Merge origin/master into skill system branch

Resolve documentation split, tool presentation, and generated catalog changes from master while preserving the skill system integration.
This commit is contained in:
Yichen Jiang
2026-07-05 16:50:29 +08:00
454 changed files with 29524 additions and 4598 deletions

View File

@@ -13,9 +13,9 @@ A terminal chat always wants the same cluster, so the package owns it rather tha
| `@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` with `process.cwd()` as the fresh session cwd |
| `@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 |
| `stdio-chat` (in-package module) | 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`.
`@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:repl` 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.
@@ -33,12 +33,12 @@ Fresh stdio sessions use the process launch directory as `session.header.cwd`, s
## 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.
`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:repl` scripts invoke it that way.
## Example leaf `cordis.yml`
```yaml
# A real coding agent: hmr + the DeepSeek adapter + local bash, then this app.
# A REPL agent demo: hmr + the DeepSeek adapter + local bash, then this app.
- id: hmr
name: '@cordisjs/plugin-hmr'
config:

View File

@@ -32,24 +32,26 @@
"peerDependencies": {
"@cordisjs/plugin-include": "^1.0.4",
"@cordisjs/plugin-loader": "^1.0.0-rc.4",
"@deepseek-ai/dsh-app-boot": "^0.0.1",
"@cordisjs/plugin-logger-console": "^1.0.0",
"@deepseek-ai/dsh-agent": "^0.0.1",
"@deepseek-ai/dsh-llm": "^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:^",
"@deepseek-ai/dsh-app-boot": "workspace:^",
"@cordisjs/plugin-logger-console": "workspace:^",
"@deepseek-ai/dsh-agent": "workspace:^",
"@deepseek-ai/dsh-llm": "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

@@ -2,139 +2,24 @@
/**
* 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`).
* adapter and a bash executor). The boot glue — `.env` loading, the fail-loud
* Loader guards, the settle-the-tree boot sequence — lives in
* {@link @deepseek-ai/dsh-app-boot}, shared with the ACP bin.
*
* Usage: `dsh-stdio-agent [path-to-cordis.yml]`. The `demo:echo` / `demo:coding`
* scripts invoke it with the example's config.
* Usage: `dsh-stdio-agent [path-to-cordis.yml]` (default `./cordis.yml`). The
* `demo:echo` / `demo:repl` 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'
import { boot, installFailLoud, loadEnv, resolveConfigPath } from '@deepseek-ai/dsh-app-boot'
/**
* 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.
}
}
const NAME = 'dsh-stdio-agent'
/**
* 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 start -- thin self-executing composition over the unit-tested
dsh-app-boot helpers; exercised end-to-end by the keyless Loader-path and
built-bin smokes */
installFailLoud(NAME)
loadEnv(NAME)
await boot(NAME, resolveConfigPath(process.argv[2] ?? './cordis.yml', undefined))
/* v8 ignore stop */

View File

@@ -1,12 +1,13 @@
/**
* 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
* chat needs — a console logger, the readline UI (the in-package `stdio-chat`
* module), 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 the swappable backends (the LLM
* the readline UI sends to. The leaf supplies the swappable backends (the LLM
* adapter, the bash executor), optional product tools, the optional `hmr`
* dev-reload plugin, and this app's {@link Config} (model, prompt, persistence
* root, welcome banner).
@@ -29,8 +30,10 @@
* 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.
* namespace (see docs/postmortem/0001). This app carries no `inject`, so a
* collapsed shape would BOOT rather than crash a smoke — the shape is pinned by
* the explicit `unwrapExports` assertion in this package's unit suite, and the
* keyless echo smoke proves the composed tree runs through the real Loader.
*
* @module @deepseek-ai/dsh-stdio-agent
*/
@@ -42,7 +45,7 @@ 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'
import * as uiStdio from './stdio-chat.ts'
export const name = 'stdio-agent'
@@ -83,7 +86,7 @@ export const Config: z<Config> = z.object({
* 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
* the readline 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 {

View File

@@ -0,0 +1,225 @@
/**
* The stdio app's readline UI: reads lines from stdin → `agent.send()`/
* `steer()`, and renders the durable transcript to stdout. A UI is "just a
* plugin" — it consumes the `session/event` feed (the assistant token stream,
* turn/step boundaries, tool activity, todos) plus a few `agent/*` control
* events (`agent/status`, `agent/created`/`agent/disposed`) and the `agents`
* service. Dimmed chain-of-thought rendering plus robust piped-stdin EOF→idle
* exit handling, configured via {@link Config}.
