Merge master into codex/grep-glob-require-rg

This commit is contained in:
Tianyi Cui
2026-07-17 21:25:37 +08:00
1149 changed files with 61193 additions and 21544 deletions

View File

@@ -11,7 +11,7 @@ The REPL agent demo wiring: DeepSeek V4 + the `read`/`write`/`edit` filesystem t
pnpm run demo:repl
```
Type a coding task. The agent works through the `read`/`write`/`edit` filesystem tools for ordinary file operations and `bash` (+ `bash_output` / `bash_kill` for background tasks) for shell commands, searches, and test runs, each in a fresh `bash -c` (the system prompt tells the model to pass `workdir` instead of `cd`). Both the fs tools and bash resolve relative paths against the session workspace. It can also delegate with `subagent`/`subagent_fork` and track multi-step work with `todo_write` (a whole-list task tracker rendered as a checklist). Reasoning streams dimmed; tool calls/results render inline.
Type a coding task. The agent works through the `read`/`write`/`edit` filesystem tools for ordinary file operations and `bash` (+ the generic `task_output` / `task_list` / `task_kill` for background tasks) for shell commands, searches, and test runs, each in a fresh `bash -c` (the system prompt tells the model to pass `workdir` instead of `cd`). Both the fs tools and bash resolve relative paths against the session workspace. It can also delegate with `subagent`/`subagent_fork` and track multi-step work with `todo_write` (a whole-list task tracker rendered as a checklist). Reasoning streams dimmed; tool calls/results render inline.
```
> fix the failing test in /path/to/project
@@ -33,7 +33,7 @@ The id is wired through `cordis.yml` (`resumeSessionId: !!js process.env.RESUME_
## Code Mode
[`code-mode.cordis.yml`](code-mode.cordis.yml) is this same tree flipped to [Code Mode](../../docs/rfc/implemented/feature/2026-06-15-code-mode.md): an include overlay over `./cordis.yml` whose two patches insert the worker-thread code runtime (`@deepseek-ai/dsh-code-runtime-worker`, registering `ctx.codeRuntime`) and set `tools: { mode: code }` on the app. The registry contributes exactly one reserved wire transport — `run_code` plus a generated TypeScript SDK section declaring the visible end-capability tools. The model composes those capabilities by writing a program; each program call carries an immutable link to its enclosing transport, bridges back through pre-policy, monotonic guards, around dispatch, post-policy, and final-result observation one at a time, and is logged as a `tool/code-dispatch` session event. Only what the program prints or returns re-enters model context. (Flip the mode to `both` to offer native calls and `run_code` side by side.)
[`code-mode.cordis.yml`](code-mode.cordis.yml) overlays the same tree with the worker-thread runtime and `tools: { mode: code }`. The model receives one `run_code` transport plus a generated TypeScript SDK for the visible tools; only program output returns to model context. Use `mode: both` to expose native calls alongside `run_code`. See the [Code Mode RFC](../../docs/rfc/implemented/feature/2026-06-15-code-mode.md) for the execution contract.
```sh
pnpm run demo:code-mode # this overlay under the REPL (default UI)
@@ -48,14 +48,14 @@ and watch the transcript: one `run_code` call, a program looping over tools, and
## What each leaf entry demonstrates
This example is a thin leaf `cordis.yml`: it picks the swappable backends, loads one app package, and adds product tools that are intentionally outside the shared spine. The spine (sessions, system-prompt, tools, agents, invariants, `agent-loop`) and the front-door cluster (console logger, JSONL persistence, readline UI, the pre-created `main` agent) live inside the [`@deepseek-ai/dsh-stdio-agent`](../../packages/ui/stdio-agent) app and the [`@deepseek-ai/dsh-agent-core`](../../packages/core/agent-core) bundle it loads; the leaf wires the backends and model-facing optional tools:
This example is a thin leaf `cordis.yml`: it picks the swappable backends, loads one app package, and adds product tools that are intentionally outside the shared spine. The spine (sessions, system-prompt, tools, agents, invariants, `agent-loop`) and the front-door cluster (console logger, JSONL persistence, readline UI, the pre-created `main` agent) live inside the [`@deepseek-ai/dsh-stdio-demo`](../../packages/examples/stdio-demo) app and the [`@deepseek-ai/dsh-agent-spine-demo`](../../packages/examples/agent-spine-demo) bundle it loads; the leaf wires the backends and model-facing optional tools:
| Entry | Demonstrates |
|---|---|
| `hmr` (`@cordisjs/plugin-hmr`) | the dev/demo edit-reload loop — a **leaf** entry (not baked into the app) because it is Loader-only and needs `node --expose-internals`, which `demo:repl` passes |
| `llm-deepseek` | real `LlmAdapter` via config (`!!js process.env.…` secrets); swap one line to `@deepseek-ai/dsh-llm-pi-ai` for the library-backed twin |
| `bash` (`dsh-bash-local`) | the executor implementation — the swappable half of the bash seam. The model-facing `bash`/`bash_output`/`bash_kill` tool schemas (`tool-bash`) come from `agent-core`, so only the executor is a leaf choice |
| `stdio-agent` (`@deepseek-ai/dsh-stdio-agent`) | the app bundle: the agent-core spine + console logger + JSONL persistence + readline UI + a pre-created `main` agent. Its config carries the model, system prompt, `persistenceRoot` (`./.sessions`), and `resumeSessionId` — so persistence and the agent are configured here, not wired as separate leaf plugins |
| `bash` (`dsh-bash-local`) | the executor implementation — the swappable half of the bash seam. The model-facing `bash` schema (`tool-bash`) and generic `task_*` controls (`tool-tasks`) come from `dsh-agent-spine-demo`, so only the executor is a leaf choice |
| `stdio-agent` (`@deepseek-ai/dsh-stdio-demo`) | the app bundle: the agent-spine demo + console logger + JSONL persistence + readline UI + a pre-created `main` agent. Its config carries the model, system prompt, `persistenceRoot` (`./.sessions`), and `resumeSessionId` — so persistence and the agent are configured here, not wired as separate leaf plugins |
| `subagent`, `subagent-spawn`, `subagent-fork` | the subagent provider registry plus the two in-process backends: a fresh child and a child seeded with the parent's completed-turn prefix |
| `tool-subagent`, `tool-subagent-fork` | two model-facing `dsh-tool-subagent` loads, each bound to a different provider and exposed under a distinct tool name (`subagent`, `subagent_fork`) |
| `tool-todo` | the model-facing `todo_write` tool; writes the whole task list to the session log and renders as a checklist in stdio |

View File

@@ -1,24 +1,21 @@
# Code Mode overlay: the live coding-agent tree (./cordis.yml) with two
# load-time patches — the app entry's config gains `tools: { mode: code }`
# (the registry offers exactly one wire tool, run_code, plus the generated
# TypeScript SDK prompt section declaring bash/read/write/edit/subagent/
# todo_write) and the worker-thread code runtime joins the tree as
# `ctx.codeRuntime`. The dsh-stdio-agent bin boots this file for
# `pnpm run demo:code-mode` (the acp-agent example carries the same-shaped
# overlay for the `acp` UI). A config patch REPLACES the entry's whole
# config, so the base entry's fields are restated verbatim; only `tools`,
# the welcome, and the persona's second paragraph are Code Mode deltas.
# Code Mode adds `ctx.codeRuntime` and changes the registry to one wire tool,
# `run_code`, plus a generated SDK for bash/read/write/edit/subagent/todo_write.
# `demo:code-mode` selects this overlay; the ACP example has the same UI-specific
# shape. A config patch replaces the whole app config, so unchanged base fields
# are restated; only `tools`, `welcome`, and the persona's second paragraph differ.
- id: base
name: '@cordisjs/plugin-include'
config:
path: ./cordis.yml
patches:
- id: stdio-agent
name: '@deepseek-ai/dsh-stdio-agent'
name: '@deepseek-ai/dsh-stdio-demo'
config:
model: deepseek-v4-flash
resumeSessionId: !!js process.env.RESUME_SESSION_ID
persistenceRoot: './.sessions'
workspaceContext:
maxBytes: 65536
tools:
mode: code
welcome: 'code-mode agent ready. Give it a multi-tool task.'

