mirror of
https://github.com/humanlayer/12-factor-agents.git
synced 2025-08-20 18:59:53 +03:00
Merge pull request #42 from humanlayer/5-17-and-contributors
5 17 and contributors
This commit is contained in:
Dex
@@ -245,6 +245,10 @@ After digging through hundreds of AI libriaries and working with dozens of found
|
||||
- [The AI Agent Index (MIT)](https://aiagentindex.mit.edu/)
|
||||
- [NotebookLM on Finding Model Capability Boundaries](https://open.substack.com/pub/swyx/p/notebooklm?selection=08e1187c-cfee-4c63-93c9-71216640a5f8)
|
||||
|
||||
## Contributors
|
||||
|
||||
Thanks to everyone who has contributed to 12-factor agents!
|
||||
|
||||
[<img src="https://avatars.githubusercontent.com/u/3730605?v=4&s=80" width="80px" alt="dexhorthy" />](https://github.com/dexhorthy) [<img src="https://avatars.githubusercontent.com/u/50557586?v=4&s=80" width="80px" alt="Sypherd" />](https://github.com/Sypherd) [<img src="https://avatars.githubusercontent.com/u/66259401?v=4&s=80" width="80px" alt="tofaramususa" />](https://github.com/tofaramususa) [<img src="https://avatars.githubusercontent.com/u/18105223?v=4&s=80" width="80px" alt="a-churchill" />](https://github.com/a-churchill) [<img src="https://avatars.githubusercontent.com/u/4084885?v=4&s=80" width="80px" alt="Elijas" />](https://github.com/Elijas) [<img src="https://avatars.githubusercontent.com/u/39267118?v=4&s=80" width="80px" alt="hugolmn" />](https://github.com/hugolmn) [<img src="https://avatars.githubusercontent.com/u/1882972?v=4&s=80" width="80px" alt="jeremypeters" />](https://github.com/jeremypeters)
|
||||
|
||||
[<img src="https://avatars.githubusercontent.com/u/380402?v=4&s=80" width="80px" alt="kndl" />](https://github.com/kndl) [<img src="https://avatars.githubusercontent.com/u/16674643?v=4&s=80" width="80px" alt="maciejkos" />](https://github.com/maciejkos) [<img src="https://avatars.githubusercontent.com/u/85041180?v=4&s=80" width="80px" alt="pfbyjy" />](https://github.com/pfbyjy) [<img src="https://avatars.githubusercontent.com/u/36044389?v=4&s=80" width="80px" alt="0xRaduan" />](https://github.com/0xRaduan) [<img src="https://avatars.githubusercontent.com/u/7169731?v=4&s=80" width="80px" alt="zyuanlim" />](https://github.com/zyuanlim) [<img src="https://avatars.githubusercontent.com/u/15862501?v=4&s=80" width="80px" alt="lombardo-chcg" />](https://github.com/lombardo-chcg) [<img src="https://avatars.githubusercontent.com/u/160066852?v=4&s=80" width="80px" alt="sahanatvessel" />](https://github.com/sahanatvessel)
|
||||
|
||||
1
hack/contributors_markdown/.python-version
Normal file
1
hack/contributors_markdown/.python-version
Normal file
@@ -0,0 +1 @@
|
||||
3.13
|
||||
0
hack/contributors_markdown/README.md
Normal file
0
hack/contributors_markdown/README.md
Normal file
120
hack/contributors_markdown/contributors_markdown.py
Normal file
120
hack/contributors_markdown/contributors_markdown.py
Normal file
@@ -0,0 +1,120 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Generate a Markdown grid of contributor avatars for a GitHub repository.
|
||||
|
||||
Usage:
|
||||
python generate_contributors_grid.py --repo owner/name --token GH_TOKEN [--cols 7] [--image_size 80] [--output FILE]
|
||||
|
||||
Arguments:
|
||||
--repo GitHub repository in "owner/name" form (e.g. "octocat/Hello-World")
|
||||
--token Personal access token with `public_repo` scope (or `repo` for private).
|
||||
Can also be provided via the GITHUB_TOKEN environment variable.
|
||||
--cols Number of avatars per row in the generated grid (default 7).
|
||||
--image_size Pixel width for avatars (GitHub automatically resizes; default 80).
|
||||
--output File to write the Markdown grid into (default: stdout, use '-' for stdout).
|
||||
|
||||
The generated file contains a Markdown table‑less grid of linked avatars that can
|
||||
be embedded in README.md or any other Markdown document.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
import argparse
|
||||
import os
|
||||
import sys
|
||||
import textwrap
|
||||
from typing import List, Dict
|
||||
|
||||
import requests
|
||||
|
||||
API_URL_TEMPLATE = "https://api.github.com/repos/{owner}/{repo}/contributors"
|
||||
|
||||
|
||||
def fetch_contributors(owner: str, repo: str, token: str | None, per_page: int = 100) -> List[Dict]:
|
||||
"""Return a list of contributor objects from the GitHub REST API."""
|
||||
headers = {"Accept": "application/vnd.github+json"}
|
||||
if token:
|
||||
headers["Authorization"] = f"Bearer {token}"
|
||||
|
||||
contributors: List[Dict] = []
|
||||
page = 1
|
||||
while True:
|
||||
url = f"{API_URL_TEMPLATE.format(owner=owner, repo=repo)}?per_page={per_page}&page={page}"
|
||||
response = requests.get(url, headers=headers, timeout=10)
|
||||
response.raise_for_status()
|
||||
batch = response.json()
|
||||
if not batch:
|
||||
break
|
||||
contributors.extend(batch)
|
||||
if len(batch) < per_page:
|
||||
break
|
||||
page += 1
|
||||
return contributors
|
||||
|
||||
|
||||
def build_markdown(contributors: List[Dict], cols: int = 7, image_size: int = 80) -> str:
|
||||
"""Return a Markdown fragment containing a grid of linked avatar images."""
