mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
feat(ui): add dedicated TUI package
Move the interactive pi-tui front door into @deepseek-ai/dsh-tui while keeping @deepseek-ai/dsh-stdio line-oriented for pipes. Select the terminal package in the demo app, preserve logger ownership, and cover the production Loader composition with a PTY smoke test.
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
# coding-agent
|
||||
|
||||
The REPL agent demo wiring: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + the bash tool suite + subagent delegation + `todo_write` + stdio chat + JSONL persistence, loaded from `cordis.yml`. The UI is a terminal readline REPL.
|
||||
The coding-agent demo wiring: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + the bash tool suite + subagent delegation + `todo_write` + terminal chat + JSONL persistence, loaded from `cordis.yml`. Interactive runs use the pi-tui coding interface; piped runs use readline.
|
||||
|
||||
## Run it
|
||||
|
||||
@@ -11,15 +11,9 @@ 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` (+ 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.
|
||||
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`.
|
||||
|
||||
```
|
||||
> fix the failing test in /path/to/project
|
||||
[main turn 1] (reasoning…)
|
||||
[tool call] bash({"command": "node --test", "workdir": "/path/to/project"})
|
||||
[tool result] … [exit code: 1]
|
||||
…
|
||||
```
|
||||
The TUI renders resumed Markdown history, reasoning, tool-owned terminal/diff/generic cards, token totals, and the latest todo list. Enter submits or steers while the agent is running; Ctrl+O expands cards, Ctrl+R toggles reasoning, Escape cancels, and `/help` lists commands. `ask_user_question` opens a keyboard-driven overlay rather than taking over the editor.
|
||||
|
||||
### Resuming a prior session
|
||||
|
||||
@@ -29,7 +23,7 @@ Each run starts a fresh session by default (its event log lands under `./.sessio
|
||||
RESUME_SESSION_ID=<prior-session-id> pnpm run demo:repl
|
||||
```
|
||||
|
||||
The id is wired through `cordis.yml` (`resumeSessionId: !!js process.env.RESUME_SESSION_ID`); unset, the agent starts a new session. A missing/unreadable id is non-fatal — it logs a warning and starts no `main` agent.
|
||||
The id is wired through `cordis.yml` (`resumeSessionId: !!js process.env.RESUME_SESSION_ID`); unset, the agent starts a new session. A missing or unreadable id starts no `main` agent, so unset it or choose an existing session id.
|
||||
|
||||
## Code Mode
|
||||
|
||||
@@ -48,17 +42,17 @@ 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-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:
|
||||
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 (JSONL persistence, TTY-selected `dsh-tui`/`dsh-stdio` channels, 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` 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 |
|
||||
| `stdio-agent` (`@deepseek-ai/dsh-stdio-demo`) | the app bundle: the agent-spine demo + JSONL persistence + TTY-selected `dsh-tui`/`dsh-stdio` channels + a pre-created `main` agent. Its config carries the model, system prompt, `persistenceRoot` (`./.sessions`), `resumeSessionId`, and optional `ui` presentation settings |
|
||||
| `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 |
|
||||
| `tool-todo` | the model-facing `todo_write` tool; writes the whole task list to the session log and renders as a persistent TUI plan or readline checklist |
|
||||
| `fs-local`, `fs-policy`, `tool-fs` | the filesystem stack: the local `ctx.fs` provider, the read-before-write/edit policy gate (on the `fs/*` event gate), and the model-facing `read`/`write`/`edit` tools. Relative paths resolve against the session workspace |
|
||||
|
||||
## End-to-end tests (`pnpm run test:e2e`, key-gated)
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
|
||||
# Coding Agent App Composition
|
||||
|
||||
The coding REPL demo adds the real DeepSeek adapter, filesystem tools, todo_write, compaction, and both subagent transports on top of the stdio app package.
|
||||
The coding-agent demo adds the real DeepSeek adapter, filesystem tools, todo_write, compaction, and both subagent transports on top of the stdio app package.
|
||||
|
||||
```mermaid
|
||||
flowchart LR
|
||||
@@ -18,7 +18,7 @@ flowchart LR
|
||||
cfg --> plugin_coding_stdio_agent
|
||||
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"]
|
||||
plugin_coding_stdio_agent --> frontdoor_stdio["dsh-tui (TTY) / dsh-stdio (pipes)<br/>pre-created main agent"]
|
||||
bundle_agent_core --> spine_llm["ctx.llm"]
|
||||
bundle_agent_core --> spine_sessions["ctx.sessions"]
|
||||
bundle_agent_core --> spine_tools["ctx.tools + tool-bash"]
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# REPL agent with swappable DeepSeek and local-bash backends. `dsh-stdio-demo`
|
||||
# supplies the agent spine, generic task controls, logging, JSONL persistence,
|
||||
# readline UI, and `main` agent.
|
||||
# Coding agent with swappable DeepSeek and local-bash backends. `dsh-stdio-demo`
|
||||
# supplies the agent spine, generic task controls, JSONL persistence, TTY-selected
|
||||
# `dsh-tui`/`dsh-stdio` terminal front doors, 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`.
|
||||
@@ -38,6 +38,11 @@
|
||||
resumeSessionId: !!js process.env.RESUME_SESSION_ID
|
||||
persistenceRoot: './.sessions'
|
||||
welcome: 'agent REPL ready. Give it a coding task.'