*
* An internal module of the stdio app, not a package of its own: the app's
* front-door cluster always includes this UI, and nothing else composes it.
* The export shape stays named `name`/`inject`/`Config`/`apply` — the plugin
* contract the app's `ctx.plugin(uiStdio, …)` mount consumes.
*
* @module @deepseek-ai/dsh-stdio-agent/stdio-chat
*/
import { createInterface } from 'node:readline'
import type { Readable, Writable } from 'node:stream'
import type { Context } from 'cordis'
import z from 'schemastery'
import { AgentId } from '@deepseek-ai/dsh-agent'
export const name = 'ui-stdio'
export const inject = ['agents']
/** Serializable plugin configuration (cordis-native, schemastery). */
export interface Config {
/** Banner printed once on start, before the first `> ` prompt. */
welcome?: string
/** Id of the agent stdin drives (`send`/`steer`) and whose status gates the EOF exit; rendering is global. Defaults to `'main'`. */
agent?: string
}
export const Config: z<Config> = z.object({
welcome: z.string().default('ready.'),
agent: z.string().default('main'),
})
/**
* Process-I/O seam — the side-effecting handles the plugin would otherwise
* reach for as globals. Defaulted to the real `process` streams in
* {@link apply}; injected by tests so the EOF, render, and disposal branches
* are exercised without hijacking globals. Deliberately NOT part of the
* serializable {@link Config} (streams/functions don't belong in YAML config).
*/
export interface StdioRuntime {
/** Line source (default `process.stdin`). */
input: Readable
/** Render sink (default `process.stdout`). */
output: Writable
/** Process-exit hook (default `process.exit`); called once on stdin EOF. */
exit: (code: number) => void
}
function isTTYPair(input: Readable, output: Writable): boolean {
return Boolean((input as { isTTY?: boolean }).isTTY && (output as { isTTY?: boolean }).isTTY)
}
/**
* The plugin body, parameterized over its I/O runtime. `apply` is the thin
* production wrapper that binds the real `process` streams; tests call this
* directly with fakes. Returns nothing — all registration is via `ctx.on`/
* `ctx.effect`, so fiber disposal tears every listener and the readline
* interface down.
*/
export function createStdioChat(ctx: Context, config: Config, runtime: StdioRuntime): void {
// Default here too (not just via schemastery's `.default()`): this helper is
// exported and called directly by tests / programmatic consumers that bypass
// Loader validation, so it must be self-contained rather than trusting the
// cast — `config.welcome as string` would otherwise be `undefined` on `{}`.
const welcome = config.welcome ?? 'ready.'
const agentId = AgentId(config.agent ?? 'main')
const { input, output, exit } = runtime
// Render label lookup: the `turn/start` session event carries only the turn
// number, so to print the short agent id (`[main turn 1]`) we map the
// session's id to its agent's id. The session id is not reliably the agent id
// (a session can be created with an explicit/client-supplied id), so build the
// map from `agent/created` rather than parsing the id string. Seed from the
// registry's current agents first: an agent registered before this plugin
// installed (e.g. the pre-created `main` agent, or any agent surviving an HMR
// reload of just this fiber) already fired its `agent/created`, so the live
// listener alone would miss it and its turns would fall back to the raw
// session id.
const labelBySession = new Map<string, string>()
for (const agent of ctx.agents.list()) labelBySession.set(agent.session.header.id, agent.id)
ctx.on('agent/created', (agent) => { labelBySession.set(agent.session.header.id, agent.id) })
ctx.on('agent/disposed', (agent) => { labelBySession.delete(agent.session.header.id) })
// Transcript rendering off the durable `session/event` feed — the assistant
// token stream, turn/step boundaries, tool activity, and todos all come from
// the one canonical stream (no agent/* mirrors). A single listener over the
// append order keeps `inReasoning` transitions deterministic across chunk and
// boundary events.
let inReasoning = false
ctx.on('session/event', (session, event) => {
if (event.type === 'assistant/chunk') {
const { chunk } = event.data
if (chunk.type === 'reasoning-delta') {
// Dim the chain-of-thought so the final answer stands out.