|
||||
lines: List[str] = []
|
||||
row: List[str] = []
|
||||
|
||||
for contributor in contributors:
|
||||
login = contributor["login"]
|
||||
avatar = f"{contributor['avatar_url']}&s={image_size}"
|
||||
profile = contributor["html_url"]
|
||||
cell = f'[<img src="{avatar}" width="{image_size}px" alt="{login}" />]({profile})'
|
||||
row.append(cell)
|
||||
if len(row) == cols:
|
||||
lines.append(" ".join(row))
|
||||
row = []
|
||||
|
||||
if row:
|
||||
lines.append(" ".join(row))
|
||||
|
||||
return "\n\n".join(lines)
|
||||
|
||||
|
||||
def main() -> None:
|
||||
parser = argparse.ArgumentParser(description="Generate a Markdown grid of contributor avatars")
|
||||
parser.add_argument("--repo", required=True, help="GitHub repo in owner/name form")
|
||||
parser.add_argument("--token", help="GitHub Personal Access Token (or set GITHUB_TOKEN env)")
|
||||
parser.add_argument("--cols", type=int, default=7, help="Number of avatars per row (default 7)")
|
||||
parser.add_argument("--image_size", type=int, default=80, help="Avatar size in px (default 80)")
|
||||
parser.add_argument("--output", "-o", default="-", help="Output file (default: stdout, use '-' for stdout)")
|
||||
|
||||
args = parser.parse_args()
|
||||
token = args.token or os.getenv("GITHUB_TOKEN")
|
||||
if not token:
|
||||
parser.error("A GitHub token must be supplied via --token or GITHUB_TOKEN env var.")
|
||||
|
||||
if "/" not in args.repo:
|
||||
parser.error("--repo must be in 'owner/name' form")
|
||||
owner, repo = args.repo.split("/", 1)
|
||||
|
||||
contributors = fetch_contributors(owner, repo, token)
|
||||
if not contributors:
|
||||
sys.exit("No contributors found. Is the repository correct and does the token have access?")
|
||||
|
||||
markdown = build_markdown(contributors, cols=args.cols, image_size=args.image_size)
|
||||
|
||||
header = textwrap.dedent(
|
||||
f"""
|
||||
<!-- AUTO-GENERATED BY generate_contributors_grid.py -->
|
||||
## Contributors
|
||||
Thanks to these wonderful people:\n
|
||||
"""
|
||||
)
|
||||
|
||||
if args.output == "-":
|
||||
sys.stdout.write(header)
|
||||
sys.stdout.write(markdown)
|
||||
sys.stdout.write("\n")
|
||||
else:
|
||||
with open(args.output, "w", encoding="utf-8") as fh:
|
||||
fh.write(header)
|
||||
fh.write(markdown)
|
||||
fh.write("\n")
|
||||
print(f"Wrote {len(contributors)} contributors to {args.output}", file=sys.stderr)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
||||
9
hack/contributors_markdown/pyproject.toml
Normal file
9
hack/contributors_markdown/pyproject.toml
Normal file
@@ -0,0 +1,9 @@
|
||||
[project]
|
||||
name = "contributors-markdown"
|
||||
version = "0.1.0"
|
||||
description = "Add your description here"
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.13"
|
||||
dependencies = [
|
||||
"requests>=2.32.3",
|
||||
]
|
||||
77
hack/contributors_markdown/uv.lock
generated
Normal file
77
hack/contributors_markdown/uv.lock
generated
Normal file
@@ -0,0 +1,77 @@
|
||||
version = 1
|
||||
requires-python = ">=3.13"
|
||||
|
||||
[[package]]
|
||||
name = "certifi"
|
||||
version = "2025.4.26"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/e8/9e/c05b3920a3b7d20d3d3310465f50348e5b3694f4f88c6daf736eef3024c4/certifi-2025.4.26.tar.gz", hash = "sha256:0a816057ea3cdefcef70270d2c515e4506bbc954f417fa5ade2021213bb8f0c6", size = 160705 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/4a/7e/3db2bd1b1f9e95f7cddca6d6e75e2f2bd9f51b1246e546d88addca0106bd/certifi-2025.4.26-py3-none-any.whl", hash = "sha256:30350364dfe371162649852c63336a15c70c6510c2ad5015b21c2345311805f3", size = 159618 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "charset-normalizer"
|
||||
version = "3.4.2"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/e4/33/89c2ced2b67d1c2a61c19c6751aa8902d46ce3dacb23600a283619f5a12d/charset_normalizer-3.4.2.tar.gz", hash = "sha256:5baececa9ecba31eff645232d59845c07aa030f0c81ee70184a90d35099a0e63", size = 126367 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/ea/12/a93df3366ed32db1d907d7593a94f1fe6293903e3e92967bebd6950ed12c/charset_normalizer-3.4.2-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:926ca93accd5d36ccdabd803392ddc3e03e6d4cd1cf17deff3b989ab8e9dbcf0", size = 199622 },
|
||||
{ url = "https://files.pythonhosted.org/packages/04/93/bf204e6f344c39d9937d3c13c8cd5bbfc266472e51fc8c07cb7f64fcd2de/charset_normalizer-3.4.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:eba9904b0f38a143592d9fc0e19e2df0fa2e41c3c3745554761c5f6447eedabf", size = 143435 },
|
||||
{ url = "https://files.pythonhosted.org/packages/22/2a/ea8a2095b0bafa6c5b5a55ffdc2f924455233ee7b91c69b7edfcc9e02284/charset_normalizer-3.4.2-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3fddb7e2c84ac87ac3a947cb4e66d143ca5863ef48e4a5ecb83bd48619e4634e", size = 153653 },
|
||||
{ url = "https://files.pythonhosted.org/packages/b6/57/1b090ff183d13cef485dfbe272e2fe57622a76694061353c59da52c9a659/charset_normalizer-3.4.2-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:98f862da73774290f251b9df8d11161b6cf25b599a66baf087c1ffe340e9bfd1", size = 146231 },
|
||||
{ url = "https://files.pythonhosted.org/packages/e2/28/ffc026b26f441fc67bd21ab7f03b313ab3fe46714a14b516f931abe1a2d8/charset_normalizer-3.4.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c9379d65defcab82d07b2a9dfbfc2e95bc8fe0ebb1b176a3190230a3ef0e07c", size = 148243 },
