): StreamChunk[] {
return [
{ type: 'block-start', index: 0, blockType: 'text' },
...Array.from(text, (char): StreamChunk => ({ type: 'text-delta', index: 0, text: char })),
{ type: 'block-end', index: 0, block: { type: 'text', text } },
{ type: 'finish', reason: { kind: 'max-tokens' } },
]
}
/** Scripted response that fails mid-turn with a finish-error chunk. */
export function errorResponse(message: string): StreamChunk[] {
return [
{ type: 'block-start', index: 0, blockType: 'text' },
{ type: 'text-delta', index: 0, text: 'partial' },
{ type: 'finish', reason: { kind: 'error', message, code: 'PROVIDER_ERROR' } },
]
}
/** Scripted single tool call (no follow-up step scripted by default). */
export function toolCallResponse(rawCallId: string, name: string, args: object): StreamChunk[] {
const argumentsJson = JSON.stringify(args)
const id = CallId(rawCallId)
return [
{ type: 'block-start', index: 0, blockType: 'tool-call' },
{ type: 'tool-call-delta', index: 0, id, name, argumentsDelta: argumentsJson },
{ type: 'block-end', index: 0, block: { type: 'tool-call', id, name, arguments: argumentsJson } },
{ type: 'finish', reason: { kind: 'tool-calls' } },
]
}
/** A captured `session/update` notification (the update payload only). */
export type CapturedUpdate = SessionNotification['update']
export interface BridgeHarness {
ctx: Context
client: ClientSideConnection
adapter: MockAdapter
/** Every `session/update` the bridge pushed, in order (payload only). */
updates: CapturedUpdate[]
/** Same, but tagged with each update's `sessionId` (for multi-session demux assertions). */
sessionUpdates: { sessionId: string; update: CapturedUpdate }[]
/** Permission requests the bridge issued (none until the gate lands). */
permissionRequests: RequestPermissionRequest[]
/** Decide each permission request's outcome (default: cancelled). */
onPermission: (req: RequestPermissionRequest) => RequestPermissionResponse
/** If set, the client's sessionUpdate throws this (tests notify error path). */
onSessionUpdateError: (() => void) | undefined
/**
* Sever the client→agent transport (close the writable the agent reads),
* which ends the agent-side stream and resolves the bridge's `conn.closed` —
* simulating an editor disconnecting. Returns once the close is requested.
*/
closeClientTransport: () => Promise<void>
/**
* The child fiber the ACP bridge is mounted in. Disposing it tears down JUST
* the bridge (its `ctx.on` listeners + effect) while the rest of the harness
* stays up — an ACP-only HMR reload.
*/
acpFiber: Awaited<ReturnType<Context['plugin']>>
dispose: () => Promise<void>
storageDir: string
}
/**
* Build the bridge + a connected client over an in-memory transport pair.
*
* Two identity `TransformStream`s cross-wired (agent writes → client reads,
* client writes → agent reads) give a faithful bidirectional JSON-RPC channel.
* The bridge's `apply` receives the agent-side `Stream` via `config.stream`;
* the test holds the `ClientSideConnection`.
*
* Pass `config: { model: undefined }` to override the default `model: 'mock'`
* (the model key is dropped entirely when explicitly undefined).
*/
export async function makeBridgeHarness(options: {
script?: (StreamChunk[] | 'hang')[]
config?: Partial<AcpConfig>
storageDir: string
/**
* Plug the REAL `dsh-bash-local` executor + `dsh-tool-bash` tools (instead of
* a test's own inline tool). Lets a test drive the actual `bash` tool — its
* real `presentCall`/`presentResult` — through the bridge, so tool-call UI
* tests verify the SHIPPING tool, not a stand-in (AGENTS.md "prefer the real
* implementation over a mock in tests").
*/
withBash?: boolean
} = { storageDir: '' }): Promise<BridgeHarness> {
const adapter = new MockAdapter(options.script ?? [])
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(SessionPersistenceJsonl, { root: options.storageDir })
if (options.withBash) {
await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 })
await ctx.plugin(ToolBash)
}
ctx.llm.registerAdapter(['mock'], adapter)
// Two identity byte pipes cross-wired into the two ndJsonStreams: bytes the
// agent writes flow to the client's reader and vice versa. (ndJsonStream
// takes (output, input): the agent writes to a2c and reads from c2a; the
// client writes to c2a and reads from a2c.) The client→agent path (c2a) runs
// through a hand-held writer so a test can close it (`closeClientTransport`)
// to simulate the editor disconnecting — closing it EOFs the agent's reader
// and resolves the bridge's `conn.closed`.
const a2c = new TransformStream<Uint8Array, Uint8Array>()
const c2a = new TransformStream<Uint8Array, Uint8Array>()
const c2aWriter = c2a.writable.getWriter()
// A WritableStream the client writes into; each chunk is forwarded to the
// held c2a writer. `closeClientTransport` closes that writer directly.
const clientOutput = new WritableStream<Uint8Array>({
write: chunk => c2aWriter.write(chunk),
})
const agentStream: Stream = ndJsonStream(a2c.writable, c2a.readable)
const clientStream: Stream = ndJsonStream(clientOutput, a2c.readable)
const updates: CapturedUpdate[] = []
const sessionUpdates: { sessionId: string; update: CapturedUpdate }[] = []
const permissionRequests: RequestPermissionRequest[] = []
const harness: BridgeHarness = {
ctx,
adapter,
updates,
sessionUpdates,
permissionRequests,
onPermission: () => ({ outcome: { outcome: 'cancelled' } }),
onSessionUpdateError: undefined,
client: undefined as unknown as ClientSideConnection,
acpFiber: undefined as unknown as BridgeHarness['acpFiber'],
// Close the writable the CLIENT writes to (c2a) — its readable, which the
// agent's ndJsonStream consumes, then EOFs cleanly, so the bridge's
// `conn.closed` resolves and it sees the client disconnect. If the client
// connection holds a writer lock on it, abort the connection's signal path
// instead by closing through the underlying stream.
closeClientTransport: async () => { await c2aWriter.close() },
dispose: async () => { await ctx.fiber.dispose() },
storageDir: options.storageDir,
}
const makeClient = (_agent: AcpAgent): Client => ({
sessionUpdate(params: SessionNotification): Promise<void> {
updates.push(params.update)
sessionUpdates.push({ sessionId: params.sessionId, update: params.update })
// Let a test force the bridge's notify() error path.
if (harness.onSessionUpdateError) return Promise.reject(new Error('client update rejected'))
return Promise.resolve()
},
requestPermission(params: RequestPermissionRequest): Promise<RequestPermissionResponse> {
permissionRequests.push(params)
return Promise.resolve(harness.onPermission(params))
},
})
// Wire the bridge (agent side) and the client (test side). The test config
// can override `model` (including to undefined): default to 'mock' unless the
// caller explicitly set the key (even to undefined), so a `{ model: undefined }`
// override means "no model at all".
const cfg: AcpConfig = { stream: agentStream, ...options.config }
if (!(options.config && 'model' in options.config)) cfg.model = 'mock'
// Mount the bridge the way production does: as a cordis PLUGIN (via
// `ctx.plugin` with the real `inject`), NOT `AcpPlugin.apply(ctx, cfg)`
// directly on the root ctx. The plugin fiber is the faithful reproduction —
// the bridge's `apply` runs inside the fiber's injection scope, and its ACP
// handlers later run from the JSON-RPC read loop OUTSIDE that scope, exactly
// as under the example's cordis.yml. (Mounting directly on root made every
// service an ungated property and hid the "cannot get property … without
// inject" failure that bit a real Zed session.) `harness.acpFiber.dispose()`
// tears down JUST the bridge (its listeners + effect) for the HMR test.
harness.acpFiber = await ctx.plugin({
name: 'acp-test',
// Use the bridge's REAL exported `inject` so this never drifts from the
// plugin's actual dependency list (adding a service to the bridge must not
// require editing the harness — a hardcoded list silently broke when `tools`
// was added). The bridge programs against the interface packages only.
inject: [...AcpPlugin.inject],
apply: (inner: Context) => { AcpPlugin.apply(inner, cfg) },
})
harness.client = new ClientSideConnection(makeClient, clientStream)
return harness
}