View File

@@ -14,9 +14,9 @@ flowchart LR
cfg --> plugin_coding_llm_deepseek
plugin_coding_bash["bash<br/>@deepseek-ai/dsh-bash-local"]
cfg --> plugin_coding_bash
plugin_coding_stdio_agent["stdio-agent<br/>@deepseek-ai/dsh-stdio-agent"]
plugin_coding_stdio_agent["stdio-agent<br/>@deepseek-ai/dsh-stdio-demo"]
cfg --> plugin_coding_stdio_agent
plugin_coding_stdio_agent --> bundle_agent_core["@deepseek-ai/dsh-agent-core"]
plugin_coding_stdio_agent --> bundle_agent_core["@deepseek-ai/dsh-agent-spine-demo"]
plugin_coding_stdio_agent --> bundle_jsonl["@deepseek-ai/dsh-session-persistence-jsonl"]
plugin_coding_stdio_agent --> frontdoor_stdio["readline UI<br/>console logger<br/>pre-created main agent"]
bundle_agent_core --> spine_llm["ctx.llm"]
@@ -62,7 +62,7 @@ flowchart LR
| `hmr` | `@cordisjs/plugin-hmr` |
| `llm-deepseek` | `@deepseek-ai/dsh-llm-deepseek` |
| `bash` | `@deepseek-ai/dsh-bash-local` |
| `stdio-agent` | `@deepseek-ai/dsh-stdio-agent` |
| `stdio-agent` | `@deepseek-ai/dsh-stdio-demo` |
| `compact-basic` | `@deepseek-ai/dsh-compact-basic` |
| `subagent` | `@deepseek-ai/dsh-subagent` |
| `subagent-spawn` | `@deepseek-ai/dsh-subagent-spawn` |

View File

@@ -1,15 +1,9 @@
# The coding-agent plugin tree: the REPL agent demo. The two swappable
# backends — the DeepSeek adapter and the local bash executor — plus `hmr` for
# the dev/demo reload loop, then the stdio chat app (@deepseek-ai/dsh-stdio-
# agent), which bundles the whole agent-core spine (timer, llm, sessions,
# system-prompt, tools, agents, invariants, tool-bash, agent-loop), the console
# logger, JSONL persistence, the readline UI, and a pre-created `main` agent.
#
# `hmr` is a leaf entry (not baked into dsh-stdio-agent): it is a Loader-only
# dev plugin that needs `--expose-internals` — the `demo:repl` script passes
# it. Requires DEEPSEEK_API_KEY (and optionally DEEPSEEK_BASE_URL) in the
# environment — the dsh-stdio-agent bin loads the gitignored repo-root .env
# first. cordis.yml reads them via the `!!js` tag.
# REPL agent with swappable DeepSeek and local-bash backends. `dsh-stdio-demo`
# supplies the agent spine, workspace instructions, generic task controls,
# logging, JSONL persistence, readline UI, and `main` agent.
# HMR remains a leaf because it requires Loader internals; `demo:repl` passes
# `--expose-internals`. The app bin loads the gitignored root `.env`; this file
# reads `DEEPSEEK_API_KEY` and optional `DEEPSEEK_BASE_URL` through `!!js`.
# Hot-module reload for the dev/demo loop (needs `node --expose-internals`).
- id: hmr
@@ -28,38 +22,34 @@
- deepseek-v4-pro
- deepseek-v4-flash
# Local bash executor for agent-core's tool-bash schema (one of several tool
# stacks in this tree: filesystem, subagent, and todo_write load below).
# Local executor for the app bundle's bash tool.
- id: bash
name: '@deepseek-ai/dsh-bash-local'
config:
timeoutMs: 60000
# The stdio chat app: the whole spine + front-door cluster, configured for a
# REPL agent demo driving a pre-created `main` agent.
# The app bundle pre-creates the REPL's `main` agent.
- id: stdio-agent
name: '@deepseek-ai/dsh-stdio-agent'
name: '@deepseek-ai/dsh-stdio-demo'
config:
model: deepseek-v4-flash
# Set RESUME_SESSION_ID to continue a prior persisted session (the ids live
# under ./.sessions); unset starts a fresh session each run.
resumeSessionId: !!js process.env.RESUME_SESSION_ID
persistenceRoot: './.sessions'
workspaceContext:
maxBytes: 65536
welcome: 'agent REPL ready. Give it a coding task.'
# The persona: identity + behavior only, nothing about transports or
# tooling — tool guidance lives with each tool plugin (descriptions +
# prompt sections). {{model}} is the prompt variable the agent loop
# resolves from this agent's configured model.
# Keep the persona to identity and behavior; tool plugins own tool guidance.
# The loop resolves {{model}} from this agent's configuration.
persona: |
You are coding-agent, a coding assistant powered by the {{model}} model.
Verify your work by running the code or tests. Keep answers brief and
factual.