|
||||
{ url = "https://files.pythonhosted.org/packages/c0/0f/9abe9bd191629c33e69e47c6ef45ef99773320e9ad8e9cb08b8ab4a8d4cb/charset_normalizer-3.4.2-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e635b87f01ebc977342e2697d05b56632f5f879a4f15955dfe8cef2448b51691", size = 150442 },
|
||||
{ url = "https://files.pythonhosted.org/packages/67/7c/a123bbcedca91d5916c056407f89a7f5e8fdfce12ba825d7d6b9954a1a3c/charset_normalizer-3.4.2-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:1c95a1e2902a8b722868587c0e1184ad5c55631de5afc0eb96bc4b0d738092c0", size = 145147 },
|
||||
{ url = "https://files.pythonhosted.org/packages/ec/fe/1ac556fa4899d967b83e9893788e86b6af4d83e4726511eaaad035e36595/charset_normalizer-3.4.2-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:ef8de666d6179b009dce7bcb2ad4c4a779f113f12caf8dc77f0162c29d20490b", size = 153057 },
|
||||
{ url = "https://files.pythonhosted.org/packages/2b/ff/acfc0b0a70b19e3e54febdd5301a98b72fa07635e56f24f60502e954c461/charset_normalizer-3.4.2-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:32fc0341d72e0f73f80acb0a2c94216bd704f4f0bce10aedea38f30502b271ff", size = 156454 },
|
||||
{ url = "https://files.pythonhosted.org/packages/92/08/95b458ce9c740d0645feb0e96cea1f5ec946ea9c580a94adfe0b617f3573/charset_normalizer-3.4.2-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:289200a18fa698949d2b39c671c2cc7a24d44096784e76614899a7ccf2574b7b", size = 154174 },
|
||||
{ url = "https://files.pythonhosted.org/packages/78/be/8392efc43487ac051eee6c36d5fbd63032d78f7728cb37aebcc98191f1ff/charset_normalizer-3.4.2-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:4a476b06fbcf359ad25d34a057b7219281286ae2477cc5ff5e3f70a246971148", size = 149166 },
|
||||
{ url = "https://files.pythonhosted.org/packages/44/96/392abd49b094d30b91d9fbda6a69519e95802250b777841cf3bda8fe136c/charset_normalizer-3.4.2-cp313-cp313-win32.whl", hash = "sha256:aaeeb6a479c7667fbe1099af9617c83aaca22182d6cf8c53966491a0f1b7ffb7", size = 98064 },
|
||||
{ url = "https://files.pythonhosted.org/packages/e9/b0/0200da600134e001d91851ddc797809e2fe0ea72de90e09bec5a2fbdaccb/charset_normalizer-3.4.2-cp313-cp313-win_amd64.whl", hash = "sha256:aa6af9e7d59f9c12b33ae4e9450619cf2488e2bbe9b44030905877f0b2324980", size = 105641 },
|
||||
{ url = "https://files.pythonhosted.org/packages/20/94/c5790835a017658cbfabd07f3bfb549140c3ac458cfc196323996b10095a/charset_normalizer-3.4.2-py3-none-any.whl", hash = "sha256:7f56930ab0abd1c45cd15be65cc741c28b1c9a34876ce8c17a2fa107810c0af0", size = 52626 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "contributors-markdown"
|
||||
version = "0.1.0"
|
||||
source = { virtual = "." }
|
||||
dependencies = [
|
||||
{ name = "requests" },
|
||||
]
|
||||
|
||||
[package.metadata]
|
||||
requires-dist = [{ name = "requests", specifier = ">=2.32.3" }]
|
||||
|
||||
[[package]]
|
||||
name = "idna"
|
||||
version = "3.10"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/f1/70/7703c29685631f5a7590aa73f1f1d3fa9a380e654b86af429e0934a32f7d/idna-3.10.tar.gz", hash = "sha256:12f65c9b470abda6dc35cf8e63cc574b1c52b11df2c86030af0ac09b01b13ea9", size = 190490 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/76/c6/c88e154df9c4e1a2a66ccf0005a88dfb2650c1dffb6f5ce603dfbd452ce3/idna-3.10-py3-none-any.whl", hash = "sha256:946d195a0d259cbba61165e88e65941f16e9b36ea6ddb97f00452bae8b1287d3", size = 70442 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "requests"
|
||||
version = "2.32.3"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "certifi" },
|
||||
{ name = "charset-normalizer" },
|
||||
{ name = "idna" },
|
||||
{ name = "urllib3" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/63/70/2bf7780ad2d390a8d301ad0b550f1581eadbd9a20f896afe06353c2a2913/requests-2.32.3.tar.gz", hash = "sha256:55365417734eb18255590a9ff9eb97e9e1da868d4ccd6402399eaf68af20a760", size = 131218 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/f9/9b/335f9764261e915ed497fcdeb11df5dfd6f7bf257d4a6a2a686d80da4d54/requests-2.32.3-py3-none-any.whl", hash = "sha256:70761cfe03c773ceb22aa2f671b4757976145175cdfca038c02654d061d6dcc6", size = 64928 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "urllib3"
|
||||
version = "2.4.0"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/8a/78/16493d9c386d8e60e442a35feac5e00f0913c0f4b7c217c11e8ec2ff53e0/urllib3-2.4.0.tar.gz", hash = "sha256:414bc6535b787febd7567804cc015fee39daab8ad86268f1310a9250697de466", size = 390672 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/6b/11/cc635220681e93a0183390e26485430ca2c7b5f9d33b15c74c2861cb8091/urllib3-2.4.0-py3-none-any.whl", hash = "sha256:4e16665048960a0900c702d4a66415956a584919c03361cac9f1df5c5dd7e813", size = 128680 },
|
||||
]
|
||||
142
workshops/2025-05-17/sections/00-hello-world/README.md
Normal file
142
workshops/2025-05-17/sections/00-hello-world/README.md
Normal file
@@ -0,0 +1,142 @@
|
||||
# Chapter 0 - Hello World
|
||||
|
||||
Let's start with a basic TypeScript setup and a hello world program.
|
||||
|
||||
This guide is written in TypeScript (yes, a python version is coming soon)
|
||||
|
||||
There are many checkpoints between the every file edit in theworkshop steps,
|
||||
so even if you aren't super familiar with typescript,
|
||||
you should be able to keep up and run each example.