View File

@@ -0,0 +1,238 @@
import { afterEach, beforeEach, describe, expect, it } from 'vitest'
import { mkdtemp, rm } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk'
import { SESSION_FORMAT_VERSION, SessionId } from '@deepseek-ai/dsh-session'
import { AgentId } from '@deepseek-ai/dsh-agent'
import { makeBridgeHarness, textResponse, toolCallResponse, type BridgeHarness, type CapturedUpdate } from './harness'
/** Concatenate the text of all agent_message_chunk updates. */
function messageText(updates: CapturedUpdate[]): string {
return updates
.filter(u => u.sessionUpdate === 'agent_message_chunk')
.map(u => (u.content.type === 'text' ? u.content.text : ''))
.join('')
}
describe('acp bridge — session/load replay', () => {
let storageDir: string
let live: BridgeHarness | undefined
let loader: BridgeHarness | undefined
beforeEach(async () => { storageDir = await mkdtemp(join(tmpdir(), 'acp-load-')) })
afterEach(async () => {
if (live) await live.dispose()
if (loader) await loader.dispose()
live = loader = undefined
await rm(storageDir, { recursive: true, force: true })
})
it('replays a persisted turn from the event log as session/update on load', async () => {
// 1. Create a session and run one turn — persistence writes the event log.
live = await makeBridgeHarness({ storageDir, script: [textResponse('remembered answer')] })
await live.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const { sessionId } = await live.client.newSession({ cwd: process.cwd(), mcpServers: [] })
await live.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'remember this' }] })
// Dispose to flush + release; the on-disk log persists.
await live.dispose()
live = undefined
// 2. A fresh bridge loads the same session id and must replay the turn.
loader = await makeBridgeHarness({ storageDir, script: [] })
await loader.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const res = await loader.client.loadSession({ sessionId, cwd: process.cwd(), mcpServers: [] })
expect(res).toBeDefined()
// The replayed updates reconstruct the assistant text from the event log
// (assistant/chunk → agent_message_chunk), NOT from deriveMessages.
expect(messageText(loader.updates)).toBe('remembered answer')
// And the USER side of the turn replays too (user/message →
// user_message_chunk), so the editor transcript shows both sides.
const userText = loader.updates
.filter(u => u.sessionUpdate === 'user_message_chunk')
.map(u => (u.content.type === 'text' ? u.content.text : ''))
.join('')
expect(userText).toBe('remember this')
})
it('replays a persisted tool call with the TOOL-OWNED presentation (title/rawInput/console output)', async () => {
// A turn with a REAL bash tool call is persisted, then loaded by a fresh
// bridge. The replayed tool_call/tool_call_update must carry the tool's OWN
// presentation — identical to how it streamed live — via a throwaway
// presenter that pairs call→result as the log replays in order. Uses the
// shipping tool (withBash), not a stand-in (AGENTS.md "prefer the real
// implementation over a mock in tests").
live = await makeBridgeHarness({
storageDir,
withBash: true,
script: [toolCallResponse('c1', 'bash', { command: 'echo hello', description: 'Print a greeting' }), textResponse('done')],
})
await live.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const { sessionId } = await live.client.newSession({ cwd: process.cwd(), mcpServers: [] })
await live.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'greet' }] })
await live.dispose()
live = undefined
// A fresh bridge — also with the real bash tool, since the presentation is
// resolved from the live registry at replay time — loads the session.
loader = await makeBridgeHarness({ storageDir, withBash: true, script: [] })
await loader.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
await loader.client.loadSession({ sessionId, cwd: process.cwd(), mcpServers: [] })
const call = loader.updates.find(u => u.sessionUpdate === 'tool_call')
expect(call).toMatchObject({ toolCallId: 'c1', title: 'echo hello', kind: 'execute', rawInput: 'echo hello' })
if (call?.sessionUpdate !== 'tool_call') throw new Error('expected a tool_call')
// Capability OFF on this loader: the description renders as a content block, no terminal block.
expect(call.content).toEqual([{ type: 'content', content: { type: 'text', text: 'Print a greeting' } }])
const update = loader.updates.find(u => u.sessionUpdate === 'tool_call_update')
expect(update?.sessionUpdate).toBe('tool_call_update')
if (update?.sessionUpdate !== 'tool_call_update') throw new Error('expected a tool_call_update')
expect(update).toMatchObject({ toolCallId: 'c1', status: 'completed' })
const content = update.content as { content: { text: string } }[]
expect(content[0]?.content.text).toBe('```console\nhello\n```')
})
it('replays a persisted bash call as a TERMINAL card when the loader advertises the capability', async () => {
// The presentation is resolved at replay time, so a loader that advertised
// _meta.terminal_output must reconstruct the terminal card (content + _meta)
// from the persisted log — identical to how it would have streamed live.
live = await makeBridgeHarness({
storageDir,
withBash: true,
script: [toolCallResponse('c1', 'bash', { command: 'echo hi', description: 'Greet' }), textResponse('done')],
})
await live.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const { sessionId } = await live.client.newSession({ cwd: process.cwd(), mcpServers: [] })
await live.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'greet' }] })
await live.dispose()
live = undefined
loader = await makeBridgeHarness({ storageDir, withBash: true, script: [] })
await loader.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: { _meta: { terminal_output: true } } })
await loader.client.loadSession({ sessionId, cwd: process.cwd(), mcpServers: [] })
const call = loader.updates.find(u => u.sessionUpdate === 'tool_call')
if (call?.sessionUpdate !== 'tool_call') throw new Error('expected a tool_call')
// Replay reconstructs the terminal card: description block, then terminal block.
expect(call.content).toEqual([
{ type: 'content', content: { type: 'text', text: 'Greet' } },
{ type: 'terminal', terminalId: 'c1' },
])
expect((call._meta as { terminal_info?: unknown }).terminal_info).toEqual({ terminal_id: 'c1', cwd: process.cwd() })
const update = loader.updates.find(u => u.sessionUpdate === 'tool_call_update')
if (update?.sessionUpdate !== 'tool_call_update') throw new Error('expected a tool_call_update')
// Terminal mode: content omitted, output + exit on _meta — matching live.
expect(update.content).toBeUndefined()
const meta = update._meta as { terminal_output?: { data: string }; terminal_exit?: { exit_code?: number } }
expect(meta.terminal_output?.data).toBe('hi\n')
expect(meta.terminal_exit?.exit_code).toBe(0)
})
it('a load whose resume finishes after a client disconnect leaks no live session', async () => {
// A session/load is mid-resume() when the client transport closes. The load
// must NOT end up with a live registered agent for the connection that is
// already gone. (The bridge's post-await `closed` guard backs this on real
// stdio; here the SDK rejects the in-flight request on close — either way no
// agent survives.) Stall persistence so resume() is pending across the close.
live = await makeBridgeHarness({ storageDir, script: [textResponse('x')] })
await live.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const { sessionId } = await live.client.newSession({ cwd: process.cwd(), mcpServers: [] })
await live.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'hi' }] })
await live.dispose()
live = undefined
loader = await makeBridgeHarness({ storageDir, script: [] })
await loader.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const realLoad = loader.ctx.sessionPersistence.load.bind(loader.ctx.sessionPersistence)
let release!: () => void
const gate = new Promise<void>((r) => { release = r })
loader.ctx.sessionPersistence.load = async (id) => { await gate; return realLoad(id) }
const loadResult = loader.client.loadSession({ sessionId, cwd: process.cwd(), mcpServers: [] })
.then(() => 'resolved' as const, () => 'rejected' as const)
await loader.closeClientTransport() // teardown sets `closed` while load is gated
release() // resume() finishes AFTER teardown
expect(await loadResult).toBe('rejected')
// No live agent was installed for the closed connection.
expect(loader.ctx.agents.get(AgentId(sessionId))).toBeUndefined()
})
it('rejects load when the requested cwd does not match the persisted session cwd', async () => {
// Seed a session on disk whose header.cwd is a DIFFERENT absolute path than
// the server's launch dir. The bridge must LOAD it (per-session cwd is
// honored — the resumed session keeps header.cwd, and bash routes there), no
// longer reject on a mismatch.
loader = await makeBridgeHarness({ storageDir, script: [] })
const otherCwd = '/some/other/workspace'
await loader.ctx.sessionPersistence.create({
version: SESSION_FORMAT_VERSION, id: SessionId('elsewhere'), createdAt: 1, cwd: otherCwd,
})
await loader.ctx.sessionPersistence.append(SessionId('elsewhere'), [
{ type: 'turn/start', seq: 0, time: 0, data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } } },
{ type: 'turn/end', seq: 1, time: 0, data: { turn: 1, reason: { kind: 'completed' } } },
])
await loader.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
await expect(loader.client.loadSession({ sessionId: 'elsewhere', cwd: process.cwd(), mcpServers: [] }))
.rejects.toThrow(/cwd mismatch/)
expect(loader.ctx.agents.get(AgentId('elsewhere'))).toBeUndefined()
const res = await loader.client.loadSession({ sessionId: 'elsewhere', cwd: `${otherCwd}/.`, mcpServers: [] })
expect(res).toBeDefined()
expect(loader.ctx.agents.get(AgentId('elsewhere'))!.session.header.cwd).toBe(otherCwd)
})
it('rejects load for a non-absolute cwd (still required to be absolute)', async () => {
loader = await makeBridgeHarness({ storageDir, script: [] })
await loader.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
await expect(loader.client.loadSession({ sessionId: 's', cwd: 'rel', mcpServers: [] }))
.rejects.toThrow(/absolute/)
})
it('lets persistence reject a load for an unknown id after metadata lookup misses', async () => {
loader = await makeBridgeHarness({ storageDir, script: [] })
await loader.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
await expect(loader.client.loadSession({ sessionId: 'missing', cwd: process.cwd(), mcpServers: [] }))
.rejects.toThrow(/Internal error/)
})
it('rejects loading a persisted session that has NO cwd (would silently run in the launch dir)', async () => {
// A legacy / externally-created session log with no header.cwd. The bridge
// must reject the load rather than accept it and let bash silently fall back
// to the server's launch dir (the request cwd does not override the header).
loader = await makeBridgeHarness({ storageDir, script: [] })
await loader.ctx.sessionPersistence.create({
version: SESSION_FORMAT_VERSION, id: SessionId('legacy'), createdAt: 1, // no cwd
})
await loader.ctx.sessionPersistence.append(SessionId('legacy'), [
{ type: 'turn/start', seq: 0, time: 0, data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } } },
{ type: 'turn/end', seq: 1, time: 0, data: { turn: 1, reason: { kind: 'completed' } } },
])
await loader.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
await expect(loader.client.loadSession({ sessionId: 'legacy', cwd: process.cwd(), mcpServers: [] }))
.rejects.toThrow(/no absolute persisted cwd/)
// Rejected BEFORE resume (metadata-only check) — no agent was registered, so
// the id is not wedged: a later attempt hits the same clean rejection, not a
// duplicate-registration error.
expect(loader.ctx.agents.get(AgentId('legacy'))).toBeUndefined()
await expect(loader.client.loadSession({ sessionId: 'legacy', cwd: process.cwd(), mcpServers: [] }))
.rejects.toThrow(/no absolute persisted cwd/)
})
it('allows loading alongside an existing session but rejects re-loading the SAME id', async () => {
// Multi-session: a load can coexist with a live session, but loading an id
// that is already live is rejected (it is already loaded).
live = await makeBridgeHarness({ storageDir, script: [textResponse('one')] })
await live.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const { sessionId } = await live.client.newSession({ cwd: process.cwd(), mcpServers: [] })
await live.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'hi' }] })
// A different new session coexists.
const other = await live.client.newSession({ cwd: process.cwd(), mcpServers: [] })
expect(other.sessionId).not.toBe(sessionId)
// Re-loading the already-live id is rejected.
await expect(live.client.loadSession({ sessionId, cwd: process.cwd(), mcpServers: [] }))
.rejects.toThrow(/already loaded/)
})
})

View File

@@ -0,0 +1,129 @@
import { afterEach, beforeEach, describe, expect, it } from 'vitest'
import { mkdtemp, rm } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk'
import { AgentId } from '@deepseek-ai/dsh-agent'
import { makeBridgeHarness, textResponse, type BridgeHarness, type CapturedUpdate } from './harness'
/** Text of the agent_message_chunk updates scoped to one session id. */
function messageTextFor(updates: { sessionId?: string; update: CapturedUpdate }[], sessionId: string): string {
return updates
.filter(u => u.sessionId === sessionId && u.update.sessionUpdate === 'agent_message_chunk')
.map(u => (u.update.sessionUpdate === 'agent_message_chunk' && u.update.content.type === 'text' ? u.update.content.text : ''))
.join('')
}
describe('acp bridge — RFC 011 multi-session isolation', () => {
let storageDir: string
let harness: BridgeHarness | undefined
beforeEach(async () => { storageDir = await mkdtemp(join(tmpdir(), 'acp-multi-')) })
afterEach(async () => {
if (harness) await harness.dispose()
harness = undefined
await rm(storageDir, { recursive: true, force: true })
})
it('two sessions stream concurrently without interleaving their updates', async () => {
// Each session's prompt answer must arrive only on its own sessionId. The
// scripted adapter answers in send order; both prompts run, and the bridge
// demuxes every chunk by session id.
harness = await makeBridgeHarness({ storageDir, script: [textResponse('answer-A'), textResponse('answer-B')] })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const a = (await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })).sessionId
const b = (await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })).sessionId
const [ra, rb] = await Promise.all([
harness.client.prompt({ sessionId: a, prompt: [{ type: 'text', text: 'go A' }] }),
harness.client.prompt({ sessionId: b, prompt: [{ type: 'text', text: 'go B' }] }),
])
expect(ra.stopReason).toBe('end_turn')
expect(rb.stopReason).toBe('end_turn')
// A's text landed only on A; B's only on B (strict id demux, no interleave).
expect(messageTextFor(harness.sessionUpdates, a)).toContain('answer-A')
expect(messageTextFor(harness.sessionUpdates, a)).not.toContain('answer-B')
expect(messageTextFor(harness.sessionUpdates, b)).toContain('answer-B')
expect(messageTextFor(harness.sessionUpdates, b)).not.toContain('answer-A')
})
it('cancel in one session leaves the other session untouched', async () => {
// Session A hangs; session B completes normally. Cancelling A settles ONLY
// A as cancelled and never disturbs B's stream or result.
harness = await makeBridgeHarness({ storageDir, script: ['hang', textResponse('B done')] })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const a = (await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })).sessionId
const b = (await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })).sessionId
const aPromise = harness.client.prompt({ sessionId: a, prompt: [{ type: 'text', text: 'hang A' }] })
await new Promise(r => setTimeout(r, 30))
await harness.client.cancel({ sessionId: a })
expect((await aPromise).stopReason).toBe('cancelled')
// B runs to completion, unaffected by A's cancel.
const rb = await harness.client.prompt({ sessionId: b, prompt: [{ type: 'text', text: 'go B' }] })
expect(rb.stopReason).toBe('end_turn')
expect(messageTextFor(harness.sessionUpdates, b)).toContain('B done')
})
it('enforces one in-flight prompt PER session independently', async () => {
harness = await makeBridgeHarness({ storageDir, script: ['hang', 'hang'] })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const a = (await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })).sessionId
const b = (await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })).sessionId
// One in-flight prompt in EACH session is allowed (independent limits).
const aPromise = harness.client.prompt({ sessionId: a, prompt: [{ type: 'text', text: 'one A' }] })
const bPromise = harness.client.prompt({ sessionId: b, prompt: [{ type: 'text', text: 'one B' }] })
await new Promise(r => setTimeout(r, 30))
// A second prompt in A is rejected, but B's in-flight prompt is unaffected.
await expect(harness.client.prompt({ sessionId: a, prompt: [{ type: 'text', text: 'two A' }] }))
.rejects.toThrow(/already in flight/)
await harness.client.cancel({ sessionId: a })
await harness.client.cancel({ sessionId: b })
expect((await aPromise).stopReason).toBe('cancelled')
expect((await bPromise).stopReason).toBe('cancelled')
})
it('a cancel for a non-existent session id is a silent no-op (does not touch others)', async () => {
harness = await makeBridgeHarness({ storageDir, script: [textResponse('A done')] })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const a = (await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })).sessionId
await expect(harness.client.cancel({ sessionId: 'ghost' })).resolves.toBeUndefined()
// A still works after a cancel for an unknown id.
const ra = await harness.client.prompt({ sessionId: a, prompt: [{ type: 'text', text: 'go A' }] })
expect(ra.stopReason).toBe('end_turn')
})
it('disposing the whole bridge drains all live sessions to quiescence', async () => {
harness = await makeBridgeHarness({ storageDir, script: ['hang', 'hang'] })
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
const a = (await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })).sessionId
const b = (await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })).sessionId
const agentA = harness.ctx.agents.get(AgentId(a))!
const agentB = harness.ctx.agents.get(AgentId(b))!
// Wait deterministically for BOTH agents to enter `running` (not a fixed
// sleep — agent startup latency is unbounded on a loaded worker).
const running = (agent: typeof agentA) => agent.status === 'running'
? Promise.resolve()
: new Promise<void>((resolve) => {
const dispose = harness!.ctx.on('agent/status', (subject, status) => {
if (subject === agent && status === 'running') { dispose(); resolve() }
})
})
void harness.client.prompt({ sessionId: a, prompt: [{ type: 'text', text: 'go A' }] }).catch(() => {})
void harness.client.prompt({ sessionId: b, prompt: [{ type: 'text', text: 'go B' }] }).catch(() => {})
await Promise.all([running(agentA), running(agentB)])
expect(agentA.status).toBe('running')
expect(agentB.status).toBe('running')
await harness.ctx.fiber.dispose()
// BOTH agents drained (not still running) — teardown reached quiescence
// across all sessions, not just one.
expect(agentA.status).not.toBe('running')
expect(agentB.status).not.toBe('running')
})
})