if (!inReasoning) output.write('\x1B[2m')
inReasoning = true
output.write(chunk.text)
} else if (chunk.type === 'text-delta') {
if (inReasoning) output.write('\x1B[0m\n')
inReasoning = false
output.write(chunk.text)
}
} else if (event.type === 'turn/start') {
const label = labelBySession.get(session.header.id) ?? session.header.id
output.write(`\n[${label} turn ${event.data.turn}] `)
} else if (event.type === 'turn/end') {
if (inReasoning) output.write('\x1B[0m')
inReasoning = false
output.write('\n> ')
} else if (event.type === 'tool/call') {
const { name: toolName, arguments: args } = event.data
if (inReasoning) output.write('\x1B[0m')
inReasoning = false
output.write(`\n [tool call] ${toolName}(${args})`)
} else if (event.type === 'tool/result') {
const { content } = event.data
const text = content.filter(block => block.type === 'text').map(block => block.text).join('')
output.write(`\n [tool result] ${text}\n `)
} else if (event.type === 'todo/write') {
if (inReasoning) output.write('\x1B[0m')
inReasoning = false
const glyph = (status: string): string =>
status === 'completed' ? '[x]' : status === 'in_progress' ? '[~]' : '[ ]'
const lines = event.data.todos.map(todo => ` ${glyph(todo.status)} ${todo.content}`).join('\n')
output.write(`\n [todos]\n${lines}\n `)
}
})
ctx.effect(() => {
const reader = createInterface({ input, output, terminal: isTTYPair(input, output) })
// Piped-input exit, once stdin reaches EOF:
// - If no line ever submitted work (empty stdin, blank-only lines), exit
// immediately — no turn will ever start, so there is nothing to wait
// for. (Gating on an observed 'running' here would hang forever.)
// - If work WAS submitted, exit the next time the agent settles to idle
// AFTER having run. Two subtleties this handles: the loop batches
// several queued messages into ONE turn (one idle), so we don't count
// sends; and agent.send() does NOT synchronously flip status to
// 'running', so requiring an observed 'running' first (`sawRunning`)
// avoids exiting in the gap before the turn starts and dropping work.
let stdinClosed = false
let disposed = false
let submittedWork = false
let sawRunning = false
let exitTimer: ReturnType<typeof setTimeout> | undefined
const maybeExit = (): void => {
if (disposed || !stdinClosed) return
// No work submitted: nothing will ever run, exit straight away.
// Work submitted: wait until a turn has run and the agent is idle.
if (submittedWork) {
if (!sawRunning) return
const agent = ctx.agents.get(agentId)
if (agent && agent.status !== 'idle') return // a turn is still running
}
// Let any final output flush, then exit. The handle is tracked so the
// disposer can cancel it — a dispose within the flush window must not let
// the process exit out from under HMR. Re-entrant `maybeExit` calls (e.g.
// repeated idle signals) coalesce onto the one pending timer.
if (exitTimer !== undefined) {
return // exit already scheduled — coalesce re-entrant calls
}
exitTimer = setTimeout(() => { exit(0) }, 200)
}
const disposeStatusListener = ctx.on('agent/status', (subject, status) => {
if (subject.id !== agentId) return
if (status === 'running') sawRunning = true
if (status === 'idle') maybeExit()
})
reader.on('line', (line) => {
const text = line.trim()
if (!text) return
const agent = ctx.agents.get(agentId)
if (!agent) {
ctx.logger.error('ui-stdio: agent "%s" is not running', agentId)
return
}
submittedWork = true
if (agent.status === 'running') {
agent.steer([{ type: 'text', text }])
} else {
agent.send([{ type: 'text', text }])
}
})
reader.on('close', () => {
// Fires for BOTH stdin EOF and plugin disposal (reader.close() below);
// `disposed` guards teardown so HMR/dispose never exits the process.
stdinClosed = true
maybeExit()
})
output.write(`${welcome}\n> `)
return () => {
disposed = true
if (exitTimer !== undefined) clearTimeout(exitTimer)
disposeStatusListener()
reader.close()
}
}, 'ui-stdio')
}
/**
* Cordis entry point. Binds the real `process` streams and delegates to
* {@link createStdioChat}; the indirection keeps the side-effecting handles out
* of the testable core, which is why the unit suite drives `createStdioChat`
* directly. This thin wrapper is exercised end-to-end by the keyless
* Loader-path e2e smoke in `examples/echo-agent` (the real product entry).