|
||||
|
||||
To run this guide, you'll need a relatively recent version of nodejs and npm installed
|
||||
|
||||
You can use whatever nodejs version manager you want, [homebrew](https://formulae.brew.sh/formula/node) is fine
|
||||
|
||||
|
||||
brew install node@20
|
||||
|
||||
You should see the node version
|
||||
|
||||
node --version
|
||||
|
||||
Copy initial package.json
|
||||
|
||||
cp ./walkthrough/00-package.json package.json
|
||||
|
||||
<details>
|
||||
<summary>show file</summary>
|
||||
|
||||
```json
|
||||
// ./walkthrough/00-package.json
|
||||
{
|
||||
"name": "my-agent",
|
||||
"version": "0.1.0",
|
||||
"private": true,
|
||||
"scripts": {
|
||||
"dev": "tsx src/index.ts",
|
||||
"build": "tsc"
|
||||
},
|
||||
"dependencies": {
|
||||
"tsx": "^4.15.0",
|
||||
"typescript": "^5.0.0"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@types/node": "^20.0.0",
|
||||
"@typescript-eslint/eslint-plugin": "^6.0.0",
|
||||
"@typescript-eslint/parser": "^6.0.0",
|
||||
"eslint": "^8.0.0"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
Install dependencies
|
||||
|
||||
npm install
|
||||
|
||||
Copy tsconfig.json
|
||||
|
||||
cp ./walkthrough/00-tsconfig.json tsconfig.json
|
||||
|
||||
<details>
|
||||
<summary>show file</summary>
|
||||
|
||||
```json
|
||||
// ./walkthrough/00-tsconfig.json
|
||||
{
|
||||
"compilerOptions": {
|
||||
"target": "ES2017",
|
||||
"lib": ["esnext"],
|
||||
"allowJs": true,
|
||||
"skipLibCheck": true,
|
||||
"strict": true,
|
||||
"noEmit": true,
|
||||
"esModuleInterop": true,
|
||||
"module": "esnext",
|
||||
"moduleResolution": "bundler",
|
||||
"resolveJsonModule": true,
|
||||
"isolatedModules": true,
|
||||
"jsx": "preserve",
|
||||
"incremental": true,
|
||||
"plugins": [],
|
||||
"paths": {
|
||||
"@/*": ["./*"]
|
||||
}
|
||||
},
|
||||
"include": ["next-env.d.ts", "**/*.ts", "**/*.tsx", ".next/types/**/*.ts"],
|
||||
"exclude": ["node_modules", "walkthrough"]
|
||||
}
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
add .gitignore
|
||||
|
||||
cp ./walkthrough/00-.gitignore .gitignore
|
||||
|
||||
<details>
|
||||
<summary>show file</summary>
|
||||
|
||||
```gitignore
|
||||
// ./walkthrough/00-.gitignore
|
||||
baml_client/
|
||||
node_modules/
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
Create src folder
|
||||
|
||||
mkdir -p src
|
||||
|
||||
Add a simple hello world index.ts
|
||||
|
||||
cp ./walkthrough/00-index.ts src/index.ts
|
||||
|
||||
<details>
|
||||
<summary>show file</summary>
|
||||
|
||||
```ts
|
||||
// ./walkthrough/00-index.ts
|
||||
async function hello(): Promise<void> {
|
||||
console.log('hello, world!')
|
||||
}
|
||||
|
||||
async function main() {
|
||||
await hello()
|
||||
}
|
||||
|
||||
main().catch(console.error)
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
Run it to verify
|
||||
|
||||
npx tsx src/index.ts
|
||||
|
||||
You should see:
|
||||
|
||||
hello, world!
|
||||
|
||||
@@ -0,0 +1,2 @@
|
||||
baml_client/
|
||||
node_modules/
|
||||
@@ -0,0 +1,9 @@
|
||||
async function hello(): Promise<void> {
|
||||
console.log('hello, world!')
|
||||
}
|
||||
|
||||
async function main() {
|
||||
await hello()
|
||||
}
|
||||
|
||||
main().catch(console.error)
|
||||
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"name": "my-agent",
|
||||
"version": "0.1.0",
|
||||
"private": true,
|
||||
"scripts": {
|
||||
"dev": "tsx src/index.ts",
|
||||
"build": "tsc"
|
||||
},
|
||||
"dependencies": {
|
||||
"tsx": "^4.15.0",
|
||||
"typescript": "^5.0.0"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@types/node": "^20.0.0",
|
||||
"@typescript-eslint/eslint-plugin": "^6.0.0",
|
||||
"@typescript-eslint/parser": "^6.0.0",
|
||||
"eslint": "^8.0.0"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"compilerOptions": {
|
||||
"target": "ES2017",
|
||||
"lib": ["esnext"],
|
||||
"allowJs": true,
|
||||
"skipLibCheck": true,
|
||||
"strict": true,
|
||||
"noEmit": true,
|
||||
"esModuleInterop": true,
|
||||
"module": "esnext",
|
||||
"moduleResolution": "bundler",
|
||||
"resolveJsonModule": true,
|
||||
"isolatedModules": true,
|
||||
"jsx": "preserve",
|
||||
"incremental": true,
|
||||
"plugins": [],
|
||||
"paths": {
|
||||
"@/*": ["./*"]
|
||||
}
|
||||
},
|
||||
"include": ["next-env.d.ts", "**/*.ts", "**/*.tsx", ".next/types/**/*.ts"],
|
||||
"exclude": ["node_modules", "walkthrough"]
|
||||
}
|
||||
|
||||
2
workshops/2025-05-17/sections/01-cli-and-agent/.gitignore
vendored
Normal file
2
workshops/2025-05-17/sections/01-cli-and-agent/.gitignore
vendored
Normal file
@@ -0,0 +1,2 @@
|
||||
baml_client/
|
||||
node_modules/
|
||||
231
workshops/2025-05-17/sections/01-cli-and-agent/README.md
Normal file
231
workshops/2025-05-17/sections/01-cli-and-agent/README.md
Normal file
@@ -0,0 +1,231 @@
|
||||
# Chapter 1 - CLI and Agent Loop
|
||||
|
||||
Now let's add BAML and create our first agent with a CLI interface.
|
||||
|
||||
First, we'll need to install [BAML](https://github.com/boundaryml/baml)
|
||||
which is a tool for prompting and structured outputs.