View File

@@ -0,0 +1,120 @@
/**
* Property-based protocol-shape tests for the ACP update stream (RFC 001 →
* ADR 0013 precedent). Fuzz arbitrary harness `SessionEvent` sequences through
* the pure `streamSessionEventUpdate` translator and assert the invariants an
* ACP client relies on:
*
* - every emitted update is a legal `SessionUpdate` variant;
* - a `tool_call_update` for a given id is never emitted before a `tool_call`
* for that id (the client must see the pending call before its completion);
* - the translator is a pure function of the event (same event → same updates),
* so live streaming and `session/load` replay produce identical streams.
*
* Pure-function fuzzing (no live loop) keeps these deterministic — a failure is
* a real finding, not timing noise.
*/
import { describe, expect, it } from 'vitest'
import fc from 'fast-check'
import { CallId } from '@deepseek-ai/dsh-llm'
import { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session'
import type { SessionNotification } from '@agentclientprotocol/sdk'
import { streamSessionEventUpdate } from '../src/index'
const LEGAL_UPDATE_KINDS = new Set([
'agent_message_chunk',
'agent_thought_chunk',
'tool_call',
'tool_call_update',
])
/**
* Build a WELL-FORMED harness event sequence: a list of "actions" where a tool
* result can only reference a call already opened earlier. This mirrors what
* the loop actually appends (tool/call always precedes its tool/result), so the
* ordering invariant is asserted over realistic logs, not arbitrary noise.
*/
type Action =
| { kind: 'text'; text: string }
| { kind: 'reasoning'; text: string }
| { kind: 'call'; id: string; name: string }
| { kind: 'result'; idx: number; isError: boolean }
| { kind: 'ignored' }
function actionsArb(): fc.Arbitrary<Action[]> {
const action: fc.Arbitrary<Action> = fc.oneof(
fc.string().map((text): Action => ({ kind: 'text', text })),
fc.string().map((text): Action => ({ kind: 'reasoning', text })),
fc.record({ id: fc.string({ minLength: 1 }), name: fc.string() }).map(({ id, name }): Action => ({ kind: 'call', id, name })),
fc.record({ idx: fc.nat(), isError: fc.boolean() }).map(({ idx, isError }): Action => ({ kind: 'result', idx, isError })),
fc.constant<Action>({ kind: 'ignored' }),
)
return fc.array(action, { maxLength: 30 })
}
/** Lower well-formed actions into a harness event sequence. */
function actionsToEvents(actions: Action[]): SessionEvent[] {
const events: SessionEvent[] = []
const openCalls: string[] = []
for (const a of actions) {
switch (a.kind) {
case 'text':
events.push({ type: 'assistant/chunk', seq: 0, time: 0, data: { turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: a.text } } })
break
case 'reasoning':
events.push({ type: 'assistant/chunk', seq: 0, time: 0, data: { turn: 1, step: 1, chunk: { type: 'reasoning-delta', index: 0, text: a.text } } })
break
case 'call':
openCalls.push(a.id)
events.push({ type: 'tool/call', seq: 0, time: 0, data: { turn: 1, step: 1, callId: CallId(a.id), name: a.name, arguments: '{}' } })
break
case 'result': {
// Only emit a result for an already-opened call (well-formedness).
if (openCalls.length === 0) break
const id = openCalls[a.idx % openCalls.length]!
events.push({ type: 'tool/result', seq: 0, time: 0, data: { turn: 1, step: 1, callId: CallId(id), content: [], isError: a.isError } })
break
}
case 'ignored':
events.push({ type: 'turn/end', seq: 0, time: 0, data: { turn: 1, reason: { kind: 'completed' } } })
break
}
}
return events
}
function runStream(events: SessionEvent[]): SessionNotification['update'][] {
const out: SessionNotification['update'][] = []
for (const event of events) streamSessionEventUpdate(SessionId('s1'), event, n => out.push(n.update))
return out
}
describe('ACP update-stream invariants (property-based)', () => {
it('every emitted update is a legal SessionUpdate variant', () => {
fc.assert(fc.property(actionsArb(), (actions) => {
for (const update of runStream(actionsToEvents(actions))) {
expect(LEGAL_UPDATE_KINDS.has(update.sessionUpdate)).toBe(true)
}
}))
})
it('never emits a tool_call_update for an id before that id\'s tool_call', () => {
fc.assert(fc.property(actionsArb(), (actions) => {
const seenCall = new Set<string>()
for (const update of runStream(actionsToEvents(actions))) {
if (update.sessionUpdate === 'tool_call') {
seenCall.add(update.toolCallId)
} else if (update.sessionUpdate === 'tool_call_update') {
expect(seenCall.has(update.toolCallId)).toBe(true)
}
}
}))
})
it('is a pure function of the event (replay equals live)', () => {
fc.assert(fc.property(actionsArb(), (actions) => {
const events = actionsToEvents(actions)
expect(runStream(events)).toEqual(runStream(events))
}))
})
})