# Automatic context compaction: when the derived history approaches the model's
# context window, summarize an older range into a checkpoint so a long-running
# or tool-heavy session keeps fitting. A leaf entry (needs ctx.llm + the
# agent-loop's `agent/pre-step` seam from the app above).
# Summarize an older range when derived history approaches the context window.
# This leaf consumes `ctx.llm` and the app's `agent/pre-step` seam.
- id: compact-basic
name: '@deepseek-ai/dsh-compact-basic'
config:
@@ -70,13 +60,9 @@
maxTokens: 8192
compactionRetries: 1
# The subagent seam + BOTH in-process backends + two model-facing tools, as leaf
# entries after the app (which provides ctx.agents/ctx.tools). spawn (a fresh
# child) and fork (a child seeded with the parent's completed-turn prefix) are
# independent backends over the shared dsh-subagent-inprocess driver. Exposing
# both transports is pure config: load each backend, then load dsh-tool-subagent
# once per backend with a distinct toolName (the tool registry rejects a
# duplicate name) — no code change.
# Expose fresh-child `spawn` and completed-prefix `fork` through independent
# in-process backends. Each tool instance needs a distinct `toolName`; the registry
# rejects duplicates. These leaves follow the app because it provides `ctx.agents` and `ctx.tools`.
- id: subagent
name: '@deepseek-ai/dsh-subagent'
@@ -103,10 +89,8 @@
toolName: subagent_fork
# Dynamic workflows: the worker-thread engine (ctx.workflows) over the spawn
# subagent backend above, plus the model-facing `workflow` tool. The model
# writes a JavaScript orchestration script (meta + body); the engine runs it
# in its own worker thread and fans agent() calls out as spawn children.
# The worker-thread workflow engine fans a model-written JavaScript script's
# `agent()` calls out through the spawn backend; the adjacent tool exposes it to the model.
- id: workflow-workerthread
name: '@deepseek-ai/dsh-workflow-workerthread'
config:
@@ -114,14 +98,12 @@
- id: tool-workflow
name: '@deepseek-ai/dsh-tool-workflow'
# The model-facing todo_write tool: whole-list task tracking written to the
# session log (todo/write), rendered as a stdio checklist / ACP plan.
# `todo_write` replaces the logged whole list and renders as a stdio checklist or ACP plan.
- id: tool-todo
name: '@deepseek-ai/dsh-tool-todo'
# Filesystem capability stack: local provider, read-before-write/edit policy
# gate, then the model-facing read/write/edit tools. stdio-agent is a single
# session, so relative paths resolve from the process cwd (the workspace).
# Policy loads before the model-facing filesystem tools so writes and edits require
# an observed file. This single-session app resolves relative paths from the process cwd.
- id: fs-local
name: '@deepseek-ai/dsh-fs-local'
config:

View File

@@ -1,99 +1,27 @@
import { spawn, type ChildProcessWithoutNullStreams } from 'node:child_process'
import { mkdtemp, rm } 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 { describe, expect, it } from 'vitest'
import { LOADER_SMOKE_TEST_TIMEOUT_MS, runLoaderSmoke } from '@deepseek-ai/dsh-loader-smoke'
/**
* Keyless Loader-path smoke for the Code Mode overlay: boot the REAL
* example through the `@deepseek-ai/dsh-stdio-agent` bin against
* `code-mode.cordis.yml` (the cordis Loader, `unwrapExports`, the include
* patches over ./cordis.yml, the worker-thread code runtime, and the
* registry in `mode: code`), then close stdin with no prompt and assert
* the Code Mode banner + a clean exit.
*
* No prompt is ever sent, so the model is NEVER called and no `run_code`
* turn happens — a dummy key lets `llm-deepseek`'s key-PRESENT check boot
* the tree. This is the export-shape guard (postmortem 0001) for the Code
* Mode composition; the with-key proof lives in `code-mode.e2e.ts`.
* Keyless Loader-path smoke for the Code Mode overlay: boot the real include
* tree through stdio-agent and `code-mode.cordis.yml`, then close stdin without
* a prompt and assert the banner. No model or `run_code` turn runs.
