pi-code-tool

KO | EN

gitlite — search

#terminal #chatgpt #swift #developer-tools #rag #database #shell #data-science #ai #ai-agent

(★ 9)

Code-mode python tool for the pi coding agent — sandboxed via @pydantic/monty; agents compose host tools in code and save reusable ephemeral tools

파일 탐색기

ZIP 다운로드

- scheduled_tasks.lock
- - ci.yml
- code-tool-demo.md
- - 01-code-mode-articles.md
  - 02-smolagents.md
  - 03-monty.md
  - 04-pi-extension-api.md
- demo.ts
- rpc-suspend-test.mjs
- smoke.ts
- index.js
- - args.ts
  - builtins.ts
  - capabilities.ts
  - registry.ts
  - runner.ts
  - session.ts
  - stdout.ts
  - toolstore.ts
  - types.ts
- - bridge.ts
  - extension.ts
- index.ts
- approval.test.ts
- bridge.test.ts
- builtins.test.ts
- capabilities.test.ts
- extension.test.ts
- registry.test.ts
- runner.test.ts
- session.test.ts
- toolstore.test.ts
.gitignore
LICENSE
package-lock.json
package.json
PLAN.md
README.md
tsconfig.json

# CDN으로 사용하기

jsDelivr

jsDelivr는 공개 GitHub 리포지토리를 별도 설정 없이 CDN으로 즉시 서빙합니다. 버전과 파일을 고르면 웹페이지에 바로 붙일 수 있는 링크와 예시 코드가 만들어집니다.

버전

파일

링크

예시

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

A code-mode meta-tool for agent harnesses: the agent writes sandboxed Python (via
[@pydantic/monty](https://github.com/pydantic/monty)) that calls host tools as plain
functions — and can save working code as named, reusable ephemeral tools. First target
harness: [pi](https://pi.dev).

- **Plan**: [PLAN.md](PLAN.md) — M0–M5 (MVP) complete
- **Research notes**: [docs/research/](docs/research/)

## Install (as a pi package)

```bash
pi install npm:pi-code-tool
pi install /path/to/checkout   # or straight from a local clone (builds dist/ first: npm run build)
```

`@pydantic/monty` (including its platform-specific native binary) and `typebox` are
regular npm `dependencies`, so pi's installer pulls them in automatically;
`@earendil-works/pi-coding-agent` is a peer dependency satisfied by pi itself.

## Why

LLMs compose code better than they compose chained JSON tool calls: loops, filtering,
and aggregation happen inside the sandbox, and intermediate data never enters model
context — only what the code `print()`s. See `docs/research/01-code-mode-articles.md`
for the evidence (Cloudflare Code Mode, Anthropic programmatic tool calling, smolagents).

## What you get

Installing registers a `code` tool. **pi's own tools are bridged into the sandbox**
as plain Python functions: `read`, `grep`, `find`, `ls` dispatch directly, so the
model can loop/filter/compose them in one snippet instead of one model round-trip
per call. The workspace is also **mounted read-only at `/workspace`** for plain
`open()`/`pathlib` reads (monty enforces read-only mode, symlink-escape and
`..`-traversal protection), plus `http_get` (host-side fetch) and
`save_tool`/`delete_tool`/`list_saved_tools`/`read_tool` for building a toolbox in
`.pi/code-tools/*.py` (plain, user-editable Python files that auto-load into future
sessions). Variables persist across calls; state rides in tool-result `details`, so
it survives session restore and branching.

**Mutating tools (`bash`, `edit`, `write`) are approval-gated**: the script freezes
mid-execution at the call, pi shows a confirm dialog with the exact invocation, and
your answer resumes the script in place — deny and the sandbox raises a catchable
`PermissionError`, or pick **"Decide later"** to suspend the run entirely: completed
work stays cached, the suspension survives pi restarts, and `{"resume": true}`
continues the script from the exact gated call — even days later; `{"abandon": true}`
discards the pending gated call without resetting the rest of the session. The model writes a
30-line codemod; you approve each mutation without it burning a single extra token.
Replayed (already-approved) calls never re-prompt. Headless runs deny gated calls
unless you opt in with `autoApprove`.

Code is **statically type-checked before execution** (monty's bundled `ty`) against
typed stubs of every host tool — wrong argument types, bad methods on tool results,
and undefined names come back as compiler diagnostics *before any side effects run*,
instead of as tracebacks after three tool calls already happened.