*/
/* v8 ignore start -- production stdio wiring; testable core is createStdioChat() (covered), exercised e2e by echo-agent keyless smoke */
export function apply(ctx: Context, config: Config): void {
createStdioChat(ctx, config, {
input: process.stdin,
output: process.stdout,
exit: code => process.exit(code),
})
}
/* v8 ignore stop */

View File

@@ -35,7 +35,7 @@ const stdioBin = join(repoRoot, 'packages/ui/stdio-agent/lib/bin.js')
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',
'bash/tool-bash', 'support/invariants', 'ui/app-boot',
'session-persistence/session-persistence',
'session-persistence/session-persistence-jsonl', 'ui/stdio-agent',
]

View File

@@ -0,0 +1,53 @@
import { EventEmitter } from 'node:events'
import type { Readable, Writable } from 'node:stream'
import { describe, expect, it, vi } from 'vitest'
import type { Context } from 'cordis'
import type { StdioRuntime } from '../src/stdio-chat.ts'
const createInterface = vi.hoisted(() => vi.fn(() => {
const reader = new EventEmitter() as EventEmitter & { close(): void }
reader.close = vi.fn()
return reader
}))
vi.mock('node:readline', () => ({ createInterface }))
function fakeContext(): Context {
return {
on: vi.fn(() => vi.fn()),
effect: vi.fn((callback: () => () => void) => callback()),
// The UI seeds its label map from the registry at install; this suite only
// exercises readline terminal-mode selection, so an empty roster suffices.
agents: { list: vi.fn(() => []) },
} as unknown as Context
}
function fakeRuntime(inputIsTTY: boolean, outputIsTTY: boolean): StdioRuntime {
return {
input: { isTTY: inputIsTTY } as Readable & { isTTY: boolean },
output: { isTTY: outputIsTTY, write: vi.fn(() => true) } as unknown as Writable & { isTTY: boolean },
exit: vi.fn(),
}
}
describe('createStdioChat readline mode', () => {
it('enables terminal editing only when both stdio streams are TTYs', async () => {
const { createStdioChat } = await import('../src/stdio-chat.ts')
const tty = fakeRuntime(true, true)
createStdioChat(fakeContext(), {}, tty)
expect(createInterface).toHaveBeenLastCalledWith({
input: tty.input,
output: tty.output,
terminal: true,
})
const piped = fakeRuntime(true, false)
createStdioChat(fakeContext(), {}, piped)
expect(createInterface).toHaveBeenLastCalledWith({
input: piped.input,
output: piped.output,
terminal: false,
})
})
})

View File

@@ -12,9 +12,11 @@ import * as stdioAgent from '../src/index.ts'
* 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
* plugin the in-process tier cannot import); the keyless echo smoke in
* `examples/echo-agent` proves the whole subprocess tree (incl. `hmr`) boots
* through the real Loader, while the export SHAPE is pinned by this suite's
* explicit `unwrapExports` assertion (an inject-less app would boot past a
* stray default rather than crash). Here we assert the composition + config
* forwarding the unit tier can reach.
*/
async function mount(config: stdioAgent.Config): Promise<Context> {

View File

@@ -0,0 +1,437 @@
import { Readable } from 'node:stream'
import { describe, expect, it, vi } from 'vitest'
import { Context } from 'cordis'
import type { Agent, AgentStatus } from '@deepseek-ai/dsh-agent'
import AgentRegistry from '@deepseek-ai/dsh-agent'
import type { ContentBlock, StreamChunk } from '@deepseek-ai/dsh-llm'
import type { Session, SessionEvent } from '@deepseek-ai/dsh-session'
import { createStdioChat, type Config, type StdioRuntime } from '../src/stdio-chat.ts'
/**
* Unit tests for the stdio UI plugin. They drive the REAL plugin body
* (`createStdioChat`) with an injected {@link StdioRuntime} so every render,
* input, EOF, and disposal branch runs without touching the real `process`
* streams — the I/O seam is what makes the per-file gate reachable. The
* `agents` service is real (`@deepseek-ai/dsh-agent`); a minimal fake `Agent`
* stands in for the loop, since the loop is the genuinely expensive collaborator
* and we only need its `status` + `send`/`steer` surface here.