View File

@@ -0,0 +1,415 @@
import { describe, expect, it } from 'vitest'
import { CallId } from '@deepseek-ai/dsh-llm'
import { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session'
import type { SessionNotification } from '@agentclientprotocol/sdk'
import type { ToolDefinition, ToolRegistry } from '@deepseek-ai/dsh-tools'
import { streamSessionEventUpdate, agentOptions, ToolPresenter } from '../src/index'
/** Collect the updates a single event produces (no presenter → generic fallback). */
function updatesFor(event: SessionEvent): SessionNotification['update'][] {
const out: SessionNotification['update'][] = []
streamSessionEventUpdate(SessionId('s1'), event, n => out.push(n.update))
return out
}
/** Collect the updates emitted by the live prompt stream (user echo suppressed). */
function liveUpdatesFor(event: SessionEvent): SessionNotification['update'][] {
const out: SessionNotification['update'][] = []
streamSessionEventUpdate(SessionId('s1'), event, n => out.push(n.update), undefined, undefined, { includeUserMessages: false })
return out
}
/** A tiny tool registry stub exposing just `get` for {@link ToolPresenter}. */
function registryOf(...tools: ToolDefinition[]): Pick<ToolRegistry, 'get'> {
const map = new Map(tools.map(t => [t.name, t]))
return { get: name => map.get(name) }
}
function evt<T extends SessionEvent['type']>(type: T, data: Extract<SessionEvent, { type: T }>['data']): SessionEvent {
return { type, seq: 0, time: 0, data } as SessionEvent
}
describe('streamSessionEventUpdate', () => {
it('maps assistant/chunk text-delta to agent_message_chunk', () => {
expect(updatesFor(evt('assistant/chunk', { turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: 'hi' } })))
.toEqual([{ sessionUpdate: 'agent_message_chunk', content: { type: 'text', text: 'hi' } }])
})
it('maps assistant/chunk reasoning-delta to agent_thought_chunk', () => {
expect(updatesFor(evt('assistant/chunk', { turn: 1, step: 1, chunk: { type: 'reasoning-delta', index: 0, text: 'mm' } })))
.toEqual([{ sessionUpdate: 'agent_thought_chunk', content: { type: 'text', text: 'mm' } }])
})
it('produces no update for a non-text/reasoning chunk (e.g. block-start)', () => {
expect(updatesFor(evt('assistant/chunk', { turn: 1, step: 1, chunk: { type: 'block-start', index: 0, blockType: 'text' } })))
.toEqual([])
})
it('maps tool/call to an in_progress tool_call with inferred kind and parsed rawInput (generic fallback, no presenter)', () => {
const updates = updatesFor(evt('tool/call', { turn: 1, step: 1, callId: CallId('c1'), name: 'bash', arguments: '{"command":"ls"}' }))
expect(updates).toEqual([{
sessionUpdate: 'tool_call',
toolCallId: 'c1',
title: 'bash',
kind: 'execute',
status: 'in_progress',
rawInput: { command: 'ls' },
}])
})
it('infers tool kinds: read*/write*/edit*/other', () => {
const kind = (name: string): unknown =>
updatesFor(evt('tool/call', { turn: 1, step: 1, callId: CallId('c'), name, arguments: '' }))[0]
expect((kind('read_file') as { kind: string }).kind).toBe('read')
expect((kind('write') as { kind: string }).kind).toBe('edit')
expect((kind('edit_file') as { kind: string }).kind).toBe('edit')
expect((kind('frobnicate') as { kind: string }).kind).toBe('other')
})
it('falls back to the raw argument string when tool arguments are not JSON', () => {
const update = updatesFor(evt('tool/call', { turn: 1, step: 1, callId: CallId('c1'), name: 'bash', arguments: 'not json' }))[0]
expect((update as { rawInput: unknown }).rawInput).toBe('not json')
})
it('maps tool/result to completed/failed tool_call_update with text content', () => {
const ok = updatesFor(evt('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'out' }], isError: false }))
expect(ok).toEqual([{
sessionUpdate: 'tool_call_update',
toolCallId: 'c1',
status: 'completed',
content: [{ type: 'content', content: { type: 'text', text: 'out' } }],
}])
const failed = updatesFor(evt('tool/result', { turn: 1, step: 1, callId: CallId('c2'), content: [], isError: true }))
expect((failed[0] as { status: string }).status).toBe('failed')
})
it('drops non-text tool-result content (text-only)', () => {
const update = updatesFor(evt('tool/result', {
turn: 1, step: 1, callId: CallId('c1'),
content: [{ type: 'image', url: 'https://x/y.png' }],
isError: false,
}))[0]
expect((update as { content: unknown[] }).content).toEqual([])
})
it('maps user/message text blocks to user_message_chunk (load replays the user side)', () => {
// A text block surfaces; a non-text block (here a tool-call) is skipped, so
// only the text chunk is emitted.
expect(updatesFor(evt('user/message', {
content: [
{ type: 'text', text: 'hi' },
{ type: 'tool-call', id: CallId('c'), name: 'bash', arguments: '{}' },
],
source: { kind: 'user' },
}))).toEqual([{ sessionUpdate: 'user_message_chunk', content: { type: 'text', text: 'hi' } }])
// A user/message with no text-bearing blocks produces no chunk.
expect(updatesFor(evt('user/message', { content: [], source: { kind: 'user' } }))).toEqual([])
})
it('can suppress user/message chunks for live prompt turns', () => {
expect(liveUpdatesFor(evt('user/message', {
content: [{ type: 'text', text: 'hi' }],
source: { kind: 'user' },
}))).toEqual([])
})
it('produces no update for boundary/other event types', () => {
expect(updatesFor(evt('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }))).toEqual([])
expect(updatesFor(evt('turn/end', { turn: 1, reason: { kind: 'completed' } }))).toEqual([])
expect(updatesFor(evt('step/start', { turn: 1, step: 1 }))).toEqual([])
})
})
describe('ToolPresenter (tool-owned presentation via the tool registry)', () => {
/** A tool whose presentCall/presentResult mirror what tool-bash declares. */
const bashLike: ToolDefinition = {
name: 'bash',
description: 'run a command',
parameters: {},
execute: async () => [],
presentCall: (args: unknown) => {
const a = args as { command: string; description: string }
return { title: a.description, kind: 'execute', rawInput: a.command }
},
presentResult: (_args: unknown, result: { content: { type: string }[] }) => ({
content: [{ type: 'text', text: `wrapped:${result.content.length}` }],
}),
}
function updatesWith(presenter: ToolPresenter, ...events: SessionEvent[]): SessionNotification['update'][] {
const out: SessionNotification['update'][] = []
for (const event of events) streamSessionEventUpdate(SessionId('s1'), event, n => out.push(n.update), presenter)
return out
}
it('tool/call uses the tool: description→title, command→rawInput, tool kind', () => {
const presenter = new ToolPresenter(registryOf(bashLike))
const [update] = updatesWith(presenter, evt('tool/call', {
turn: 1, step: 1, callId: CallId('c1'), name: 'bash',
arguments: JSON.stringify({ command: 'ls -la', description: 'List files' }),
}))
expect(update).toEqual({
sessionUpdate: 'tool_call',
toolCallId: 'c1',
title: 'List files',
kind: 'execute',
status: 'in_progress',
rawInput: 'ls -la',
})
})
it('tool/result uses the tool to reformat content (resolved by the remembered tool/call)', () => {
const presenter = new ToolPresenter(registryOf(bashLike))
const updates = updatesWith(
presenter,
evt('tool/call', { turn: 1, step: 1, callId: CallId('c1'), name: 'bash', arguments: JSON.stringify({ command: 'x', description: 'd' }) }),
evt('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'out' }], isError: false }),
)
expect(updates[1]).toEqual({
sessionUpdate: 'tool_call_update',
toolCallId: 'c1',
status: 'completed',
content: [{ type: 'content', content: { type: 'text', text: 'wrapped:1' } }],
})
})
it('a result with NO preceding call (unknown callId) falls back to the raw content', () => {
const presenter = new ToolPresenter(registryOf(bashLike))
// No tool/call for c9 → presenter has nothing remembered → generic fallback.
const [update] = updatesWith(presenter, evt('tool/result', {
turn: 1, step: 1, callId: CallId('c9'), content: [{ type: 'text', text: 'raw' }], isError: false,
}))
expect(update).toEqual({
sessionUpdate: 'tool_call_update',
toolCallId: 'c9',
status: 'completed',
content: [{ type: 'content', content: { type: 'text', text: 'raw' } }],
})
})
it('a tool with no presentCall/presentResult gets the generic fallback (title = name)', () => {
const plain: ToolDefinition = { name: 'plain', description: 'p', parameters: {}, execute: async () => [] }
const presenter = new ToolPresenter(registryOf(plain))
const [update] = updatesWith(presenter, evt('tool/call', {
turn: 1, step: 1, callId: CallId('c1'), name: 'plain', arguments: '{"a":1}',
}))
expect(update).toMatchObject({ title: 'plain', kind: 'other', rawInput: { a: 1 } })
})
it('a presentation that omits kind/content/rawInput uses the defaults (kind other, raw result content kept)', () => {
// A minimal tool-owned presentation: presentCall returns only a title (no
// kind → defaults to `other`, no rawInput → omitted); presentResult returns
// only a title (no content → the raw result content is kept).
const minimal: ToolDefinition = {
name: 'mini',
description: 'm',
parameters: {},
execute: async () => [],
presentCall: () => ({ title: 'Doing a thing' }),
presentResult: () => ({ title: 'Did the thing' }),
}
const presenter = new ToolPresenter(registryOf(minimal))
const updates = updatesWith(
presenter,
evt('tool/call', { turn: 1, step: 1, callId: CallId('c1'), name: 'mini', arguments: '{}' }),
evt('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'kept' }], isError: false }),
)
// No kind → 'other'; no rawInput key at all.
expect(updates[0]).toEqual({ sessionUpdate: 'tool_call', toolCallId: 'c1', title: 'Doing a thing', kind: 'other', status: 'in_progress' })
// Title replaced; content falls back to the raw result content.
expect(updates[1]).toEqual({
sessionUpdate: 'tool_call_update',
toolCallId: 'c1',
status: 'completed',
content: [{ type: 'content', content: { type: 'text', text: 'kept' } }],
title: 'Did the thing',
})
})
it('holds ONLY in-flight calls: the callId entry is removed once its result is presented', () => {
const presenter = new ToolPresenter(registryOf(bashLike))
updatesWith(
presenter,
evt('tool/call', { turn: 1, step: 1, callId: CallId('c1'), name: 'bash', arguments: JSON.stringify({ command: 'x', description: 'd' }) }),
evt('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'o' }], isError: false }),
)
// A SECOND result for the same callId now finds nothing remembered, so it
// falls back to raw content (proving the first result consumed the entry —
// the map does not retain finished calls).
const [late] = updatesWith(presenter, evt('tool/result', {
turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'late' }], isError: false,
}))
expect(late).toMatchObject({ content: [{ type: 'content', content: { type: 'text', text: 'late' } }] })
})
it('a THROWING presentCall/presentResult is contained: generic fallback + onError, never propagates', () => {
// A buggy tool whose display callbacks throw must NOT fail a live turn or a
// session/load replay (AGENTS.md "contain callback exceptions at the
// boundary"). The presenter swallows the throw, reports via onError, and
// falls back to the generic presentation.
const boom: ToolDefinition = {
name: 'boom',
description: 'b',
parameters: {},
execute: async () => [],
presentCall: () => { throw new Error('call boom') },
presentResult: () => { throw new Error('result boom') },
}
const errors: string[] = []
const presenter = new ToolPresenter(registryOf(boom), msg => errors.push(msg))
const updates = updatesWith(
presenter,
evt('tool/call', { turn: 1, step: 1, callId: CallId('c1'), name: 'boom', arguments: '{"a":1}' }),
evt('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'raw' }], isError: false }),
)
// tool/call fell back to title=name, raw args as rawInput.
expect(updates[0]).toMatchObject({ sessionUpdate: 'tool_call', title: 'boom', kind: 'other', rawInput: { a: 1 } })
// tool/result fell back to the raw content.
expect(updates[1]).toMatchObject({ sessionUpdate: 'tool_call_update', content: [{ type: 'content', content: { type: 'text', text: 'raw' } }] })
// Both throws were reported, not propagated.
expect(errors).toHaveLength(2)
expect(errors[0]).toContain('presentCall threw')
expect(errors[1]).toContain('presentResult threw')
})
it('contains a throwing presenter even with the DEFAULT (no-op) onError sink', () => {
// Constructed without an onError sink (the default `() => {}`): a throwing
// presenter is still swallowed and falls back generically — the absence of a
// logger must not turn a display bug into a propagated exception.
const boom: ToolDefinition = {
name: 'boom',
description: 'b',
parameters: {},
execute: async () => [],
presentCall: () => { throw new Error('call boom') },
presentResult: () => { throw new Error('result boom') },
}
const presenter = new ToolPresenter(registryOf(boom))
const updates = updatesWith(
presenter,
evt('tool/call', { turn: 1, step: 1, callId: CallId('c1'), name: 'boom', arguments: '{}' }),
evt('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'raw' }], isError: false }),
)
expect(updates[0]).toMatchObject({ sessionUpdate: 'tool_call', title: 'boom' })
expect(updates[1]).toMatchObject({ sessionUpdate: 'tool_call_update', content: [{ type: 'content', content: { type: 'text', text: 'raw' } }] })
})
})
describe('terminal-card mapping (capability-gated)', () => {
// A tool that asks to render as a terminal — a stand-in for tool-bash's shape,
// letting us drive the bridge's terminal mapping without the real executor.
type CallTerm = { cwd?: string } | undefined
type ResultTerm = { output?: string; exitCode?: number; signal?: string } | undefined
const termTool = (callTerminal: CallTerm, resultTerminal: ResultTerm): ToolDefinition => ({
name: 'bash',
description: 'run a command',
parameters: {},
execute: async () => [],
presentCall: (args: unknown) => ({
title: (args as { command: string }).command,
kind: 'execute',
rawInput: (args as { command: string }).command,
content: [{ type: 'text', text: (args as { description: string }).description }],
...callTerminal !== undefined ? { terminal: callTerminal } : {},
}),
presentResult: () => ({
content: [{ type: 'text', text: 'fallback' }],
...resultTerminal !== undefined ? { terminal: resultTerminal } : {},
}),
})
const callEvent = evt('tool/call', { turn: 1, step: 1, callId: CallId('c1'), name: 'bash', arguments: JSON.stringify({ command: 'echo hi', description: 'Greet' }) })
const resultEvent = evt('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'hi\n' }], isError: false })
function termUpdates(tool: ToolDefinition, enabled: boolean, cwd: string | undefined, ...events: SessionEvent[]): SessionNotification['update'][] {
const presenter = new ToolPresenter(registryOf(tool))
const out: SessionNotification['update'][] = []
for (const event of events) streamSessionEventUpdate(SessionId('s1'), event, n => out.push(n.update), presenter, { enabled, cwd })
return out
}
it('capability ON: description content THEN terminal block; cwd from the session header when the tool gives none', () => {
const [call, update] = termUpdates(termTool({}, { output: 'hi\n', exitCode: 0 }), true, '/work/proj', callEvent, resultEvent)
expect(call).toMatchObject({
sessionUpdate: 'tool_call',
content: [
{ type: 'content', content: { type: 'text', text: 'Greet' } },
{ type: 'terminal', terminalId: 'c1' },
],
_meta: { terminal_info: { terminal_id: 'c1', cwd: '/work/proj' } },
})
// The update OMITS content (it would clobber the terminal block) and carries output + exit.
expect(update).toEqual({
sessionUpdate: 'tool_call_update',
toolCallId: 'c1',
status: 'completed',
_meta: { terminal_output: { terminal_id: 'c1', data: 'hi\n' }, terminal_exit: { terminal_id: 'c1', exit_code: 0 } },
})
})
it('capability ON: an ABSOLUTE tool cwd wins; a RELATIVE one resolves against the session cwd', () => {
const [absCall] = termUpdates(termTool({ cwd: '/explicit/abs' }, { output: 'x' }), true, '/work/proj', callEvent)
expect((absCall as unknown as { _meta: { terminal_info: { cwd: string } } })._meta.terminal_info.cwd).toBe('/explicit/abs')
const [relCall] = termUpdates(termTool({ cwd: 'sub/dir' }, { output: 'x' }), true, '/work/proj', callEvent)
// Relative workdir resolved against the session cwd — the card header matches
// where execution actually ran (tool-bash resolves the same way).
expect((relCall as unknown as { _meta: { terminal_info: { cwd: string } } })._meta.terminal_info.cwd).toBe('/work/proj/sub/dir')
// No session cwd to resolve against → the relative tool cwd is passed through as-is.
const [noSessionCwd] = termUpdates(termTool({ cwd: 'rel/only' }, { output: 'x' }), true, undefined, callEvent)
expect((noSessionCwd as unknown as { _meta: { terminal_info: { cwd: string } } })._meta.terminal_info.cwd).toBe('rel/only')
})
it('capability ON: a signal kill maps to terminal_exit.signal', () => {
const [, update] = termUpdates(termTool({}, { output: 'gone', signal: 'SIGKILL' }), true, '/w', callEvent, resultEvent)
expect((update as unknown as { _meta: { terminal_exit: unknown } })._meta.terminal_exit).toEqual({ terminal_id: 'c1', signal: 'SIGKILL' })
})
it('capability ON: a terminal result with output but NO exit/signal emits terminal_output and NO exit pill', () => {
// A terminal-rendering tool that reports no structured exit (neither exitCode
// nor signal) — the card shows output but no exit pill.
const [, update] = termUpdates(termTool({}, { output: 'partial' }), true, '/w', callEvent, resultEvent)
const meta = (update as unknown as { _meta: { terminal_output?: unknown; terminal_exit?: unknown } })._meta
expect(meta.terminal_output).toEqual({ terminal_id: 'c1', data: 'partial' })
expect(meta.terminal_exit).toBeUndefined()
})
it('capability OFF: no terminal block or _meta; the description content and fenced result still render', () => {
const [call, update] = termUpdates(termTool({}, { output: 'hi\n' }), false, '/work/proj', callEvent, resultEvent)
expect(call).toEqual({
sessionUpdate: 'tool_call',
toolCallId: 'c1',
title: 'echo hi',
kind: 'execute',
status: 'in_progress',
rawInput: 'echo hi',
content: [{ type: 'content', content: { type: 'text', text: 'Greet' } }],
})
expect(update).toEqual({
sessionUpdate: 'tool_call_update',
toolCallId: 'c1',
status: 'completed',
content: [{ type: 'content', content: { type: 'text', text: 'fallback' } }],
})
})
it('orphan guard: a result-side terminal with NO call-side terminal is dropped (no orphan terminal_output)', () => {
// presentCall declares NO terminal, but presentResult returns one — the
// bridge must not emit _meta.terminal_output for a terminal Zed never made.
const [call, update] = termUpdates(termTool(undefined, { output: 'hi\n', exitCode: 0 }), true, '/w', callEvent, resultEvent)
// The call had no terminal → ordinary tool_call (description content, no _meta).
expect((call as { _meta?: unknown })._meta).toBeUndefined()
expect((call as { content: unknown }).content).toEqual([{ type: 'content', content: { type: 'text', text: 'Greet' } }])
// The result falls back to text content; NO terminal _meta.
expect((update as { _meta?: unknown })._meta).toBeUndefined()
expect((update as { content: unknown }).content).toEqual([{ type: 'content', content: { type: 'text', text: 'fallback' } }])
})
})
describe('agentOptions', () => {
it('includes only the fields present in config', () => {
expect(agentOptions({})).toEqual({})
expect(agentOptions({ model: 'm' })).toEqual({ model: 'm' })
expect(agentOptions({ systemPrompt: 'sp' })).toEqual({ systemPrompt: 'sp' })
expect(agentOptions({ model: 'm', systemPrompt: 'sp' })).toEqual({ model: 'm', systemPrompt: 'sp' })
})
})