|
||||
ui:
|
||||
mode: auto
|
||||
tui:
|
||||
showReasoning: true
|
||||
maxToolOutputLines: 12
|
||||
# Keep the persona to identity and behavior; tool plugins own tool guidance.
|
||||
# The loop resolves {{model}} from this agent's configuration.
|
||||
persona: |
|
||||
|
||||
101
examples/coding-agent/tests/tui-keyless-smoke.e2e.ts
Normal file
101
examples/coding-agent/tests/tui-keyless-smoke.e2e.ts
Normal file
@@ -0,0 +1,101 @@
|
||||
import { spawn } 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 { describe, expect, it } from 'vitest'
|
||||
import { LOADER_SMOKE_TEST_TIMEOUT_MS } from '@deepseek-ai/dsh-loader-smoke'
|
||||
|
||||
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 tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
|
||||
const tsxLoader = fileURLToPath(import.meta.resolve('tsx'))
|
||||
|
||||
const PTY_DRIVER = String.raw`
|
||||
import errno, os, pty, select, signal, sys, time
|
||||
node, tsx_loader, bin_script, config_path, tsconfig_path, cwd = sys.argv[1:]
|
||||
env = os.environ.copy()
|
||||
env.update({
|
||||
"DEEPSEEK_API_KEY": "keyless-tui-no-call",
|
||||
"DSH_HOME": os.path.join(cwd, ".dsh"),
|
||||
"DSH_AGENTS_HOME": os.path.join(cwd, ".agents"),
|
||||
"TSX_TSCONFIG_PATH": tsconfig_path,
|
||||
})
|
||||
pid, fd = pty.fork()
|
||||
if pid == 0:
|
||||
os.chdir(cwd)
|
||||
os.execvpe(node, [node, "--expose-internals", "--import", tsx_loader, bin_script, config_path], env)
|
||||
|
||||
output = bytearray()
|
||||
sent_exit = False
|
||||
deadline = time.monotonic() + 25
|
||||
status = None
|
||||
while time.monotonic() < deadline:
|
||||
ready, _, _ = select.select([fd], [], [], 0.05)
|
||||
if ready:
|
||||
try:
|
||||
chunk = os.read(fd, 65536)
|
||||
except OSError as error:
|
||||
if error.errno != errno.EIO:
|
||||
raise
|
||||
chunk = b""
|
||||
if chunk:
|
||||
output.extend(chunk)
|
||||
if not sent_exit and b"agent REPL ready." in output:
|
||||
os.write(fd, b"/exit\r")
|
||||
sent_exit = True
|
||||
waited, candidate = os.waitpid(pid, os.WNOHANG)
|
||||
if waited == pid:
|
||||
status = candidate
|
||||
break
|
||||
|
||||
if status is None:
|
||||
os.kill(pid, signal.SIGKILL)
|
||||
_, status = os.waitpid(pid, 0)
|
||||
sys.stdout.buffer.write(output)
|
||||
if not sent_exit:
|
||||
sys.stderr.write("TUI did not render its welcome marker before timeout\n")
|
||||
sys.exit(124)
|
||||
if not os.WIFEXITED(status) or os.WEXITSTATUS(status) != 0:
|
||||
sys.stderr.write("TUI child did not exit cleanly\n")
|
||||
sys.exit(125)
|
||||
`
|
||||
|
||||
async function runTuiLoaderSmoke(): Promise<string> {
|
||||
const cwd = await mkdtemp(join(tmpdir(), 'coding-tui-smoke-'))
|
||||
try {
|
||||
return await new Promise((resolve, reject) => {
|
||||
const child = spawn('python3', [
|
||||
'-c',
|
||||
PTY_DRIVER,
|
||||
process.execPath,
|
||||
tsxLoader,
|
||||
binScript,
|
||||
configPath,
|
||||
tsconfigPath,
|
||||
cwd,
|
||||
], { stdio: ['ignore', 'pipe', 'pipe'] })
|
||||
let stdout = ''
|
||||
let stderr = ''
|
||||
child.stdout.setEncoding('utf8')
|
||||
child.stdout.on('data', (chunk: string) => { stdout += chunk })
|
||||
child.stderr.setEncoding('utf8')
|
||||
child.stderr.on('data', (chunk: string) => { stderr += chunk })
|
||||
child.once('error', reject)
|
||||
child.once('exit', (code) => {
|
||||
if (code === 0) resolve(stdout)
|
||||
else reject(new Error(`TUI PTY smoke exited ${String(code)}. stdout:\n${stdout}\nstderr:\n${stderr}`))
|
||||
})
|
||||
})
|
||||
} finally {
|
||||
await rm(cwd, { recursive: true, force: true })
|
||||
}
|
||||
}
|
||||
|
||||
describe('coding-agent TUI keyless smoke (real Loader tree in a PTY)', () => {
|
||||
it('boots pi-tui, renders the configured banner, accepts /exit, and restores the terminal', async () => {
|
||||
const output = await runTuiLoaderSmoke()
|
||||
expect(output).toContain('DEEPSEEK')
|
||||
expect(output).toContain('agent REPL ready.')
|
||||
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
|
||||
})
|
||||
Reference in New Issue
Block a user