*/
/** A controllable stdin: a Readable we push lines into and can end on demand. */
function makeInput(): Readable & { feed(line: string): void; finish(): void } {
const stream = new Readable({ read() {} }) as Readable & { feed(line: string): void; finish(): void }
stream.feed = (line: string) => stream.push(`${line}\n`)
stream.finish = () => stream.push(null)
return stream
}
/** A stdout sink that accumulates everything written, for assertions. */
function makeOutput(): { write: (s: string) => boolean; text: () => string } {
let buf = ''
return { write: (s: string) => { buf += s; return true }, text: () => buf }
}
function makeRuntime(over: Partial<StdioRuntime> = {}): {
runtime: StdioRuntime
input: ReturnType<typeof makeInput>
out: ReturnType<typeof makeOutput>
exit: ReturnType<typeof vi.fn>
} {
const input = makeInput()
const out = makeOutput()
const exit = vi.fn()
return { runtime: { input, output: { write: out.write } as never, exit, ...over }, input, out, exit }
}
/** A minimal Agent fake exposing the surface the UI touches. */
function makeAgent(id: string, status: AgentStatus = 'idle'): Agent & {
status: AgentStatus
sent: ContentBlock[][]
steered: ContentBlock[][]
} {
const sent: ContentBlock[][] = []
const steered: ContentBlock[][] = []
return {
id: id as Agent['id'],
status,
sent,
steered,
// A minimal session stub: the UI reads only `session.header.id` (to map the
// session back to its agent id for the turn-boundary label).
session: { header: { id: `${id}-session` } },
send: (content: ContentBlock[]) => void sent.push(content),
steer: (content: ContentBlock[]) => void steered.push(content),
} as never
}
/** A session stub whose `header.id` matches an agent's, for `session/event` emits. */
function makeSession(agentId: string): Session {
return { header: { id: `${agentId}-session` } } as Session
}
/** An `assistant/chunk` session event carrying one raw stream chunk. */
function chunkEvent(chunk: StreamChunk): SessionEvent {
return { type: 'assistant/chunk', seq: 0, time: 0, data: { turn: 1, step: 0, chunk } }
}
const CONFIG: Config = { welcome: 'hi there', agent: 'main' }
async function setup(config: Config = CONFIG, runtimeOver: Partial<StdioRuntime> = {}) {
const ctx = new Context()
await ctx.plugin(AgentRegistry)
const { runtime, input, out, exit } = makeRuntime(runtimeOver)
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
createStdioChat(inner, config, runtime)
}, { inject: ['agents'] }))
return { ctx, fiber, input, out, exit }
}
/** Drive a fake idle timer past the 200ms flush delay. */
function flushExit(): Promise<void> {
return new Promise(resolve => setTimeout(resolve, 250))
}
describe('createStdioChat rendering', () => {
it('writes the welcome banner and prompt on start', async () => {
const { out } = await setup()
expect(out.text()).toBe('hi there\n> ')
})
it('falls back to default welcome/agent when called with empty config', async () => {
// createStdioChat is exported and may be driven directly (bypassing the
// Loader's schemastery validation), so it must default welcome/agent itself.
const { out } = await setup({})
expect(out.text()).toBe('ready.\n> ')
// And it drives the default agent id 'main'.
})
it('renders text-delta chunks verbatim', async () => {
const { ctx, out } = await setup()
ctx.emit('session/event', makeSession('main'), chunkEvent({ type: 'text-delta', index: 0, text: 'hello' }))
expect(out.text()).toContain('hello')
})
it('wraps reasoning-delta in the dim SGR and resets on the following text-delta', async () => {
const { ctx, out } = await setup()
const session = makeSession('main')
ctx.emit('session/event', session, chunkEvent({ type: 'reasoning-delta', index: 0, text: 'think' }))
ctx.emit('session/event', session, chunkEvent({ type: 'reasoning-delta', index: 0, text: 'more' }))
ctx.emit('session/event', session, chunkEvent({ type: 'text-delta', index: 0, text: 'answer' }))
expect(out.text()).toContain('\x1B[2mthinkmore\x1B[0m\nanswer')
})
it('ignores stream-chunk types it does not render', async () => {
const { ctx, out } = await setup()
const before = out.text()
ctx.emit('session/event', makeSession('main'), chunkEvent({ type: 'block-start', index: 0, blockType: 'text' }))
expect(out.text()).toBe(before)
})
it('renders turn/start and turn/end markers from the session feed', async () => {
const { ctx, out } = await setup()
const agent = makeAgent('main')
// agent/created populates the session-id → agent-id label map.