View File

@@ -0,0 +1,414 @@
import { afterEach, beforeEach, describe, expect, it } from 'vitest'
import { mkdtemp, rm } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { defineTool } from '@deepseek-ai/dsh-tools'
import { AgentId } from '@deepseek-ai/dsh-agent'
import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk'
import {
errorResponse,
makeBridgeHarness,
maxTokensResponse,
textResponse,
toolCallResponse,
type BridgeHarness,
} from './harness'
/** Boilerplate: initialize + create one session, returning its id. */
async function newSession(h: BridgeHarness, clientCapabilities: Record<string, unknown> = {}): Promise<string> {
await h.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities })
const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] })
return sessionId
}
describe('acp bridge — turn outcomes', () => {
let storageDir: string
let harness: BridgeHarness | undefined
beforeEach(async () => { storageDir = await mkdtemp(join(tmpdir(), 'acp-test-')) })
afterEach(async () => {
if (harness) await harness.dispose()
harness = undefined
await rm(storageDir, { recursive: true, force: true })
})
it('maps a max-tokens turn to stopReason max_tokens', async () => {
harness = await makeBridgeHarness({ storageDir, script: [maxTokensResponse('cut off')] })
const sessionId = await newSession(harness)
const res = await harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] })
expect(res.stopReason).toBe('max_tokens')
})
it('rejects the prompt RPC when a turn fails (no misleading end_turn)', async () => {
// ACP has no "error" stop reason; a failed turn must surface as a rejected
// session/prompt, not a normal end_turn that hides the failure from the
// client. The bridge rejects via the turn/end{error} log record.
harness = await makeBridgeHarness({ storageDir, script: [errorResponse('provider boom')] })
const sessionId = await newSession(harness)
await expect(harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }))
.rejects.toThrow(/turn failed: provider boom/)
})
it('streams a tool call as tool_call then tool_call_update', async () => {
harness = await makeBridgeHarness({
storageDir,
script: [toolCallResponse('c1', 'bash', { command: 'echo hi' }), textResponse('done')],
})
harness.ctx.tools.register(defineTool({
name: 'bash',
description: 'run a command',
parameters: { command: { type: 'string' } },
async execute() { return [{ type: 'text', text: 'hi\n' }] },
}))
const sessionId = await newSession(harness)
await harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'run it' }] })
const toolCalls = harness.updates.filter(u => u.sessionUpdate === 'tool_call')
const toolUpdates = harness.updates.filter(u => u.sessionUpdate === 'tool_call_update')
expect(toolCalls).toHaveLength(1)
expect(toolCalls[0]).toMatchObject({ toolCallId: 'c1', title: 'bash', kind: 'execute', status: 'in_progress' })
expect(toolUpdates).toHaveLength(1)
expect(toolUpdates[0]).toMatchObject({ toolCallId: 'c1', status: 'completed' })
// Ordering invariant: the tool_call precedes its tool_call_update.
const callIdx = harness.updates.findIndex(u => u.sessionUpdate === 'tool_call')
const updIdx = harness.updates.findIndex(u => u.sessionUpdate === 'tool_call_update')
expect(callIdx).toBeLessThan(updIdx)
})
it('the REAL bash tool drives the tool-call UI end-to-end: command title + description block + console output', async () => {
// Use the SHIPPING tool (dsh-tool-bash + dsh-bash-local), not an inline
// stand-in, so this verifies the actual presentCall/presentResult the editor
// sees (AGENTS.md "prefer the real implementation over a mock in tests").
// The mock MODEL still scripts the tool call (no real LLM needed), but the
// tool and executor are real: a real `echo` runs and its real output flows
// back through the bridge.
harness = await makeBridgeHarness({
storageDir,
withBash: true,
script: [
toolCallResponse('c1', 'bash', { command: 'echo hello', description: 'Print a greeting' }),
textResponse('done'),
],
})
const sessionId = await newSession(harness)
await harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'greet' }] })
// presentCall: execute kind, title IS the command (an execute card hides
// rawInput, so the command is the title), the description rides as a content
// text block, the command is also rawInput for non-terminal UIs.
const call = harness.updates.find(u => u.sessionUpdate === 'tool_call')
expect(call).toMatchObject({
toolCallId: 'c1',
title: 'echo hello',
kind: 'execute',
rawInput: 'echo hello',
status: 'in_progress',
})
if (call?.sessionUpdate !== 'tool_call') throw new Error('expected a tool_call')
// Capability OFF: the description renders as the only content block (no terminal block).
expect(call.content).toEqual([{ type: 'content', content: { type: 'text', text: 'Print a greeting' } }])
// presentResult: the REAL command output, wrapped in a fenced console block.
const update = harness.updates.find(u => u.sessionUpdate === 'tool_call_update')
expect(update?.sessionUpdate).toBe('tool_call_update')
if (update?.sessionUpdate !== 'tool_call_update') throw new Error('expected a tool_call_update')
expect(update).toMatchObject({ toolCallId: 'c1', status: 'completed' })
const content = update.content as { content: { type: string; text: string } }[]
expect(content[0]?.content.text).toBe('```console\nhello\n```')
// Capability OFF (the default newSession): NO terminal _meta on either update.
expect((call as { _meta?: unknown })._meta).toBeUndefined()
expect((update as { _meta?: unknown })._meta).toBeUndefined()
})
it('with the terminal_output capability ON, a real bash call renders as a TERMINAL card (content + _meta + exit)', async () => {
// Drive the REAL bash tool, and advertise the Zed `_meta.terminal_output`
// capability in initialize. The bridge must then emit the terminal CARD: the
// description content block THEN a terminal content block + `_meta.terminal_info`
// (cwd header) on the call, and `_meta.terminal_output`/`terminal_exit` on the
// result — and OMIT the update's text content (it would clobber the card).
harness = await makeBridgeHarness({
storageDir,
withBash: true,
script: [toolCallResponse('c1', 'bash', { command: 'echo hi', description: 'Greet' }), textResponse('done')],
})
// Capability lives under clientCapabilities._meta.terminal_output.
const sessionId = await newSession(harness, { _meta: { terminal_output: true } })
await harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'greet' }] })
const call = harness.updates.find(u => u.sessionUpdate === 'tool_call')
if (call?.sessionUpdate !== 'tool_call') throw new Error('expected a tool_call')
// The description content block FIRST (renders above the card), then a
// terminal content block keyed by the callId; terminal_info carries the
// session cwd (the bridge fills it from the session header).
expect(call.content).toEqual([
{ type: 'content', content: { type: 'text', text: 'Greet' } },
{ type: 'terminal', terminalId: 'c1' },
])
expect((call._meta as { terminal_info?: unknown }).terminal_info).toEqual({ terminal_id: 'c1', cwd: process.cwd() })
const update = harness.updates.find(u => u.sessionUpdate === 'tool_call_update')
if (update?.sessionUpdate !== 'tool_call_update') throw new Error('expected a tool_call_update')
// In terminal mode the text content is OMITTED (a tool_call_update.content
// REPLACES the call's content — it would clobber the terminal block).
expect(update.content).toBeUndefined()
// Output rides on _meta.terminal_output; the parsed exit on _meta.terminal_exit.
const meta = update._meta as {
terminal_output?: { terminal_id: string; data: string }
terminal_exit?: { terminal_id: string; exit_code?: number; signal?: string }
}
expect(meta.terminal_output).toEqual({ terminal_id: 'c1', data: 'hi\n' })
expect(meta.terminal_exit).toEqual({ terminal_id: 'c1', exit_code: 0 })
})
it('the terminal capability is snapshotted per-session: a later initialize cannot desync a call/result', async () => {
// The session is created with the capability ON. A SECOND initialize then
// turns it OFF at the connection level — but this session keeps its snapshot,
// so its bash call STILL renders as a terminal card (call + result agree).
// Without the snapshot, the result path would re-read the now-OFF capability
// and either clobber the card (content sent) or be inconsistent with the call.
harness = await makeBridgeHarness({
storageDir,
withBash: true,
script: [toolCallResponse('c1', 'bash', { command: 'echo hi', description: 'Greet' }), textResponse('done')],
})
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: { _meta: { terminal_output: true } } })
const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })
// A re-initialize that DROPS the capability after the session exists.
await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
await harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'greet' }] })
const call = harness.updates.find(u => u.sessionUpdate === 'tool_call')
if (call?.sessionUpdate !== 'tool_call') throw new Error('expected a tool_call')
// Still a terminal card (the session's snapshot, not the mutated connection cap).
expect((call._meta as { terminal_info?: unknown }).terminal_info).toBeDefined()
const update = harness.updates.find(u => u.sessionUpdate === 'tool_call_update')
if (update?.sessionUpdate !== 'tool_call_update') throw new Error('expected a tool_call_update')
// The result AGREES with the call: terminal output present, content omitted.
expect(update.content).toBeUndefined()
expect((update._meta as { terminal_output?: unknown }).terminal_output).toBeDefined()
})
it('a throwing tool presenter does not break the turn: the bridge falls back generically', async () => {
// A buggy tool whose presentCall throws must not fail the live turn — the
// bridge's presenter contains the throw (logging via its onError sink) and
// falls back to the generic title=name presentation. Exercises the real
// bridge wiring of the per-session presenter's error sink.
harness = await makeBridgeHarness({
storageDir,
script: [toolCallResponse('c1', 'kaboom', { x: 1 }), textResponse('done')],
})
harness.ctx.tools.register(defineTool({
name: 'kaboom',
description: 'explodes when presented',
parameters: { x: { type: 'number' } },
async execute() { return [{ type: 'text', text: 'ok' }] },
presentCall: () => { throw new Error('present boom') },
}))
const sessionId = await newSession(harness)
const res = await harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] })
expect(res.stopReason).toBe('end_turn') // the turn completed despite the throw
const call = harness.updates.find(u => u.sessionUpdate === 'tool_call')
// Generic fallback: title is the tool name, raw args as rawInput.
expect(call).toMatchObject({ toolCallId: 'c1', title: 'kaboom', kind: 'other', rawInput: { x: 1 } })
const update = harness.updates.find(u => u.sessionUpdate === 'tool_call_update')
expect(update).toMatchObject({ toolCallId: 'c1', status: 'completed' })
})
it('a failing tool yields a failed tool_call_update', async () => {
harness = await makeBridgeHarness({
storageDir,
script: [toolCallResponse('c1', 'bash', { command: 'boom' }), textResponse('ok')],
})
harness.ctx.tools.register(defineTool({
name: 'bash',
description: 'run a command',
parameters: { command: { type: 'string' } },
async execute() { throw new Error('command failed') },
}))
const sessionId = await newSession(harness)
await harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'run it' }] })
const failed = harness.updates.filter(u => u.sessionUpdate === 'tool_call_update' && u.status === 'failed')
expect(failed).toHaveLength(1)
})
it('settles via the log fallback when a prior session/event listener throws (starvation)', async () => {
// A peer session/event listener that runs BEFORE the bridge's listener
// throws on turn/end (prepend: true puts it first). cordis emit stops at the
// throw, so the bridge's session/event listener never sees turn/end and
// cannot settle there. The agent/status idle-fallback must reconcile the
// prompt from the log so the RPC settles instead of hanging.
harness = await makeBridgeHarness({ storageDir, script: [textResponse('answer')] })
harness.ctx.on('session/event', (_s, event) => {
if (event.type === 'turn/end') throw new Error('peer listener boom')
}, { prepend: true })
const sessionId = await newSession(harness)
const res = await harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] })
expect(res.stopReason).toBe('end_turn')
})
it('log fallback REJECTS when the starved turn ended in error', async () => {
// Same starvation as above, but the turn fails: the idle-fallback must
// reject the RPC from the logged turn/end{error}, not resolve.
harness = await makeBridgeHarness({ storageDir, script: [errorResponse('starved boom')] })
harness.ctx.on('session/event', (_s, event) => {
if (event.type === 'turn/end') throw new Error('peer listener boom')
}, { prepend: true })
const sessionId = await newSession(harness)
await expect(harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }))
.rejects.toThrow(/turn failed: starved boom/)
})
it('log fallback infers the owning turn when turn/START capture is starved', async () => {
// A peer listener throws on turn/START (not turn/end): the bridge never
// captures inflight.turn via the live stream. A throwing turn/start listener
// also FAILS the turn (the throw is recorded as the turn's error). Without
// the watermark inference the fallback would resolve `cancelled` (the bug);
// with it, it infers the owning turn from the log and REJECTS from that
// turn's error turn/end. (The model's own error is never reached — the turn
// failed at start — so the rejection carries the listener's failure.)
harness = await makeBridgeHarness({ storageDir, script: [textResponse('never runs')] })
harness.ctx.on('session/event', (_s, event) => {
if (event.type === 'turn/start') throw new Error('peer listener boom on start')
}, { prepend: true })
const sessionId = await newSession(harness)
await expect(harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }))
.rejects.toThrow(/turn failed:/)
})
it('a between-turn injection does not settle the prompt early (message-trigger correlation)', async () => {
// A plugin injects context (a one-shot injection-triggered turn) right after
// the prompt is queued but before the prompt's own message turn runs. The
// bridge must NOT mistake the injection turn's turn/end for the prompt's —
// it correlates only to message-triggered turns. The prompt settles on its
// OWN turn with the real model answer.
harness = await makeBridgeHarness({ storageDir, script: [textResponse('real answer')] })
const sessionId = await newSession(harness)
const agent = harness.ctx.agents.get(AgentId(sessionId))!
// On the queued prompt, synchronously inject a one-shot context turn (idle
// inject writes turn/start{injection} → context/message → turn/end). Fire
// once so it lands between install and the prompt turn.
let injected = false
harness.ctx.on('agent/queued', (subject) => {
if (subject === agent && !injected) {
injected = true
agent.inject([{ type: 'text', text: 'ctx note' }], { source: { kind: 'plugin', plugin: 'test' } })
}
})
const res = await harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] })
expect(res.stopReason).toBe('end_turn')
const text = harness.updates
.filter(u => u.sessionUpdate === 'agent_message_chunk')
.map(u => (u.content.type === 'text' ? u.content.text : ''))
.join('')
expect(text).toContain('real answer')
})
it('rejects a second prompt while one is in flight', async () => {
harness = await makeBridgeHarness({ storageDir, script: ['hang'] })
const sessionId = await newSession(harness)
// Start the first prompt but do NOT await — it hangs in the model stream.
const first = harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'one' }] })
// Give the loop a tick to install the settle + start running.
await new Promise(r => setTimeout(r, 30))
await expect(harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'two' }] }))
.rejects.toThrow(/already in flight/)
// Cancel to settle the first so the harness disposes cleanly.
await harness.client.cancel({ sessionId })
await first
})
it('session/cancel aborts a running turn and settles the prompt as cancelled', async () => {
harness = await makeBridgeHarness({ storageDir, script: ['hang'] })
const sessionId = await newSession(harness)
const promptDone = harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] })
await new Promise(r => setTimeout(r, 30))
await harness.client.cancel({ sessionId })
const res = await promptDone
expect(res.stopReason).toBe('cancelled')
})
it('cancel right after prompt settles cancelled and leaves the agent idle, no leaked turn', async () => {
// Over the async JSON-RPC transport the loop usually wakes before cancel
// arrives, so this is a running/mid-step cancel (the synchronous pre-step
// DROP is unit-tested in agent-loop/cancel.spec.ts). The ACP-level guarantee:
// the prompt settles cancelled, the agent reaches idle, and no second/leaked
// turn runs afterward.
harness = await makeBridgeHarness({ storageDir, script: [textResponse('answer'), textResponse('leaked')] })
const sessionId = await newSession(harness)
const promptDone = harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] })
await harness.client.cancel({ sessionId })
const res = await promptDone
expect(res.stopReason).toBe('cancelled')
const agent = harness.ctx.agents.get(AgentId(sessionId))!
await agent.whenIdle()
// At most ONE turn ran (the cancelled one) — the cancel cleared the queue, so
// no second turn was batched or leaked. (A best-effort abort that left queued
// work could have started a second turn.)
const turnStarts = agent.session.events.filter(e => e.type === 'turn/start').length
expect(turnStarts).toBeLessThanOrEqual(1)
})
it('idle session/cancel then session/prompt runs the prompt (no intervening whenIdle)', async () => {
// The ACP bridge settles the cancel RPC synchronously and accepts the next
// prompt WITHOUT awaiting quiescence — so this drives cancel→prompt with NO
// whenIdle() between, the production race. An idle cancel must be a no-op that
// does NOT drop the following prompt.
harness = await makeBridgeHarness({ storageDir, script: [textResponse('real answer')] })
const sessionId = await newSession(harness)
// Cancel while idle (no prompt in flight) — a no-op.
await harness.client.cancel({ sessionId })
// Immediately prompt, no whenIdle() between.
const res = await harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] })
expect(res.stopReason).toBe('end_turn')
const text = harness.updates
.filter(u => u.sessionUpdate === 'agent_message_chunk')
.map(u => (u.content.type === 'text' ? u.content.text : ''))
.join('')
expect(text).toContain('real answer')
})
it('mid-stream cancel then an IMMEDIATE next prompt runs (no intervening whenIdle)', async () => {
// Cancel a running turn, then send the next prompt WITHOUT awaiting quiescence
// (the synchronous-settle path). The new prompt must run — the cancel marker
// must not leak onto it.
harness = await makeBridgeHarness({ storageDir, script: ['hang', textResponse('next answer')] })
const sessionId = await newSession(harness)
const a = harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'A' }] })
await new Promise(r => setTimeout(r, 30))
await harness.client.cancel({ sessionId })
expect((await a).stopReason).toBe('cancelled')
// Immediately — no whenIdle() — send the next prompt.
const b = await harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'B' }] })
expect(b.stopReason).toBe('end_turn')
const text = harness.updates
.filter(u => u.sessionUpdate === 'agent_message_chunk')
.map(u => (u.content.type === 'text' ? u.content.text : ''))
.join('')
expect(text).toContain('next answer')
})
it('a cancelled turn\'s late turn/end does not settle the NEXT prompt', async () => {
// Regression: prompt A runs; cancel settles A and frees the slot; A's
// aborted turn/end is still pending in the loop. Prompt B is sent before
// A's turn/end arrives. A's late turn/end (an EARLIER turn number) must NOT
// settle B — B owns a later turn. B then completes on its OWN turn/end.
harness = await makeBridgeHarness({ storageDir, script: ['hang', textResponse('B answer')] })
const sessionId = await newSession(harness)
const a = harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'A' }] })
await new Promise(r => setTimeout(r, 30)) // let A start running (turn 1)
await harness.client.cancel({ sessionId })
expect((await a).stopReason).toBe('cancelled')
// Immediately send B; its turn (2) is distinct from A's (1). If A's late
// turn/end leaked onto B, B would settle 'cancelled' instead of 'end_turn'.
const b = await harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'B' }] })
expect(b.stopReason).toBe('end_turn')
const text = harness.updates
.filter(u => u.sessionUpdate === 'agent_message_chunk')
.map(u => (u.content.type === 'text' ? u.content.text : ''))
.join('')
expect(text).toContain('B answer')
})
})