## Example pi session

```text
$ pi
> Use the code tool to fetch https://api.github.com/repos/pydantic/monty,
  report the star count, and save a reusable tool gh_stars(repo) for next time.

● Code
    data = json.loads(http_get("https://api.github.com/repos/pydantic/monty"))
    print(f"stars: {data['stargazers_count']}")
    tool_code = (
        "def gh_stars(repo):\n"
        "    import json\n"
        "    url = f'https://api.github.com/repos/{repo}'\n"
        "    return json.loads(http_get(url))['stargazers_count']\n"
    )
    save_tool("gh_stars", tool_code, "Return the GitHub star count for owner/repo.")

pydantic/monty currently has 1,234 stars. I saved gh_stars(repo) for future use.
```

In a later session — no redefinition needed, `gh_stars` auto-loads:

```text
> how many stars does josephkern/pi-code-tool have?

● Code
    gh_stars("josephkern/pi-code-tool")
```

Because the work happens in one sandboxed snippet, intermediate data (the full API
response, loop iterations, file contents) never enters the model's context — only
what the code prints comes back.

## Configuration

The default export works out of the box. For custom host tools or a different tool
name, re-export from your own extension file (e.g. `.pi/extensions/code.ts`):

```ts
import { createPythonExtension } from 'pi-code-tool/pi'

export default createPythonExtension({
  toolName: 'code',              // rename if your model responds better to e.g. 'python'
  root: process.cwd(),           // workspace root for mounts, file tools, and the default store
  mountWorkspace: true,          // false: no /workspace mount, read_file tool instead
  bridgePiTools: true,           // false: don't expose pi's read/grep/find/ls/bash/edit/write
  noBuiltins: false,             // true: skip read_file/list_files/http_get starter tools
  toolStore: '.pi/code-tools',   // false: disable save_tool/delete_tool/list/read helpers
  typeCheck: true,               // false: skip the pre-execution type-check gate
  autoApprove: false,            // true: run bash/edit/write without asking (headless automation)
  limits: { maxDurationSecs: 5, maxMemory: 64 * 1024 * 1024 },
  tools: [
    {
      name: 'query_db',
      description: 'Run a read-only SQL query.',
      params: [{ name: 'sql', type: 'str' }],
      returns: 'list[dict]',
      returnsDescription: 'rows as dicts',
      execute: async ([sql]) => db.query(String(sql)),
    },
  ],
})
```

## Develop against this repo

```bash
pi -e src/pi/extension.ts        # load straight from source, no build needed
```

## Use as a library

```ts
import { CodeRunner, createBuiltinTools } from 'pi-code-tool'

const runner = new CodeRunner({ tools: createBuiltinTools({ root: process.cwd() }) })
const result = await runner.run('len(list_files("."))')
if (result.status === 'ok') console.log(result.output)
```

`RunResult` is a discriminated union with `status: 'ok' | 'error' | 'suspended'`,
`stdout`, `stdoutTruncated`, and per-call traces. `Session` adds persistent state
across runs (replay with a tool-call cache — earlier side effects never repeat) and
serializes to JSON with `dump()` / `Session.load()`. If an approval gate suspends a
run, call `session.resume()` to continue or `session.abandon()` to discard it before
running new code. `ToolStore` adds the saved-tools layer.

## Develop

```bash
npm install
npm test            # vitest (111 tests)
npm run typecheck
npm run smoke       # verifies monty primitives on your machine
npx tsx examples/demo.ts
```

## Architecture

```
src/core/    runner.ts    CodeRunner: owns monty's start/resume loop; tool dispatch,
                          tracebacks, limits, abort, per-call traces
             registry.ts  ToolRegistry + Python/typecheck stub rendering + prompt rules
             builtins.ts  read_file / list_files / http_get starter tools
             session.ts   Persistent state via transcript replay + tool-call cache
             toolstore.ts Agent-saved tools as plain .py files + manage-from-sandbox
src/pi/      extension.ts pi adapter: `code` tool (configurable name), streaming output, branch-safe state
             bridge.ts    pi built-in tools → Python stubs; bash/edit/write approval-gated
```

Known monty 0.0.18 quirks we code around are documented in
[docs/research/03-monty.md](docs/research/03-monty.md).

pi-code-tool

파일 탐색기

# CDN으로 사용하기

Was this content helpful?

Recent Feedback

Download README