ctx.emit('agent/created', agent)
const session = makeSession('main')
ctx.emit('session/event', session, {
type: 'turn/start', seq: 1, time: 0, data: { turn: 3, trigger: { kind: 'message' } },
} as SessionEvent)
expect(out.text()).toContain('[main turn 3] ')
ctx.emit('session/event', session, {
type: 'turn/end', seq: 2, time: 0, data: { turn: 3, reason: { kind: 'completed' } },
} as SessionEvent)
expect(out.text()).toContain('\n> ')
})
it('falls back to the session id as the label when no agent is mapped', async () => {
const { ctx, out } = await setup()
// No agent/created emitted, so the label map is empty — the header id shows.
ctx.emit('session/event', makeSession('orphan'), {
type: 'turn/start', seq: 1, time: 0, data: { turn: 1, trigger: { kind: 'message' } },
} as SessionEvent)
expect(out.text()).toContain('[orphan-session turn 1] ')
})
it('seeds labels for agents already registered before the UI installs', async () => {
// The pre-created `main` agent (and any agent surviving an HMR reload of just
// this fiber) fired its `agent/created` before the UI's listener existed, so
// the live listener alone would miss it. Seeding from `ctx.agents.list()` at
// install time is what keeps its turn header showing `[main turn N]` instead
// of the raw session id.
const ctx = new Context()
await ctx.plugin(AgentRegistry)
const agent = makeAgent('main')
ctx.agents.register(agent) // registered BEFORE the UI plugin below
const { runtime, out } = makeRuntime()
await ctx.plugin(Object.assign((inner: Context) => {
createStdioChat(inner, CONFIG, runtime)
}, { inject: ['agents'] }))
ctx.emit('session/event', makeSession('main'), {
type: 'turn/start', seq: 1, time: 0, data: { turn: 5, trigger: { kind: 'message' } },
} as SessionEvent)
expect(out.text()).toContain('[main turn 5] ')
})
it('resets dim styling at turn/end if a turn ends mid-reasoning', async () => {
const { ctx, out } = await setup()
const session = makeSession('main')
ctx.emit('session/event', session, chunkEvent({ type: 'reasoning-delta', index: 0, text: 'mid' }))
ctx.emit('session/event', session, {
type: 'turn/end', seq: 1, time: 0, data: { turn: 1, reason: { kind: 'completed' } },
} as SessionEvent)
expect(out.text()).toContain('\x1B[2mmid\x1B[0m')
})
it('drops the label mapping on agent/disposed', async () => {
const { ctx, out } = await setup()
const agent = makeAgent('main')
ctx.emit('agent/created', agent)
ctx.emit('agent/disposed', agent)
// After disposal the map no longer resolves the agent id — fall back to the
// session header id.