View File

@@ -0,0 +1,36 @@
{
"extends": "../../../tsconfig.base.json",
"compilerOptions": {
"rootDir": "src",
"outDir": "lib/types"
},
"include": [
"src"
],
"references": [
{
"path": "../../../vendor/cosmokit"
},
{
"path": "../../../vendor/cordis"
},
{
"path": "../../../vendor/schemastery"
},
{
"path": "../../llm/llm"
},
{
"path": "../../core/session"
},
{
"path": "../../core/agent"
},
{
"path": "../../core/tools"
},
{
"path": "../../session-persistence/session-persistence"
}
]
}

View File

@@ -0,0 +1,60 @@
# @deepseek-ai/dsh-stdio-agent
The **terminal stdio chat app**: a Cordis app plugin that composes the providerless agent spine ([`@deepseek-ai/dsh-agent-core`](../../core/agent-core/README.md)) with the front-door cluster a terminal chat needs, and a `bin` that boots a leaf `cordis.yml`.
It is the readline counterpart to [`@deepseek-ai/dsh-acp-agent`](../acp-agent/README.md): both consume the same spine, but each bakes in the OPPOSITE front-door cluster.
## What it bakes in
A terminal chat always wants the same cluster, so the package owns it rather than trusting each leaf to re-wire it:
| Plugin | Why it is here |
|---|---|
| `@cordisjs/plugin-logger-console` | the console logger — stdout is just the terminal here, so logging to it is correct (the ACP app must NOT have this) |
| `@deepseek-ai/dsh-agent-core` | the spine, pre-creating a `main` agent from this app's `model`/`systemPrompt` |
| `@deepseek-ai/dsh-session-persistence-jsonl` | durable JSONL session log under `persistenceRoot` |
| `@deepseek-ai/dsh-ui-stdio` | the readline UI, bound to the `main` agent |
`@cordisjs/plugin-hmr` (the dev/demo edit-reload loop) is deliberately a **leaf** entry, NOT baked in here: it is a Loader-only, subprocess-only dev plugin — its constructor throws without `node --expose-internals` + a live `loader`, and the in-process test tier cannot even import it (so a package whose `apply` statically pulled it in could never carry the per-file coverage gate). Unlike the console logger, a stray `hmr` is not a stdout-purity footgun, so leaving it at the leaf costs no safety. The `demo:echo` / `demo:coding` leaves load it and pass `--expose-internals`.
The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapter (`llm-deepseek` for the real model, or the mock `mock-llm` for a demo) and a bash executor (`bash-local`) — `hmr`, plus this app's [`Config`](#config). The whole plugin tree a run loads is therefore: this app's cluster, the spine inside `agent-core`, `hmr`, and the two leaf backends.
## Config
| Key | Default | Routed to |
|---|---|---|
| `model` | (required) | the pre-created `main` agent's model |
| `systemPrompt` | (required) | the `main` agent's system prompt |
| `persistenceRoot` | `./.sessions` | the JSONL backend's root directory |
| `welcome` | `ready.` | the stdin-chat banner |
| `resumeSessionId` | — | resume a persisted session id instead of starting fresh (sourced from an env var in the leaf) |
## The bin
`dsh-stdio-agent [path-to-cordis.yml]` (default `./cordis.yml`) loads a gitignored `.env` from the cwd (`DEEPSEEK_API_KEY` / `DEEPSEEK_BASE_URL`), then drives the cordis Loader against the config and awaits the whole plugin tree before returning. Run it under `node --expose-internals`: the cordis Loader resolves the config's bare plugin specifiers (`@deepseek-ai/dsh-*`, npm packages) through its internal module loader, which is only active under that flag. The `demo:echo` / `demo:coding` scripts invoke it that way.
## Example leaf `cordis.yml`
```yaml
# A real coding agent: hmr + the DeepSeek adapter + local bash, then this app.
- id: hmr
name: '@cordisjs/plugin-hmr'
config:
root: ['.']
- id: llm-deepseek
name: '@deepseek-ai/dsh-llm-deepseek'
config:
apiKey: !!js process.env.DEEPSEEK_API_KEY
models: [deepseek-v4-flash]
- id: bash
name: '@deepseek-ai/dsh-bash-local'
config:
timeoutMs: 60000
- id: stdio-agent
name: '@deepseek-ai/dsh-stdio-agent'
config:
model: deepseek-v4-flash
systemPrompt: 'You are a CLI coding assistant. Your only tools are bash…'
```
Swap `llm-deepseek` for a `mock-llm` leaf plugin and you have the echo demo — "swap the backend, keep the app".

View File

@@ -0,0 +1,53 @@
{
"name": "@deepseek-ai/dsh-stdio-agent",
"description": "Terminal stdio chat app: the agent-core spine + console logger + readline UI + a pre-created main agent, with a bin to boot a leaf cordis.yml",
"version": "0.0.1",
"private": true,
"type": "module",
"main": "lib/index.js",
"types": "lib/index.d.ts",
"bin": {
"dsh-stdio-agent": "lib/bin.js"
},
"exports": {
".": {
"types": "./lib/index.d.ts",
"default": "./lib/index.js"
},
"./bin": {
"types": "./lib/bin.d.ts",
"default": "./lib/bin.js"
},
"./src/*": "./src/*",
"./package.json": "./package.json"
},
"files": [
"lib",
"src"
],
"license": "BSD-3-Clause",
"peerDependencies": {
"@cordisjs/plugin-include": "^1.0.4",
"@cordisjs/plugin-loader": "^1.0.0-rc.4",
"@cordisjs/plugin-logger-console": "^1.0.0",
"@deepseek-ai/dsh-agent": "^0.0.1",
"@deepseek-ai/dsh-agent-core": "^0.0.1",
"@deepseek-ai/dsh-session": "^0.0.1",
"@deepseek-ai/dsh-session-persistence-jsonl": "^0.0.1",
"@deepseek-ai/dsh-ui-stdio": "^0.0.1",
"cordis": "^4.0.0-rc.6",
"schemastery": "^3.17.0"
},
"devDependencies": {
"@cordisjs/plugin-include": "workspace:^",
"@cordisjs/plugin-loader": "workspace:^",
"@cordisjs/plugin-logger-console": "workspace:^",
"@deepseek-ai/dsh-agent": "workspace:^",
"@deepseek-ai/dsh-agent-core": "workspace:^",
"@deepseek-ai/dsh-session": "workspace:^",
"@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^",
"@deepseek-ai/dsh-ui-stdio": "workspace:^",
"cordis": "^4.0.0-rc.6",
"schemastery": "^3.17.0"
}
}