*/
const binScript = fileURLToPath(new URL('../../../packages/ui/stdio-agent/src/bin.ts', import.meta.url))
const binScript = fileURLToPath(new URL('../../../packages/examples/stdio-demo/src/bin.ts', import.meta.url))
const configPath = fileURLToPath(new URL('../code-mode.cordis.yml', import.meta.url))
const tsxLoader = fileURLToPath(import.meta.resolve('tsx'))
// Dev/test run UNBUILT: resolve `@deepseek-ai/dsh-*` through the root tsconfig
// `paths` map; tsx searches UP from cwd, and we spawn from a temp dir outside
// the repo, so point it at the repo tsconfig.
const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
// The real-API workflow runs up to 14 e2e files at once. Cold tsx/Loader
// startup can therefore outlive a tight smoke-test deadline before the child
// emits any output; 30s still detects a wedged process without confusing
// bounded CI contention with a lifecycle failure.
const PROCESS_TIMEOUT_MS = 30_000
// Leave enough room for the process-owned timeout to report captured output
// before Vitest aborts the test itself.
const TEST_TIMEOUT_MS = PROCESS_TIMEOUT_MS + 15_000
let child: ChildProcessWithoutNullStreams | undefined
let workdir: string | undefined
afterEach(async () => {
if (child !== undefined && child.exitCode === null) child.kill('SIGKILL')
child = undefined
if (workdir !== undefined) await rm(workdir, { recursive: true, force: true })
workdir = undefined
})
async function bootAndEof(): Promise<{ stdout: string; code: number }> {
workdir = await mkdtemp(join(tmpdir(), 'code-mode-smoke-'))
const cwd = workdir
return new Promise((resolve, reject) => {
const proc = spawn(
process.execPath,
// --expose-internals: the included cordis.yml loads the HMR plugin (mirrors demo:code-mode).
['--expose-internals', '--import', tsxLoader, binScript, configPath],
{
cwd,
env: {
...process.env,
TSX_TSCONFIG_PATH: repoTsconfig,
// A dummy key so llm-deepseek's apply() (key-PRESENT check only) boots.
// No prompt is sent, so the adapter never streams — no network call.
DEEPSEEK_API_KEY: 'keyless-smoke-no-call',
},
stdio: ['pipe', 'pipe', 'pipe'],
},
)
child = proc
let stdout = ''
let stderr = ''
proc.stdout.setEncoding('utf8')
proc.stdout.on('data', (chunk: string) => { stdout += chunk })
proc.stderr.setEncoding('utf8')
proc.stderr.on('data', (chunk: string) => { stderr += chunk })
const timer = setTimeout(() => {
proc.kill('SIGKILL')
reject(new Error(`code-mode overlay did not exit within ${PROCESS_TIMEOUT_MS / 1_000}s. stdout:\n${stdout}\nstderr:\n${stderr}`))
}, PROCESS_TIMEOUT_MS)
proc.on('exit', (code) => {
clearTimeout(timer)
if (code === 0) resolve({ stdout, code })
else reject(new Error(`code-mode overlay exited ${code}. stderr:\n${stderr}`))
})
proc.on('error', (err) => { clearTimeout(timer); reject(err) })
// No prompt — just EOF, so the stdio UI exits without ever running a turn.
proc.stdin.end()
})
}
const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
describe('code-mode overlay keyless smoke (real code-mode.cordis.yml via the Loader)', () => {
it('boots the Code Mode plugin tree, prints its banner, and exits cleanly on EOF', async () => {
const { stdout, code } = await bootAndEof()
expect(code).toBe(0)
const { stdout } = await runLoaderSmoke({
label: 'code-mode overlay',
tempDirPrefix: 'code-mode-smoke-',
binScript,
configPath,
tsconfigPath,
env: { DEEPSEEK_API_KEY: 'keyless-smoke-no-call' },
})
expect(stdout).toContain('code-mode agent ready.')
}, TEST_TIMEOUT_MS)
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
})

View File

@@ -1,10 +1,10 @@
import { mkdtemp, readFile, rm } from 'node:fs/promises'
import { mkdtemp, mkdir, readFile, rm, writeFile } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { afterEach, describe, expect, it } from 'vitest'
import { Context } from 'cordis'
import LlmService from '@deepseek-ai/dsh-llm'
import SessionStore from '@deepseek-ai/dsh-session'
import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
import type { SessionEvent } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { RUN_CODE_NAME } from '@deepseek-ai/dsh-tools'
@@ -14,20 +14,19 @@ import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
import * as ToolBash from '@deepseek-ai/dsh-tool-bash'
import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
import { WorkerCodeRuntime } from '@deepseek-ai/dsh-code-runtime-worker'
import LocalFileSystem from '@deepseek-ai/dsh-fs-local'
import * as ToolFs from '@deepseek-ai/dsh-tool-fs'
import * as WorkspaceContext from '@deepseek-ai/dsh-workspace-context'
/**
* The Code Mode with-key proof (the RFC's e2e tier): a REAL model under
* `mode: 'code'`, a task that requires composing two tool calls, verified
* against the WORLD — the persisted request header carried exactly
* `[run_code]` as the wire tool list, each sub-call landed as a
* `tool/code-dispatch` event, the file the program wrote exists on disk, and
* the final answer is the program's curated output. Key-gated (see
* vitest.e2e.config.ts); the keyless Loader-path smoke of the overlay lives
* in `code-mode-keyless-smoke.e2e.ts`.