ctx.emit('session/event', makeSession('main'), {
type: 'turn/start', seq: 1, time: 0, data: { turn: 1, trigger: { kind: 'message' } },
} as SessionEvent)
expect(out.text()).toContain('[main-session turn 1] ')
})
it('renders tool/call and tool/result session events', async () => {
const { ctx, out } = await setup()
const session = {} as Session
const callEvent = {
type: 'tool/call', seq: 1, time: 0,
data: { turn: 1, step: 0, callId: 'c1', name: 'bash', arguments: '{"command":"ls"}' },
} as SessionEvent
ctx.emit('session/event', session, callEvent)
expect(out.text()).toContain('[tool call] bash({"command":"ls"})')
const resultEvent = {
type: 'tool/result', seq: 2, time: 0,
data: { turn: 1, step: 0, callId: 'c1', content: [{ type: 'text', text: 'file.txt' }], isError: false },
} as SessionEvent
ctx.emit('session/event', session, resultEvent)
expect(out.text()).toContain('[tool result] file.txt')
})
it('renders a todo/write session event as a glyphed checklist', async () => {
const { ctx, out } = await setup()
const session = {} as Session
ctx.emit('session/event', session, {
type: 'todo/write', seq: 1, time: 0,
data: { todos: [
{ content: 'read the code', status: 'completed' },
{ content: 'write the fix', status: 'in_progress' },
{ content: 'run the tests', status: 'pending' },
] },
} as SessionEvent)
const text = out.text()
expect(text).toContain('[todos]')
expect(text).toContain('[x] read the code')
expect(text).toContain('[~] write the fix')
expect(text).toContain('[ ] run the tests')
})
it('resets dim styling when a todo/write interrupts reasoning', async () => {
const { ctx, out } = await setup()
ctx.emit('session/event', {} as Session, chunkEvent({ type: 'reasoning-delta', index: 0, text: 'r' }))
ctx.emit('session/event', {} as Session, {
type: 'todo/write', seq: 1, time: 0,
data: { todos: [{ content: 'a task', status: 'pending' }] },
} as SessionEvent)
expect(out.text()).toContain('\x1B[2mr\x1B[0m')
})
it('resets dim styling when a tool/call interrupts reasoning', async () => {
const { ctx, out } = await setup()
const session = {} as Session
ctx.emit('session/event', session, chunkEvent({ type: 'reasoning-delta', index: 0, text: 'r' }))
ctx.emit('session/event', session, {
type: 'tool/call', seq: 1, time: 0,
data: { turn: 1, step: 0, callId: 'c1', name: 'bash', arguments: '{}' },
} as SessionEvent)
expect(out.text()).toContain('\x1B[2mr\x1B[0m')
})
it('ignores session events it does not render', async () => {
const { ctx, out } = await setup()
const before = out.text()
ctx.emit('session/event', {} as Session, {
type: 'user/message', seq: 1, time: 0,
data: { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } },
} as SessionEvent)
expect(out.text()).toBe(before)
})
})
describe('createStdioChat input', () => {
it('sends a typed line to an idle agent', async () => {
const { ctx, input } = await setup()
const agent = makeAgent('main', 'idle')
ctx.agents.register(agent)
input.feed('do a thing')
await new Promise(r => setImmediate(r))
expect(agent.sent).toEqual([[{ type: 'text', text: 'do a thing' }]])
expect(agent.steered).toEqual([])
})
it('steers a typed line into a running agent', async () => {
const { ctx, input } = await setup()
const agent = makeAgent('main', 'running')
ctx.agents.register(agent)
input.feed('steer me')
await new Promise(r => setImmediate(r))
expect(agent.steered).toEqual([[{ type: 'text', text: 'steer me' }]])
expect(agent.sent).toEqual([])
})
it('ignores blank lines', async () => {
const { ctx, input } = await setup()
const agent = makeAgent('main')
ctx.agents.register(agent)
input.feed(' ')
await new Promise(r => setImmediate(r))
expect(agent.sent).toEqual([])
})
it('logs and drops a line when the target agent is not running', async () => {
const { ctx, input } = await setup()
const spy = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {})
input.feed('nobody home')
await new Promise(r => setImmediate(r))
expect(spy).toHaveBeenCalledWith('ui-stdio: agent "%s" is not running', 'main')
})
it('drives the agent named in config, not a hardcoded id', async () => {
const { ctx, input } = await setup({ welcome: 'w', agent: 'worker' })
const agent = makeAgent('worker')
ctx.agents.register(agent)
input.feed('hi')
await new Promise(r => setImmediate(r))
expect(agent.sent).toHaveLength(1)
})
})
describe('createStdioChat EOF exit', () => {
it('exits immediately on EOF when no work was submitted', async () => {
const { input, exit } = await setup()
input.finish()
await flushExit()
expect(exit).toHaveBeenCalledWith(0)
})
it('waits for the agent to settle idle after running before exiting', async () => {
const { ctx, input, exit } = await setup()
const agent = makeAgent('main', 'idle')
ctx.agents.register(agent)
input.feed('work')
await new Promise(r => setImmediate(r))
input.finish()
await new Promise(r => setImmediate(r))
// Work submitted but no 'running' observed yet — must NOT exit.
expect(exit).not.toHaveBeenCalled()
// The turn starts, then settles.