|
||||
|
||||
|
||||
npm install @boundaryml/baml
|
||||
|
||||
Initialize BAML
|
||||
|
||||
npx baml-cli init
|
||||
|
||||
Remove default resume.baml
|
||||
|
||||
rm baml_src/resume.baml
|
||||
|
||||
Add our starter agent, a single baml prompt that we'll build on
|
||||
|
||||
cp ./walkthrough/01-agent.baml baml_src/agent.baml
|
||||
|
||||
<details>
|
||||
<summary>show file</summary>
|
||||
|
||||
```rust
|
||||
// ./walkthrough/01-agent.baml
|
||||
class DoneForNow {
|
||||
intent "done_for_now"
|
||||
message string
|
||||
}
|
||||
|
||||
client<llm> Qwen3 {
|
||||
provider "openai-generic"
|
||||
options {
|
||||
base_url env.BASETEN_BASE_URL
|
||||
api_key env.BASETEN_API_KEY
|
||||
}
|
||||
}
|
||||
|
||||
function DetermineNextStep(
|
||||
thread: string
|
||||
) -> DoneForNow {
|
||||
client Qwen3
|
||||
|
||||
// use /nothink for now because the thinking tokens (or streaming thereof) screw with baml (i think (no pun intended))
|
||||
prompt #"
|
||||
{{ _.role("system") }}
|
||||
|
||||
/nothink
|
||||
|
||||
You are a helpful assistant that can help with tasks.
|
||||
|
||||
{{ _.role("user") }}
|
||||
|
||||
You are working on the following thread:
|
||||
|
||||
{{ thread }}
|
||||
|
||||
What should the next step be?
|
||||
|
||||
{{ ctx.output_format }}
|
||||
"#
|
||||
}
|
||||
|
||||
test HelloWorld {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
{
|
||||
"type": "user_input",
|
||||
"data": "hello!"
|
||||
}
|
||||
"#
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
Generate BAML client code
|
||||
|
||||
npx baml-cli generate
|
||||
|
||||
Enable BAML logging for this section
|
||||
|
||||
export BAML_LOG=debug
|
||||
|
||||
Add the CLI interface
|
||||
|
||||
cp ./walkthrough/01-cli.ts src/cli.ts
|
||||
|
||||
<details>
|
||||
<summary>show file</summary>
|
||||
|
||||
```ts
|
||||
// ./walkthrough/01-cli.ts
|
||||
// cli.ts lets you invoke the agent loop from the command line
|
||||
|
||||
import { agentLoop, Thread, Event } from "./agent";
|
||||
|
||||
export async function cli() {
|
||||
// Get command line arguments, skipping the first two (node and script name)
|
||||
const args = process.argv.slice(2);
|
||||
|
||||
if (args.length === 0) {
|
||||
console.error("Error: Please provide a message as a command line argument");
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
// Join all arguments into a single message
|
||||
const message = args.join(" ");
|
||||
|
||||
// Create a new thread with the user's message as the initial event
|
||||
const thread = new Thread([{ type: "user_input", data: message }]);
|
||||
|
||||
// Run the agent loop with the thread
|
||||
const result = await agentLoop(thread);
|
||||
console.log(result);
|
||||
}
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
Update index.ts to use the CLI
|
||||
|
||||
```diff
|
||||
src/index.ts
|
||||
+import { cli } from "./cli"
|
||||
+
|
||||
async function hello(): Promise<void> {
|
||||
console.log('hello, world!')
|
||||
|
||||
async function main() {
|
||||
- await hello()
|
||||
+ await cli()
|
||||
}
|
||||
|
||||
```
|
||||
|
||||
<details>
|
||||
<summary>skip this step</summary>
|
||||
|
||||
cp ./walkthrough/01-index.ts src/index.ts
|
||||
|
||||
</details>
|
||||
|
||||
Add the agent implementation
|
||||
|
||||
cp ./walkthrough/01-agent.ts src/agent.ts
|
||||
|
||||
<details>
|
||||
<summary>show file</summary>
|
||||
|
||||
```ts
|
||||
// ./walkthrough/01-agent.ts
|
||||
import { b } from "../baml_client";
|
||||
|
||||
// tool call or a respond to human tool
|
||||
type AgentResponse = Awaited<ReturnType<typeof b.DetermineNextStep>>;
|
||||
|
||||
export interface Event {
|
||||
type: string
|
||||
data: any;
|
||||
}
|
||||
|
||||
export class Thread {
|
||||
events: Event[] = [];
|
||||
|
||||
constructor(events: Event[]) {
|
||||
this.events = events;
|
||||
}
|
||||
|
||||
serializeForLLM() {
|
||||
// can change this to whatever custom serialization you want to do, XML, etc
|
||||
// e.g. https://github.com/got-agents/agents/blob/59ebbfa236fc376618f16ee08eb0f3bf7b698892/linear-assistant-ts/src/agent.ts#L66-L105
|
||||
return JSON.stringify(this.events);
|
||||
}
|
||||
}
|
||||
|
||||
// right now this just runs one turn with the LLM, but
|
||||
// we'll update this function to handle all the agent logic
|
||||
export async function agentLoop(thread: Thread): Promise<AgentResponse> {
|
||||
const nextStep = await b.DetermineNextStep(thread.serializeForLLM());
|
||||
return nextStep;
|
||||
}
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
The the BAML code is configured to use BASETEN_API_KEY by default
|
||||
|
||||
To get a Baseten API key and URL, create an account at [baseten.co](https://baseten.co),
|
||||
and then deploy [Qwen3 32B from the model library](https://www.baseten.co/library/qwen-3-32b/).
|
||||
|
||||
```rust
|
||||
function DetermineNextStep(thread: string) -> DoneForNow {
|
||||
client Qwen3
|
||||
// ...
|
||||
```
|
||||
|
||||
If you want to run the example with no changes, you can set the BASETEN_API_KEY env var to any valid baseten key.
|
||||
|
||||
If you want to try swapping out the model, you can change the `client` line.
|
||||
|
||||
[Docs on baml clients can be found here](https://docs.boundaryml.com/guide/baml-basics/switching-llms)
|
||||
|
||||
For example, you can configure [gemini](https://docs.boundaryml.com/ref/llm-client-providers/google-ai-gemini)
|
||||
or [anthropic](https://docs.boundaryml.com/ref/llm-client-providers/anthropic) as your model provider.
|
||||
|
||||
For example, to use openai with an OPENAI_API_KEY, you can do:
|
||||
|
||||
client "openai/gpt-4o"
|
||||
|
||||
|
||||
Set your env vars
|
||||
|
||||
export BASETEN_API_KEY=...
|
||||
export BASETEN_BASE_URL=...