View File

@@ -0,0 +1,140 @@
#!/usr/bin/env node
/**
* The `dsh-stdio-agent` bin: boot a Cordis app from a leaf `cordis.yml` that
* loads the {@link @deepseek-ai/dsh-stdio-agent} app plugin (plus a backend LLM
* adapter and a bash executor). Owns the boot glue the three `examples/*` once
* duplicated in their `start.ts`: load the gitignored repo-root `.env`, then
* drive the cordis Loader against the config path (default `./cordis.yml`).
*
* Usage: `dsh-stdio-agent [path-to-cordis.yml]`. The `demo:echo` / `demo:coding`
* scripts invoke it with the example's config.
*
* @module @deepseek-ai/dsh-stdio-agent/bin
*/
import { pathToFileURL } from 'node:url'
import { dirname, resolve } from 'node:path'
import { Context } from 'cordis'
import Loader from '@cordisjs/plugin-loader'
/**
* Load `DEEPSEEK_API_KEY` / `DEEPSEEK_BASE_URL` from a gitignored `.env` in the
* CURRENT WORKING DIRECTORY (Node native `process.loadEnvFile`). An absent file
* is fine — the environment may already carry the variables; the leaf
* `cordis.yml` reads them via the `!!js` tag. A present-but-unreadable/malformed
* `.env` is a real misconfiguration: surface it on stderr rather than silently
* running with the wrong environment. The mock-model demo (echo) ships no key
* and simply has no `.env`.
*/
function loadEnv(): void {
try {
process.loadEnvFile(resolve(process.cwd(), '.env'))
} catch (error) {
if ((error as NodeJS.ErrnoException | null)?.code !== 'ENOENT') {
process.stderr.write(`dsh-stdio-agent: failed to load .env: ${String(error)}\n`)
}
// ENOENT (no .env) is fine — rely on the ambient environment.
}
}
/**
* Make a load failure fail loud with a clear message on stderr. Covers the
* failure path the entry-tree check below cannot: when the include's
* `[Service.init]` throws (e.g. a config FILE that does not exist in a real
* directory), the cordis Loader surfaces it as an unhandled promise rejection
* AFTER `boot()` has resolved — `loader.await()` does NOT rethrow it, because
* `EntryTree.await()` uses `Promise.allSettled`, which swallows rejections.
* Node's default handler already exits non-zero on an unhandled rejection, so
* this does not change the exit code; it replaces Node's noisy stack dump with a
* single labelled line and guarantees `process.exit(1)`. Install before `boot()`.
*/
export function installFailLoud(): void {
process.on('unhandledRejection', (err: unknown) => {
process.stderr.write(`dsh-stdio-agent: fatal load failure: ${err instanceof Error ? err.stack ?? err.message : String(err)}\n`)
process.exit(1)
})
}
/**
* After the tree settles, assert every loader entry actually started. This is
* the load-bearing guard against the SILENT-exit-0 bug: when a plugin module
* fails to IMPORT (e.g. a config path in a non-existent directory, so the include
* plugin itself cannot be resolved), the cordis Loader catches the import error
* and only LOGS it (`entry._init`), leaving the entry with no `fiber` and
* producing no rejection — so the process would otherwise exit 0 with a usable
* config typo reported only as a log line. A started entry has a `fiber`; an
* entry with `fiber === undefined` after the tree settled never loaded. Throw on
* any such entry so `boot()` rejects (and the top-level `await` fails the process
* non-zero) instead of returning a half-empty context.
*
* A `disabled` entry is the one legitimate fiber-less state: `Entry.refresh()`
* deliberately skips `init()` for it, so it settles without a fiber by design.
* That is a valid config (a consumer turning an optional plugin off), not a
* failed import — exclude it so the guard catches only real load failures.
*/
function assertEntriesLoaded(ctx: Context): void {
const failed = [...ctx.loader.entries()].filter(entry => entry.fiber === undefined && !entry.disabled)
if (failed.length > 0) {
const names = failed.map(entry => entry.options.name).join(', ')
throw new Error(`dsh-stdio-agent: plugin(s) failed to load: ${names} (see the error(s) logged above)`)
}
}
/**
* Boot the Loader against `configPath` (resolved from the CWD). The include is
* handed the config's ABSOLUTE `file://` URL as its `path`, so resolution never
* depends on `ctx.baseUrl` (an absolute URL ignores the base) and can never fall
* back to the cwd. `baseUrl` is still pinned to the config's directory so the
* config's OWN relative plugin/include paths (e.g. `./src/mock-llm.ts`) resolve
* against it. Returns the root context once the whole tree has settled.
*
* The `await ctx.loader.await()` is load-bearing: `loader.create()` returns once
* the include ENTRY is registered, but the include then loads its child plugins
* asynchronously. Without awaiting the tree, `boot()` (and `main()`) would
* resolve while the app plugins — the stdin reader, the agent loop — are still
* mounting, and a CLI process with no attached handles yet exits 0 silently.
* Awaiting the tree keeps the process alive until the app's handles are attached.
*
* `loader.await()` does NOT, however, rethrow load errors (`EntryTree.await()`
* uses `Promise.allSettled`), so failures are surfaced two ways: a plugin that
* fails to IMPORT leaves an entry with no fiber, caught here by
* {@link assertEntriesLoaded} (this `boot()` rejects); a plugin whose init
* THROWS surfaces as an unhandled rejection caught by {@link installFailLoud}
* (installed by `main()` before this runs). Together they make any load failure
* exit non-zero with a clear message.
*
* Bare plugin specifiers in the config (`@deepseek-ai/dsh-*`, npm packages) are
* resolved by the cordis Loader's internal module loader, which is only active
* under `node --expose-internals` (the flag the `demo:echo`/`demo:coding` scripts
* pass). Without it the Loader falls back to resolving relative to its own module
* and cannot find the config's plugins, so a consumer running the built bin must
* pass `--expose-internals` (or install the plugins where node hoists them).
*/
export async function boot(configPath: string): Promise<Context> {
const absolute = resolve(process.cwd(), configPath)
const ctx = new Context()
ctx.baseUrl = pathToFileURL(dirname(absolute)).href + '/'
await ctx.plugin(Loader)
await ctx.loader.create({
name: '@cordisjs/plugin-include',
config: { path: pathToFileURL(absolute).href },
})
await ctx.loader.await()
assertEntriesLoaded(ctx)
return ctx
}
/**
* Entry point: install the fail-loud guard, load `.env`, then boot the config
* named on argv (default `./cordis.yml`). Awaited at the module top level by the
* published bin (`#!/usr/bin/env node` shebang via the package's `bin` field).
*/
export async function main(argv: string[] = process.argv.slice(2)): Promise<void> {
installFailLoud()
loadEnv()
await boot(argv[0] ?? './cordis.yml')
}
/* v8 ignore start -- top-level CLI invocation; the testable core is boot()/main(), driven by the keyless Loader-path smoke */
await main()
/* v8 ignore stop */

View File

@@ -0,0 +1,98 @@
/**
* The stdio chat app: the providerless agent spine ({@link
* @deepseek-ai/dsh-agent-core}) plus the coupled front-door cluster a terminal
* chat needs — a console logger, the readline `ui-stdio` UI, JSONL session
* persistence, and a pre-created `main` agent the UI drives.
*
* The cluster is BAKED IN, not left to the leaf: a stdio app always logs to the
* console (stdout is just the terminal) and always pre-creates the `main` agent
* `ui-stdio` sends to. The leaf supplies only the swappable backends (the LLM
* adapter, the bash executor), the optional `hmr` dev-reload plugin, and this
* app's {@link Config} (model, prompt, persistence root, welcome banner).
*
* `hmr` is deliberately a LEAF entry, not baked in here: it is a Loader-only,
* subprocess-only dev plugin (its constructor throws without `--expose-internals`
* + a live `loader`, and the in-process test tier cannot even import it), so a
* package whose `apply` statically pulled it in could never be unit-tested or
* carry the per-file coverage gate. Unlike the console logger, a stray `hmr` is
* not a stdout-purity footgun — so leaving it at the leaf costs no safety, while
* baking the LOGGER in (the real coupling) keeps stdout-vs-no-stdout a property
* of the artifact.
*
* Counterpart to {@link @deepseek-ai/dsh-acp-agent}, which bakes in the OPPOSITE
* cluster (no stdout logger, no pre-created agents — the ACP bridge reserves
* stdout for JSON-RPC and creates agents on demand). Splitting the two front
* doors into two packages makes each cluster a property of the artifact: there
* is no logger entry in the ACP leaf to get wrong.
*
* Plugin export shape: named `name`/`Config`/`apply`, NO default export — the
* cordis Loader's `unwrapExports` does `exports.default ?? exports`, so a stray
* default would collapse the module to the bare `apply` and drop the `Config`
* namespace (see docs/postmortem/0001). The keyless Loader-path smoke in the
* echo example guards this end-to-end.
*
* @module @deepseek-ai/dsh-stdio-agent
*/
import type { Context } from 'cordis'
import ConsoleExporter from '@cordisjs/plugin-logger-console'
import z from 'schemastery'
import { AgentId } from '@deepseek-ai/dsh-agent'
import { SessionId } from '@deepseek-ai/dsh-session'
import * as agentCore from '@deepseek-ai/dsh-agent-core'
import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
import * as uiStdio from '@deepseek-ai/dsh-ui-stdio'
export const name = 'stdio-agent'
/**
* App config: the swappable per-demo values, each routed to where the app wires
* it. `model`/`systemPrompt`/`resumeSessionId` configure the pre-created `main`
* agent (through {@link @deepseek-ai/dsh-agent-core}'s forwarded `agents` list);
* `persistenceRoot` is the JSONL backend's directory; `welcome` is the UI banner.
*/
export interface Config {
/** Model name for the `main` agent (must have a registered adapter). */
model: string
/** System prompt for the `main` agent. */
systemPrompt: string
/** Directory the JSONL session backend writes under. Defaults to `./.sessions`. */
persistenceRoot?: string
/** stdin-chat banner printed once on start. Defaults to `'ready.'`. */
welcome?: string
/**
* If set, the `main` agent RESUMES this persisted session id instead of
* starting fresh. Sourced from an env var in the leaf `cordis.yml`
* (`resumeSessionId: !!js process.env.RESUME_SESSION_ID`).
*/
resumeSessionId?: string
}
export const Config: z<Config> = z.object({
model: z.string().required(),
systemPrompt: z.string().required(),
persistenceRoot: z.string().default('./.sessions'),
welcome: z.string().default('ready.'),
resumeSessionId: z.string(),
})
/**
* Compose the spine with the stdio front door. The console logger comes first
* (infra), then the agent-core bundle pre-creating the `main` agent from this
* app's `model`/`systemPrompt`/`resumeSessionId`, then the JSONL backend, then
* the `ui-stdio` UI bound to `main`. The `hmr` dev-reload plugin is a leaf
* concern (see the module doc), so it is not mounted here.
*/
export function apply(ctx: Context, config: Config): void {
ctx.plugin(ConsoleExporter)
ctx.plugin(agentCore, {
agents: [{
id: AgentId('main'),
model: config.model,
systemPrompt: config.systemPrompt,
...config.resumeSessionId !== undefined ? { resumeSessionId: SessionId(config.resumeSessionId) } : {},
}],
})
ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' })
ctx.plugin(uiStdio, { welcome: config.welcome ?? 'ready.', agent: 'main' })
}