ctx.emit('agent/status', agent, 'running')
;(agent as { status: AgentStatus }).status = 'idle'
ctx.emit('agent/status', agent, 'idle')
await flushExit()
expect(exit).toHaveBeenCalledWith(0)
})
it('schedules the exit only once when idle fires repeatedly', async () => {
const { ctx, input, exit } = await setup()
const agent = makeAgent('main', 'running')
ctx.agents.register(agent)
input.feed('work')
await new Promise(r => setImmediate(r))
ctx.emit('agent/status', agent, 'running') // sawRunning = true
input.finish()
await new Promise(r => setImmediate(r)) // let readline 'close' set stdinClosed
;(agent as { status: AgentStatus }).status = 'idle'
// Two idle signals while stdin is already closed: the first arms the timer,
// the second must hit the already-scheduled guard, not arm a second.
ctx.emit('agent/status', agent, 'idle')
ctx.emit('agent/status', agent, 'idle')
await flushExit()
expect(exit).toHaveBeenCalledTimes(1)
})
it('does not exit on an idle transition for a different agent', async () => {
const { ctx, input, exit } = await setup()
const agent = makeAgent('main', 'idle')
ctx.agents.register(agent)
input.feed('work')
await new Promise(r => setImmediate(r))
input.finish()
const other = makeAgent('other')
ctx.emit('agent/status', other, 'running')
ctx.emit('agent/status', other, 'idle')
await flushExit()
expect(exit).not.toHaveBeenCalled()
})
it('does not exit while a turn is still running at EOF', async () => {
const { ctx, input, exit } = await setup()
const agent = makeAgent('main', 'idle')
ctx.agents.register(agent)
input.feed('work')
await new Promise(r => setImmediate(r))
ctx.emit('agent/status', agent, 'running')
;(agent as { status: AgentStatus }).status = 'running'
input.finish()
// sawRunning is true, but the agent is still running — the idle gate holds.
ctx.emit('agent/status', agent, 'idle') // a stale/duplicate signal while status stays 'running'
await flushExit()
expect(exit).not.toHaveBeenCalled()
})
})
describe('createStdioChat disposal (HMR safety)', () => {
it('never exits the process when EOF arrives after fiber dispose', async () => {
const { fiber, input, exit } = await setup()
await fiber.dispose()
// A late EOF after disposal (reader.close() also fires 'close') must not exit.
input.finish()
await flushExit()
expect(exit).not.toHaveBeenCalled()
})
it('cancels a scheduled exit if disposed within the flush window', async () => {
const { fiber, input, exit } = await setup()
// EOF with no work submitted schedules the 200ms flush-then-exit timer.
input.finish()
await new Promise(r => setImmediate(r))
expect(exit).not.toHaveBeenCalled() // not yet — still inside the window
// Dispose BEFORE the timer fires: the tracked handle must be cleared.
await fiber.dispose()
await flushExit()
expect(exit).not.toHaveBeenCalled()
})
it('stops handling input after dispose', async () => {
const { ctx, fiber, input } = await setup()
const agent = makeAgent('main')
ctx.agents.register(agent)
await fiber.dispose()
// The readline interface is closed on dispose; a late line reaches no handler.
input.feed('too late')
await new Promise(r => setImmediate(r))
expect(agent.sent).toEqual([])
})
it('removes the agent/status listener on dispose', async () => {
const { ctx, fiber, input, exit } = await setup()
const agent = makeAgent('main', 'idle')
ctx.agents.register(agent)
input.feed('work')
await new Promise(r => setImmediate(r))
await fiber.dispose()
// After dispose, status transitions must neither throw nor schedule an exit
// (the listener and the EOF-exit path are both torn down).
expect(() => {
ctx.emit('agent/status', agent, 'running')
ctx.emit('agent/status', agent, 'idle')
}).not.toThrow()
await flushExit()
expect(exit).not.toHaveBeenCalled()
})
})

View File

@@ -17,6 +17,9 @@
{
"path": "../../../vendor/loader"
},
{
"path": "../app-boot"
},
{
"path": "../../../vendor/logger-console"
},
@@ -31,9 +34,6 @@
},
{
"path": "../../session-persistence/session-persistence-jsonl"
},
{
"path": "../../support/ui-stdio"
}
]
}