* With-key Code Mode proof: a real model receives only `run_code`, composes two
* sub-calls, writes a file, and returns curated output while the log records
* each `tool/code-dispatch`. The keyless Loader smoke is in the sibling test.
*/
const PERSONA = 'You are coding-agent. You work by writing TypeScript programs for run_code: '
+ 'batch related tool work into one program and print or return ONLY the findings that matter.'
const WORKSPACE_PROBE = 'dragonfruit-8675309'
let ctx: Context | undefined
let workdir: string | undefined
@@ -57,6 +56,22 @@ async function codeModeHarness(cwd: string): Promise<Context> {
return harness
}
async function workspaceCodeModeHarness(): Promise<Context> {
const harness = new Context()
await harness.plugin(LlmService)
await harness.plugin(SessionStore)
await harness.plugin(SystemPrompt, { persona: PERSONA })
await harness.plugin(ToolRegistry, { mode: 'code' })
await harness.plugin(AgentRegistry)
await harness.plugin(LocalFileSystem, { cwd: '/' })
await harness.plugin(ToolFs)
await harness.plugin(WorkspaceContext, { maxBytes: 65536 })
await harness.plugin(AgentLoop, { agents: [] })
await harness.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] })
await harness.plugin(WorkerCodeRuntime, {})
return harness
}
function waitForIdle(harness: Context, agent: ReactLoopAgent): Promise<void> {
return new Promise((resolve) => {
const dispose = harness.on('agent/status', (subject, status) => {
@@ -112,4 +127,43 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p
expect(finalText).toContain('alpha-7')
expect(finalText).toContain('beta-9')
}, 180_000)
it('delivers nested workspace instructions discovered by an fs sub-call after the outer result', async () => {
workdir = await mkdtemp(join(tmpdir(), 'dsh-code-mode-workspace-e2e-'))
await mkdir(join(workdir, '.git'), { recursive: true })
await mkdir(join(workdir, 'pkg/deep'), { recursive: true })
await writeFile(join(workdir, 'pkg/AGENTS.md'), `If asked for the Code Mode workspace handshake, reply with exactly ${WORKSPACE_PROBE} and nothing else.\n`)
await writeFile(join(workdir, 'pkg/deep/task.txt'), 'Touch this file to discover the nested instructions.\n')
ctx = await workspaceCodeModeHarness()
const handle = await ctx.agents.create({
agentId: AgentId('e2e-code-mode-workspace'),
sessionId: SessionId('e2e-code-mode-workspace-session'),
meta: { cwd: workdir },
agentOptions: { model: 'deepseek-v4-flash' },
})
handle.agent.send([{
type: 'text',
text: 'Use one run_code program to call tools.read on pkg/deep/task.txt. After it finishes, answer: Code Mode workspace handshake?',
}])
await waitForIdle(ctx, handle.agent as ReactLoopAgent)
const events: SessionEvent[] = [...handle.agent.session.events]
const dispatch = events.find(event => event.type === 'tool/code-dispatch' && event.data.name === 'read')
const outerResult = events.find(event => event.type === 'tool/result')
const workspaceContext = events.find(event => event.type === 'context/message'
&& typeof event.data.meta === 'object'
&& event.data.meta !== null
&& !Array.isArray(event.data.meta)
&& event.data.meta.kind === 'workspace-instructions')
expect(dispatch).toBeDefined()
expect(outerResult).toBeDefined()
expect(workspaceContext).toBeDefined()
expect(workspaceContext!.seq).toBeGreaterThan(outerResult!.seq)
const finalMessage = events.findLast(event => event.type === 'assistant/message')
const answer = finalMessage?.type === 'assistant/message'
? finalMessage.data.content.filter(block => block.type === 'text').map(block => block.text).join('')
: ''
expect(answer).toContain(WORKSPACE_PROBE)
}, 180_000)
})

View File

@@ -7,25 +7,11 @@ import { AgentId } from '@deepseek-ai/dsh-agent'
import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts'
/**
* The compaction smoke test: a real model runs a multi-step bash task with a
* deliberately tiny context window, so the auto-compaction listener fires
* MID-SESSION and summarizes the older history into a checkpoint. This is the
* first end-to-end exercise of the compaction seam (it is wired nowhere else),
* and the runaway-survival regression net — it proves a session that grows past
* the window keeps running rather than overflowing. Key-gated.