|
||||
|
||||
Try it out
|
||||
|
||||
npx tsx src/index.ts hello
|
||||
|
||||
you should see a familiar response from the model
|
||||
|
||||
{
|
||||
intent: 'done_for_now',
|
||||
message: 'Hello! How can I assist you today?'
|
||||
}
|
||||
|
||||
@@ -0,0 +1,9 @@
|
||||
async function hello(): Promise<void> {
|
||||
console.log('hello, world!')
|
||||
}
|
||||
|
||||
async function main() {
|
||||
await hello()
|
||||
}
|
||||
|
||||
main().catch(console.error)
|
||||
@@ -0,0 +1,49 @@
|
||||
class DoneForNow {
|
||||
intent "done_for_now"
|
||||
message string
|
||||
}
|
||||
|
||||
client<llm> Qwen3 {
|
||||
provider "openai-generic"
|
||||
options {
|
||||
base_url env.BASETEN_BASE_URL
|
||||
api_key env.BASETEN_API_KEY
|
||||
}
|
||||
}
|
||||
|
||||
function DetermineNextStep(
|
||||
thread: string
|
||||
) -> DoneForNow {
|
||||
client Qwen3
|
||||
|
||||
// use /nothink for now because the thinking tokens (or streaming thereof) screw with baml (i think (no pun intended))
|
||||
prompt #"
|
||||
{{ _.role("system") }}
|
||||
|
||||
/nothink
|
||||
|
||||
You are a helpful assistant that can help with tasks.
|
||||
|
||||
{{ _.role("user") }}
|
||||
|
||||
You are working on the following thread:
|
||||
|
||||
{{ thread }}
|
||||
|
||||
What should the next step be?
|
||||
|
||||
{{ ctx.output_format }}
|
||||
"#
|
||||
}
|
||||
|
||||
test HelloWorld {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
{
|
||||
"type": "user_input",
|
||||
"data": "hello!"
|
||||
}
|
||||
"#
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,32 @@
|
||||
import { b } from "../baml_client";
|
||||
|
||||
// tool call or a respond to human tool
|
||||
type AgentResponse = Awaited<ReturnType<typeof b.DetermineNextStep>>;
|
||||
|
||||
export interface Event {
|
||||
type: string
|
||||
data: any;
|
||||
}
|
||||
|
||||
export class Thread {
|
||||
events: Event[] = [];
|
||||
|
||||
constructor(events: Event[]) {
|
||||
this.events = events;
|
||||
}
|
||||
|
||||
serializeForLLM() {
|
||||
// can change this to whatever custom serialization you want to do, XML, etc
|
||||
// e.g. https://github.com/got-agents/agents/blob/59ebbfa236fc376618f16ee08eb0f3bf7b698892/linear-assistant-ts/src/agent.ts#L66-L105
|
||||
return JSON.stringify(this.events);
|
||||
}
|
||||
}
|
||||
|
||||
// right now this just runs one turn with the LLM, but
|
||||
// we'll update this function to handle all the agent logic
|
||||
export async function agentLoop(thread: Thread): Promise<AgentResponse> {
|
||||
const nextStep = await b.DetermineNextStep(thread.serializeForLLM());
|
||||
return nextStep;
|
||||
}
|
||||
|
||||
|
||||
@@ -0,0 +1,23 @@
|
||||
// cli.ts lets you invoke the agent loop from the command line
|
||||
|
||||
import { agentLoop, Thread, Event } from "./agent";
|
||||
|
||||
export async function cli() {
|
||||
// Get command line arguments, skipping the first two (node and script name)
|
||||
const args = process.argv.slice(2);
|
||||
|
||||
if (args.length === 0) {
|
||||
console.error("Error: Please provide a message as a command line argument");
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
// Join all arguments into a single message
|
||||
const message = args.join(" ");
|
||||
|
||||
// Create a new thread with the user's message as the initial event
|
||||
const thread = new Thread([{ type: "user_input", data: message }]);
|
||||
|
||||
// Run the agent loop with the thread
|
||||
const result = await agentLoop(thread);
|
||||
console.log(result);
|
||||
}
|
||||
@@ -0,0 +1,11 @@
|
||||
import { cli } from "./cli"
|
||||
|
||||
async function hello(): Promise<void> {
|
||||
console.log('hello, world!')
|
||||
}
|
||||
|
||||
async function main() {
|
||||
await cli()
|
||||
}
|
||||
|
||||
main().catch(console.error)
|
||||
2
workshops/2025-05-17/sections/02-calculator-tools/.gitignore
vendored
Normal file
2
workshops/2025-05-17/sections/02-calculator-tools/.gitignore
vendored
Normal file
@@ -0,0 +1,2 @@
|
||||
baml_client/
|
||||
node_modules/
|
||||
84
workshops/2025-05-17/sections/02-calculator-tools/README.md
Normal file
84
workshops/2025-05-17/sections/02-calculator-tools/README.md
Normal file
@@ -0,0 +1,84 @@
|
||||
# Chapter 2 - Add Calculator Tools
|
||||
|
||||
Let's add some calculator tools to our agent.
|
||||
|
||||
Let's start by adding a tool definition for the calculator
|
||||
|
||||
These are simpile structured outputs that we'll ask the model to
|
||||
return as a "next step" in the agentic loop.