View File

@@ -0,0 +1,186 @@
import { spawn } from 'node:child_process'
import { cp, mkdtemp, mkdir, rm, symlink, writeFile, readFile } from 'node:fs/promises'
import { existsSync } from 'node:fs'
import { tmpdir } from 'node:os'
import { dirname, join } from 'node:path'
import { fileURLToPath } from 'node:url'
import { afterEach, describe, expect, it } from 'vitest'
/**
* BUILT-ARTIFACT smoke for the published `dsh-stdio-agent` bin. The other smokes
* boot `src/bin.ts` under tsx — but the package's `bin` field points at
* `lib/bin.js`, run under plain `node` by a real consumer. tsx masks two failure
* modes the built bin had: (1) `boot()` returned before the loader tree settled,
* so the process exited 0 with no output and load errors surfaced as unhandled
* rejections AFTER boot; (2) config-path resolution could fall back to the cwd.
* This test runs the REAL `lib/bin.js` under `node` (NOT tsx) and asserts the
* banner + echo round-trip, so a regression in the published entry fails here.
*
* It build-gates: if `lib/bin.js` is absent (suite run without `pnpm run build`)
* the test SKIPS with a note. CI runs it after the build step. Setup mirrors a
* real install: a temp dir whose `node_modules/@deepseek-ai/*` (and the vendored
* `cordis`/`@cordisjs/*`) are symlinked to the built packages, a `cordis.yml`
* that loads the app + the example's mock backend, and `node --expose-internals`
* (the cordis Loader resolves bare plugin specifiers via its internal module
* loader, active only under that flag — the same flag `demo:echo` passes).
*/
const repoRoot = fileURLToPath(new URL('../../../../', import.meta.url))
const stdioBin = join(repoRoot, 'packages/ui/stdio-agent/lib/bin.js')
// Workspace packages the stdio app's tree needs, by repo-relative path. Each is
// symlinked into the temp consumer's node_modules under its package name, so
// plain `node` resolves the bare `@deepseek-ai/dsh-*` specifiers in cordis.yml
// to the built `lib/` (package.json `main`), exactly as an installed dep would.
const dshPackages = [
'core/agent-core', 'core/agent', 'core/session', 'core/system-prompt',
'core/tools', 'core/agent-loop', 'llm/llm', 'bash/bash', 'bash/bash-local',
'bash/tool-bash', 'support/invariants', 'support/ui-stdio',
'session-persistence/session-persistence',
'session-persistence/session-persistence-jsonl', 'ui/stdio-agent',
]
const vendorPackages = [
'cordis', 'loader', 'include', 'timer', 'hmr', 'logger-console',
'schemastery', 'cosmokit',
]
async function pkgName(absDir: string): Promise<string> {
const json = JSON.parse(await readFile(join(absDir, 'package.json'), 'utf8')) as { name: string }
return json.name
}
/**
* Build a temp consumer dir: `node_modules` with the workspace + vendor packages
* symlinked in, a `src/` carrying the example mock backend, and a `cordis.yml`
* that wires them onto the stdio app. Returns the dir (caller removes it).
*
* `disabledBrokenEntry` appends an entry that points at a non-existent plugin but
* is marked `disabled: true`. The Loader leaves a disabled entry fiber-less by
* design, so it exercises that the fail-loud entry-load guard does NOT mistake a
* valid disabled entry for a failed import.
*/
async function makeConsumer(welcome: string, disabledBrokenEntry = false): Promise<string> {
const dir = await mkdtemp(join(tmpdir(), 'stdio-built-bin-'))
const nm = join(dir, 'node_modules')
for (const rel of dshPackages) {
const abs = join(repoRoot, 'packages', rel)
const name = await pkgName(abs)
const target = join(nm, name)
await mkdir(dirname(target), { recursive: true })
await symlink(abs, target)
}
for (const v of vendorPackages) {
const abs = join(repoRoot, 'vendor', v)
const name = await pkgName(abs)
const target = join(nm, name)
await mkdir(dirname(target), { recursive: true })
await symlink(abs, target)
}
// The example's mock model + echo tool are example-local TS plugins (Node 24+
// strips types natively, so plain `node` loads them); they import the workspace
// packages the symlinked node_modules now provides.
await cp(join(repoRoot, 'examples/echo-agent/src'), join(dir, 'src'), { recursive: true })
await writeFile(join(dir, 'cordis.yml'), [
'- id: mock-llm',
' name: \'./src/mock-llm.ts\'',
'- id: echo-tool',
' name: \'./src/echo-tool.ts\'',
'- id: bash',
' name: \'@deepseek-ai/dsh-bash-local\'',
'- id: stdio-agent',
' name: \'@deepseek-ai/dsh-stdio-agent\'',
' config:',
' model: mock-echo',
' systemPrompt: \'demo\'',
` welcome: '${welcome}'`,
...disabledBrokenEntry
? ['- id: off', ' name: \'./src/does-not-exist.ts\'', ' disabled: true']
: [],
'',
].join('\n'))
return dir
}
/** Run the built bin in `cwd` against `configArg` with one stdin line; resolve with stdout/stderr + exit code. */
function runBuiltBin(cwd: string, configArg: string, line: string): Promise<{ stdout: string; code: number; stderr: string }> {
return new Promise((resolve, reject) => {
// --expose-internals: the cordis Loader resolves bare plugin specifiers via
// its internal module loader (active only under this flag); demo:echo passes
// it too. NO tsx — this is the published `node lib/bin.js` path.
const child = spawn(process.execPath, ['--expose-internals', stdioBin, configArg], {
cwd,
// Mock model: never calls the network, so no key needed.
env: { ...process.env },
stdio: ['pipe', 'pipe', 'pipe'],
})
let stdout = ''
let stderr = ''
child.stdout.setEncoding('utf8')
child.stdout.on('data', (c: string) => { stdout += c })
child.stderr.setEncoding('utf8')
child.stderr.on('data', (c: string) => { stderr += c })
const timer = setTimeout(() => {
child.kill('SIGKILL')
reject(new Error(`built bin did not exit within 25s. stdout:\n${stdout}\nstderr:\n${stderr}`))
}, 25_000)
child.on('exit', (code) => { clearTimeout(timer); resolve({ stdout, code: code ?? -1, stderr }) })
child.on('error', (err) => { clearTimeout(timer); reject(err) })
child.stdin.write(`${line}\n`)
child.stdin.end()
})
}
let consumer: string | undefined
afterEach(async () => {
if (consumer !== undefined) await rm(consumer, { recursive: true, force: true })
consumer = undefined
})
describe.skipIf(!existsSync(stdioBin))('dsh-stdio-agent BUILT bin (node lib/bin.js, no tsx)', () => {
it('boots the published bin, prints its banner, and runs the echo tool round-trip', async () => {
consumer = await makeConsumer('BUILT-BIN-OK ready.')
const { stdout, code, stderr } = await runBuiltBin(consumer, './cordis.yml', 'echo hi')
expect(stderr).not.toContain('UNHANDLED')
expect(stderr).not.toContain('without inject')
// The banner proves boot() awaited the tree (the settle-race regression would
// exit 0 with empty stdout); the round-trip proves the whole app mounted.
expect(stdout).toContain('BUILT-BIN-OK ready.')
expect(stdout).toContain('[tool call] echo')
expect(stdout).toContain('[tool result] ECHO: HI')
expect(code).toBe(0)
}, 30_000)
it('boots cleanly when the config disables an (otherwise unresolvable) entry', async () => {
// A `disabled: true` entry settles without a fiber by design; the fail-loud
// entry-load guard must NOT mistake it for a failed import. Even though its
// plugin path does not exist, the app boots and the round-trip works.
consumer = await makeConsumer('DISABLED-OK ready.', true)
const { stdout, code, stderr } = await runBuiltBin(consumer, './cordis.yml', 'echo hi')
expect(stderr).not.toContain('failed to load')
expect(stdout).toContain('DISABLED-OK ready.')
expect(stdout).toContain('[tool result] ECHO: HI')
expect(code).toBe(0)
}, 30_000)
it('fails LOUD (non-zero exit + stderr) on a config whose directory does not exist', async () => {
// A consumer who typos the config path must get a clear failure, not silent
// success. This dir does not exist, so the include PLUGIN itself fails to
// import; the cordis Loader logs that and leaves the entry with no fiber (no
// rejection), which `boot()`'s entry-load check turns into a thrown error.
consumer = await makeConsumer('unused')
const { code, stderr } = await runBuiltBin(consumer, '/nonexistent/dir/cordis.yml', '')
expect(code).not.toBe(0)
expect(stderr).toContain('failed to load')
}, 30_000)
it('fails LOUD (non-zero exit + stderr) on a missing config file in a real directory', async () => {
// The config DIRECTORY exists (the include plugin imports), but the file does
// not — the include's init throws "config file not found", which surfaces as
// an unhandled rejection the fail-loud guard turns into a non-zero exit.
consumer = await makeConsumer('unused')
const { code, stderr } = await runBuiltBin(consumer, './does-not-exist.yml', '')
expect(code).not.toBe(0)
expect(stderr).toContain('config file not found')
}, 30_000)
})

View File

@@ -0,0 +1,92 @@
import { describe, it, expect } from 'vitest'
import { Context } from 'cordis'
import Loader from '@cordisjs/plugin-loader'
import { AgentId } from '@deepseek-ai/dsh-agent'
import * as stdioAgent from '../src/index.ts'
/**
* Unit coverage for the @deepseek-ai/dsh-stdio-agent app plugin: mounting it
* composes the console logger, the agent-core spine (pre-creating the `main`
* agent from the app config), the JSONL backend, and the readline UI in one
* `ctx.plugin`. The forwarded `model`/`systemPrompt` reach the pre-created
* agent; `persistenceRoot`/`welcome`/`resumeSessionId` route to their backends.
*
* `hmr` is NOT part of this plugin (it is a leaf entry — a Loader-only dev
* plugin the in-process tier cannot import); the REAL Loader-path guard (export
* shape, `unwrapExports`, the whole subprocess tree incl. `hmr`) is the keyless
* echo smoke in `examples/echo-agent`. Here we assert the composition + config
* forwarding the unit tier can reach.
*/
async function mount(config: stdioAgent.Config): Promise<Context> {
const ctx = new Context()
await ctx.plugin(stdioAgent, config)
// The app mounts its children inside apply() (not awaited there); let their
// fibers settle so the spine services + the pre-created agent are ready.
await new Promise(resolve => setTimeout(resolve, 80))
return ctx
}
describe('dsh-stdio-agent app', () => {
it('composes the spine + front-door cluster and pre-creates the main agent', async () => {
const ctx = await mount({ model: 'mock', systemPrompt: 'hi', persistenceRoot: '/tmp/dsh-stdio-agent-spec' })
// The spine services (brought up by the agent-core bundle) are all present.
expect(ctx.get('agents')).toBeDefined()
expect(ctx.get('agentLoop')).toBeDefined()
expect(ctx.get('sessionPersistence')).toBeDefined()
// The pre-created `main` agent the UI drives.
expect(ctx.get('agents')?.get(AgentId('main'))).toBeDefined()
await ctx.fiber.dispose()
})
it('defaults persistenceRoot and welcome when omitted', async () => {
// Direct apply (NOT via ctx.plugin, which validates+defaults the config
// first) so the runtime `?? './.sessions'` / `?? 'ready.'` fallbacks on
// apply()'s last two lines are the ones that fire — covering a
// schema-bypassing direct-mount caller.
const ctx = new Context()
stdioAgent.apply(ctx, { model: 'mock', systemPrompt: 'hi' })
await new Promise(resolve => setTimeout(resolve, 80))
expect(ctx.get('sessionPersistence')).toBeDefined()
expect(ctx.get('agents')?.get(AgentId('main'))).toBeDefined()
await ctx.fiber.dispose()
})
it('forwards resumeSessionId onto the pre-created agent when set', async () => {
// A resume id defers agent creation until persistence loads; with no backing
// session the resume is contained + logged, so no `main` agent registers —
// the branch that maps resumeSessionId through is what this covers.
const ctx = await mount({
model: 'mock',
systemPrompt: 'hi',
persistenceRoot: '/tmp/dsh-stdio-agent-spec-resume',
resumeSessionId: 'no-such-session',
})
expect(ctx.get('agents')?.get(AgentId('main'))).toBeUndefined()
await ctx.fiber.dispose()
})
it('exposes its name and Config schema', () => {
expect(stdioAgent.name).toBe('stdio-agent')
expect(stdioAgent.Config).toBeDefined()
})
it('has the namespace-plugin export shape (no stray default) so the Loader keeps name/Config/apply', () => {
// Postmortem 0001 guard: a stray `export default apply` makes the Loader's
// `unwrapExports` (`exports.default ?? exports`) collapse the module to the
// bare `apply` function, DROPPING the named `name`/`Config`. This package has
// no `inject` export, so that collapse would NOT crash at load (the keyless
// echo smoke would still boot the tree) — it would silently lose its config
// schema. So guard the shape directly here: assert no `default` export, and
// that the real `unwrapExports` leaves `name`/`Config`/`apply` intact. Adding
// `export default` to src/index.ts fails this test.
expect('default' in stdioAgent).toBe(false)
expect(typeof stdioAgent.apply).toBe('function')
const loader = Object.create(Loader.prototype) as Loader
const unwrapped = loader.unwrapExports(stdioAgent) as Record<string, unknown>
expect(unwrapped).toBe(stdioAgent)
expect(unwrapped.name).toBe('stdio-agent')
expect(unwrapped.Config).toBeDefined()
expect(typeof unwrapped.apply).toBe('function')
})
})

View File

@@ -0,0 +1,39 @@
{
"extends": "../../../tsconfig.base.json",
"compilerOptions": {
"rootDir": "src",
"outDir": "lib"
},
"include": [
"src"
],
"references": [
{
"path": "../../../vendor/cordis"
},
{
"path": "../../../vendor/schemastery"
},
{
"path": "../../../vendor/loader"
},
{
"path": "../../../vendor/logger-console"
},
{
"path": "../../core/agent"
},
{
"path": "../../core/session"
},
{
"path": "../../core/agent-core"
},
{
"path": "../../session-persistence/session-persistence-jsonl"
},
{
"path": "../../support/ui-stdio"
}
]
}

View File

@@ -0,0 +1,18 @@
import { defineConfig } from 'tsdown'
/**
* stdio-agent ships TWO entries: the plugin (`index`) and the CLI `bin`
* (`bin`), the latter referenced by package.json `bin`/`exports["./bin"]`.
* The root tsdown builds only `src/index.ts`, so this override adds `bin.ts`.
* Declarations come from `tsc -b` (dts: false), matching every package.
*/
export default defineConfig({
entry: ['src/index.ts', 'src/bin.ts'],
outDir: 'lib',
format: ['esm'],
platform: 'node',
target: 'es2024',
fixedExtension: false,
dts: false,
clean: false,
})