*
* Verifies the WORLD, not the agent's self-report: a compact/start…end pair
* landed in the real session log, the surface actually shrank (a replace node
* exists and shadowed older nodes), and the agent still produced a final answer
* after compaction (so the summarized history did not break the conversation).
*
* FIXME(compaction-snapshot): this key-gated e2e is the ONLY coverage of runaway
* compaction — there is no keyless full-transcript snapshot of it. dsh-llm-replay
* reconstructs one model call per (turn, step) from `assistant/chunk` events, but
* `summarize()` assembles its stream into a local BlockAssembler and appends no
* `assistant/chunk`, so the interleaved summarization call is unreplayable. A
* snapshot needs replay-harness work to serve that call; deferred as a follow-up.
* Key-gated smoke for mid-session compaction. It verifies the compact event
* pair, replacement of older surface nodes, and a final answer after compaction.
*/
// FIXME(compaction-snapshot): this is the only full compaction coverage because
// replay cannot serve the summarizer's unlogged model call.
let workdir: string | undefined
let ctx: Context | undefined
@@ -40,18 +26,11 @@ afterEach(async () => {
describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compacts mid-flight and keeps running', () => {
it('summarizes older history into a checkpoint without breaking the task', async () => {
workdir = await mkdtemp(join(tmpdir(), 'dsh-compaction-'))
// A handful of files for the model to read, so multiple bash steps
// accumulate surface nodes (tool calls + results) and grow the history past
// the (deliberately tiny) window.
for (let i = 1; i <= 4; i++) {
await writeFile(join(workdir, `file${i}.txt`), `This is file number ${i}. `.repeat(50))
}
// Tiny window so a couple of steps crosses the threshold. The generation
// cap is deliberately larger than the final checkpoint because
// reasoning-capable APIs count reasoning tokens against the provider output
// budget even though those blocks are stripped before the checkpoint is
// stored.
// Reasoning tokens require a larger generation cap than the retained checkpoint.
ctx = await codingHarness(workdir, {
persona: SYSTEM_PROMPT,
compact: {

View File

@@ -1,11 +1,7 @@
import { Context } from 'cordis'
import LlmService from '@deepseek-ai/dsh-llm'
import SessionStore from '@deepseek-ai/dsh-session'
import type { SessionEvent } 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, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit'
import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
import * as ToolBash from '@deepseek-ai/dsh-tool-bash'
import * as ToolTodo from '@deepseek-ai/dsh-tool-todo'
@@ -50,11 +46,9 @@ export interface CodingHarnessOptions {
export async function codingHarness(workdir: string, options: CodingHarnessOptions = {}): Promise<Context> {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt, { persona: options.persona ?? '' })
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await mountAgentLoopTestDependencies(ctx, {
systemPrompt: { persona: options.persona ?? '' },
})
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] })
await ctx.plugin(LocalBashExecutor, { cwd: workdir, timeoutMs: 30_000 })

View File

@@ -1,110 +1,28 @@
import { spawn, type ChildProcessWithoutNullStreams } from 'node:child_process'
import { mkdtemp, rm } 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 { describe, expect, it } from 'vitest'
import { LOADER_SMOKE_TEST_TIMEOUT_MS, runLoaderSmoke } from '@deepseek-ai/dsh-loader-smoke'
/**
* Keyless Loader-path smoke for examples/coding-agent: boot the REAL example
* through the `@deepseek-ai/dsh-stdio-agent` bin against its `cordis.yml` (the
* cordis Loader, `unwrapExports`, the full plugin tree incl. the
* `@deepseek-ai/dsh-agent-core` bundle and the app's in-package readline UI
* module), then close stdin with no prompt and assert the
* ready banner + a clean exit.
*
* No prompt is ever sent, so the model is NEVER called — this is why it runs
* without a real key. coding-agent's `cordis.yml` loads `llm-deepseek`, whose
* `apply()` only requires a key to be PRESENT (it does not validate it and only
* uses it when a stream actually starts), so a dummy key lets the tree boot
* while the absence of any prompt guarantees no network call. The value is the
* real-Loader-path guard that the composed tree boots (see postmortem 0001;
* the app carries no `inject`, so its export SHAPE is pinned by the stdio-agent
* unit suite's unwrap assertion, not by a crash here),
* complementing coding-agent's with-key e2e suites which prove the real
* product.