|
||||
|
||||
|
||||
cp ./walkthrough/02-tool_calculator.baml baml_src/tool_calculator.baml
|
||||
|
||||
<details>
|
||||
<summary>show file</summary>
|
||||
|
||||
```rust
|
||||
// ./walkthrough/02-tool_calculator.baml
|
||||
type CalculatorTools = AddTool | SubtractTool | MultiplyTool | DivideTool
|
||||
|
||||
|
||||
class AddTool {
|
||||
intent "add"
|
||||
a int | float
|
||||
b int | float
|
||||
}
|
||||
|
||||
class SubtractTool {
|
||||
intent "subtract"
|
||||
a int | float
|
||||
b int | float
|
||||
}
|
||||
|
||||
class MultiplyTool {
|
||||
intent "multiply"
|
||||
a int | float
|
||||
b int | float
|
||||
}
|
||||
|
||||
class DivideTool {
|
||||
intent "divide"
|
||||
a int | float
|
||||
b int | float
|
||||
}
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
Now, let's update the agent's DetermineNextStep method to
|
||||
expose the calculator tools as potential next steps
|
||||
|
||||
|
||||
```diff
|
||||
baml_src/agent.baml
|
||||
function DetermineNextStep(
|
||||
thread: string
|
||||
-) -> DoneForNow {
|
||||
+) -> CalculatorTools | DoneForNow {
|
||||
client Qwen3
|
||||
|
||||
```
|
||||
|
||||
<details>
|
||||
<summary>skip this step</summary>
|
||||
|
||||
cp ./walkthrough/02-agent.baml baml_src/agent.baml
|
||||
|
||||
</details>
|
||||
|
||||
Generate updated BAML client
|
||||
|
||||
npx baml-cli generate
|
||||
|
||||
Try out the calculator
|
||||
|
||||
npx tsx src/index.ts 'can you add 3 and 4'
|
||||
|
||||
You should see a tool call to the calculator
|
||||
|
||||
{
|
||||
intent: 'add',
|
||||
a: 3,
|
||||
b: 4
|
||||
}
|
||||
|
||||
@@ -0,0 +1,49 @@
|
||||
class DoneForNow {
|
||||
intent "done_for_now"
|
||||
message string
|
||||
}
|
||||
|
||||
client<llm> Qwen3 {
|
||||
provider "openai-generic"
|
||||
options {
|
||||
base_url env.BASETEN_BASE_URL
|
||||
api_key env.BASETEN_API_KEY
|
||||
}
|
||||
}
|
||||
|
||||
function DetermineNextStep(
|
||||
thread: string
|
||||
) -> DoneForNow {
|
||||
client Qwen3
|
||||
|
||||
// use /nothink for now because the thinking tokens (or streaming thereof) screw with baml (i think (no pun intended))
|
||||
prompt #"
|
||||
{{ _.role("system") }}
|
||||
|
||||
/nothink
|
||||
|
||||
You are a helpful assistant that can help with tasks.
|
||||
|
||||
{{ _.role("user") }}
|
||||
|
||||
You are working on the following thread:
|
||||
|
||||
{{ thread }}
|
||||
|
||||
What should the next step be?
|
||||
|
||||
{{ ctx.output_format }}
|
||||
"#
|
||||
}
|
||||
|
||||
test HelloWorld {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
{
|
||||
"type": "user_input",
|
||||
"data": "hello!"
|
||||
}
|
||||
"#
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,75 @@
|
||||
// Learn more about clients at https://docs.boundaryml.com/docs/snippets/clients/overview
|
||||
|
||||
client<llm> CustomGPT4o {
|
||||
provider openai
|
||||
options {
|
||||
model "gpt-4o"
|
||||
api_key env.OPENAI_API_KEY
|
||||
}
|
||||
}
|
||||
|
||||
client<llm> CustomGPT4oMini {
|
||||
provider openai
|
||||
retry_policy Exponential
|
||||
options {
|
||||
model "gpt-4o-mini"
|
||||
api_key env.OPENAI_API_KEY
|
||||
}
|
||||
}
|
||||
|
||||
client<llm> CustomSonnet {
|
||||
provider anthropic
|
||||
options {
|
||||
model "claude-3-5-sonnet-20241022"
|
||||
api_key env.ANTHROPIC_API_KEY
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
client<llm> CustomHaiku {
|
||||
provider anthropic
|
||||
retry_policy Constant
|
||||
options {
|
||||
model "claude-3-haiku-20240307"
|
||||
api_key env.ANTHROPIC_API_KEY
|
||||
}
|
||||
}
|
||||
|
||||
// https://docs.boundaryml.com/docs/snippets/clients/round-robin
|
||||
client<llm> CustomFast {
|
||||
provider round-robin
|
||||
options {
|
||||
// This will alternate between the two clients
|
||||
strategy [CustomGPT4oMini, CustomHaiku]
|
||||
}
|
||||
}
|
||||
|
||||
// https://docs.boundaryml.com/docs/snippets/clients/fallback
|
||||
client<llm> OpenaiFallback {
|
||||
provider fallback
|
||||
options {
|
||||
// This will try the clients in order until one succeeds
|
||||
strategy [CustomGPT4oMini, CustomGPT4oMini]
|
||||
}
|
||||
}
|
||||
|
||||
// https://docs.boundaryml.com/docs/snippets/clients/retry
|
||||
retry_policy Constant {
|
||||
max_retries 3
|
||||
// Strategy is optional
|
||||
strategy {
|
||||
type constant_delay
|
||||
delay_ms 200
|
||||
}
|
||||
}
|
||||
|
||||
retry_policy Exponential {
|
||||
max_retries 2
|
||||
// Strategy is optional
|
||||
strategy {
|
||||
type exponential_backoff
|
||||
delay_ms 300
|
||||
multiplier 1.5
|
||||
max_delay_ms 10000
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,18 @@
|
||||
// This helps use auto generate libraries you can use in the language of
|
||||
// your choice. You can have multiple generators if you use multiple languages.
|
||||
// Just ensure that the output_dir is different for each generator.
|
||||
generator target {
|
||||
// Valid values: "python/pydantic", "typescript", "ruby/sorbet", "rest/openapi"
|
||||
output_type "typescript"
|
||||
|
||||
// Where the generated code will be saved (relative to baml_src/)
|
||||
output_dir "../"
|
||||
|
||||
// The version of the BAML package you have installed (e.g. same version as your baml-py or @boundaryml/baml).
|
||||
// The BAML VSCode extension version should also match this version.
|
||||
version "0.88.0"
|
||||
|
||||
// Valid values: "sync", "async"
|
||||
// This controls what `b.FunctionName()` will be (sync or async).