* Keyless Loader-path smoke for examples/coding-agent: boot the real example
* through the stdio-agent bin and its `cordis.yml`, then close stdin without a
* prompt and assert the banner. The dummy key satisfies adapter construction;
* immediate EOF guarantees there is no model call.
*/
// The dsh-stdio-agent bin (the demo:repl entry) and this example's cordis.yml.
// The bin resolves its config-path arg from CWD; the test spawns from a temp
// cwd, so we pass the example config's ABSOLUTE path.
const binScript = fileURLToPath(new URL('../../../packages/ui/stdio-agent/src/bin.ts', import.meta.url))
const binScript = fileURLToPath(new URL('../../../packages/examples/stdio-demo/src/bin.ts', import.meta.url))
const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url))
const tsxLoader = fileURLToPath(import.meta.resolve('tsx'))
// Dev/test run UNBUILT: resolve `@deepseek-ai/dsh-*` through the root tsconfig
// `paths` map; tsx searches UP from cwd, and we spawn from a temp dir outside
// the repo, so point it at the repo tsconfig (root is four levels up).
const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
// The real-API workflow runs up to 14 e2e files at once. Cold tsx/Loader
// startup can therefore outlive a tight smoke-test deadline before the child
// emits any output; 30s still detects a wedged process without confusing
// bounded CI contention with a lifecycle failure.
const PROCESS_TIMEOUT_MS = 30_000
// Leave enough room for the process-owned timeout to report captured output
// before Vitest aborts the test itself.
const TEST_TIMEOUT_MS = PROCESS_TIMEOUT_MS + 15_000
let child: ChildProcessWithoutNullStreams | undefined
let workdir: string | undefined
afterEach(async () => {
if (child !== undefined && child.exitCode === null) child.kill('SIGKILL')
child = undefined
if (workdir !== undefined) await rm(workdir, { recursive: true, force: true })
workdir = undefined
})
async function bootAndEof(): Promise<{ stdout: string; code: number }> {
workdir = await mkdtemp(join(tmpdir(), 'coding-smoke-'))
const cwd = workdir
return new Promise((resolve, reject) => {
const proc = spawn(
process.execPath,
// --expose-internals: cordis.yml loads the HMR plugin (mirrors demo:repl).
['--expose-internals', '--import', tsxLoader, binScript, configPath],
{
cwd,
env: {
...process.env,
TSX_TSCONFIG_PATH: repoTsconfig,
// A dummy key so llm-deepseek's apply() (key-PRESENT check only) boots.
// No prompt is sent, so the adapter never streams — no network call.
DEEPSEEK_API_KEY: 'keyless-smoke-no-call',
DSH_HOME: join(cwd, '.dsh'),
DSH_AGENTS_HOME: join(cwd, '.agents'),
},
stdio: ['pipe', 'pipe', 'pipe'],
},
)
child = proc
let stdout = ''
let stderr = ''
proc.stdout.setEncoding('utf8')
proc.stdout.on('data', (chunk: string) => { stdout += chunk })
proc.stderr.setEncoding('utf8')
proc.stderr.on('data', (chunk: string) => { stderr += chunk })
const timer = setTimeout(() => {
proc.kill('SIGKILL')
reject(new Error(`coding-agent did not exit within ${PROCESS_TIMEOUT_MS / 1_000}s. stdout:\n${stdout}\nstderr:\n${stderr}`))
}, PROCESS_TIMEOUT_MS)
proc.on('exit', (code) => {
clearTimeout(timer)
if (code === 0) resolve({ stdout, code })
else reject(new Error(`coding-agent exited ${code}. stderr:\n${stderr}`))
})
proc.on('error', (err) => { clearTimeout(timer); reject(err) })
// No prompt — just EOF, so the stdio UI exits without ever running a turn.
proc.stdin.end()
})
}
const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
describe('coding-agent keyless smoke (real cordis.yml via the Loader)', () => {
it('boots the full plugin tree, prints its banner, and exits cleanly on EOF', async () => {
const { stdout, code } = await bootAndEof()
expect(code).toBe(0)
const { stdout } = await runLoaderSmoke({
label: 'coding-agent',
tempDirPrefix: 'coding-smoke-',
binScript,
configPath,
tsconfigPath,
env: { DEEPSEEK_API_KEY: 'keyless-smoke-no-call' },
})
expect(stdout).toContain('agent REPL ready.')
}, TEST_TIMEOUT_MS)
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
})