|
||||
default_client_mode async
|
||||
}
|
||||
@@ -0,0 +1,32 @@
|
||||
import { b } from "../baml_client";
|
||||
|
||||
// tool call or a respond to human tool
|
||||
type AgentResponse = Awaited<ReturnType<typeof b.DetermineNextStep>>;
|
||||
|
||||
export interface Event {
|
||||
type: string
|
||||
data: any;
|
||||
}
|
||||
|
||||
export class Thread {
|
||||
events: Event[] = [];
|
||||
|
||||
constructor(events: Event[]) {
|
||||
this.events = events;
|
||||
}
|
||||
|
||||
serializeForLLM() {
|
||||
// can change this to whatever custom serialization you want to do, XML, etc
|
||||
// e.g. https://github.com/got-agents/agents/blob/59ebbfa236fc376618f16ee08eb0f3bf7b698892/linear-assistant-ts/src/agent.ts#L66-L105
|
||||
return JSON.stringify(this.events);
|
||||
}
|
||||
}
|
||||
|
||||
// right now this just runs one turn with the LLM, but
|
||||
// we'll update this function to handle all the agent logic
|
||||
export async function agentLoop(thread: Thread): Promise<AgentResponse> {
|
||||
const nextStep = await b.DetermineNextStep(thread.serializeForLLM());
|
||||
return nextStep;
|
||||
}
|
||||
|
||||
|
||||
23
workshops/2025-05-17/sections/02-calculator-tools/src/cli.ts
Normal file
23
workshops/2025-05-17/sections/02-calculator-tools/src/cli.ts
Normal file
@@ -0,0 +1,23 @@
|
||||
// cli.ts lets you invoke the agent loop from the command line
|
||||
|
||||
import { agentLoop, Thread, Event } from "./agent";
|
||||
|
||||
export async function cli() {
|
||||
// Get command line arguments, skipping the first two (node and script name)
|
||||
const args = process.argv.slice(2);
|
||||
|
||||
if (args.length === 0) {
|
||||
console.error("Error: Please provide a message as a command line argument");
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
// Join all arguments into a single message
|
||||
const message = args.join(" ");
|
||||
|
||||
// Create a new thread with the user's message as the initial event
|
||||
const thread = new Thread([{ type: "user_input", data: message }]);
|
||||
|
||||
// Run the agent loop with the thread
|
||||
const result = await agentLoop(thread);
|
||||
console.log(result);
|
||||
}
|
||||
@@ -0,0 +1,11 @@
|
||||
import { cli } from "./cli"
|
||||
|
||||
async function hello(): Promise<void> {
|
||||
console.log('hello, world!')
|
||||
}
|
||||
|
||||
async function main() {
|
||||
await cli()
|
||||
}
|
||||
|
||||
main().catch(console.error)
|
||||
@@ -0,0 +1,49 @@
|
||||
class DoneForNow {
|
||||
intent "done_for_now"
|
||||
message string
|
||||
}
|
||||
|
||||
client<llm> Qwen3 {
|
||||
provider "openai-generic"
|
||||
options {
|
||||
base_url env.BASETEN_BASE_URL
|
||||
api_key env.BASETEN_API_KEY
|
||||
}
|
||||
}
|
||||
|
||||
function DetermineNextStep(
|
||||
thread: string
|
||||
) -> CalculatorTools | DoneForNow {
|
||||
client Qwen3
|
||||
|
||||
// use /nothink for now because the thinking tokens (or streaming thereof) screw with baml (i think (no pun intended))
|
||||
prompt #"
|
||||
{{ _.role("system") }}
|
||||
|
||||
/nothink
|
||||
|
||||
You are a helpful assistant that can help with tasks.
|
||||
|
||||
{{ _.role("user") }}
|
||||
|
||||
You are working on the following thread:
|
||||
|
||||
{{ thread }}
|
||||
|
||||
What should the next step be?
|
||||
|
||||
{{ ctx.output_format }}
|
||||
"#
|
||||
}
|
||||
|
||||
test HelloWorld {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
{
|
||||
"type": "user_input",
|
||||
"data": "hello!"
|
||||
}
|
||||
"#
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,27 @@
|
||||
type CalculatorTools = AddTool | SubtractTool | MultiplyTool | DivideTool
|
||||
|
||||
|
||||
class AddTool {
|
||||
intent "add"
|
||||
a int | float
|
||||
b int | float
|
||||
}
|
||||
|
||||
class SubtractTool {
|
||||
intent "subtract"
|
||||
a int | float
|
||||
b int | float
|
||||
}
|
||||
|
||||
class MultiplyTool {
|
||||
intent "multiply"
|
||||
a int | float
|
||||
b int | float
|
||||
}
|
||||
|
||||
class DivideTool {
|
||||
intent "divide"
|
||||
a int | float
|
||||
b int | float
|
||||
}
|
||||
|
||||
2
workshops/2025-05-17/sections/03-tool-loop/.gitignore
vendored
Normal file
2
workshops/2025-05-17/sections/03-tool-loop/.gitignore
vendored
Normal file
@@ -0,0 +1,2 @@
|
||||
baml_client/
|
||||
node_modules/
|
||||
194
workshops/2025-05-17/sections/03-tool-loop/README.md
Normal file
194
workshops/2025-05-17/sections/03-tool-loop/README.md
Normal file
@@ -0,0 +1,194 @@
|
||||
# Chapter 3 - Process Tool Calls in a Loop
|
||||
|
||||
Now let's add a real agentic loop that can run the tools and get a final answer from the LLM.
|
||||
|
||||
First, lets update the agent to handle the tool call
|
||||
|
||||
|
||||
```diff
|
||||
src/agent.ts
|
||||
}
|
||||
|
||||
-// right now this just runs one turn with the LLM, but
|
||||
-// we'll update this function to handle all the agent logic
|
||||
-export async function agentLoop(thread: Thread): Promise<AgentResponse> {
|
||||
- const nextStep = await b.DetermineNextStep(thread.serializeForLLM());
|
||||
- return nextStep;
|
||||
+
|
||||
+
|
||||
+export async function agentLoop(thread: Thread): Promise<string> {
|
||||
+
|
||||
+ while (true) {
|
||||
+ const nextStep = await b.DetermineNextStep(thread.serializeForLLM());
|
||||
+ console.log("nextStep", nextStep);
|
||||
+
|
||||
+ switch (nextStep.intent) {
|
||||
+ case "done_for_now":
|
||||
+ // response to human, return the next step object
|
||||
+ return nextStep.message;
|
||||
+ case "add":
|
||||
+ thread.events.push({
|
||||
+ "type": "tool_call",
|
||||
+ "data": nextStep
|
||||
+ });
|
||||
+ const result = nextStep.a + nextStep.b;
|
||||
+ console.log("tool_response", result);
|
||||
+ thread.events.push({
|
||||
+ "type": "tool_response",
|
||||
+ "data": result
|
||||
+ });
|
||||
+ continue;
|
||||
+ default:
|
||||
+ throw new Error(`Unknown intent: ${nextStep.intent}`);
|
||||
+ }
|
||||
+ }
|
||||
}
|
||||
|
||||
```
|
||||
|
||||
<details>
|
||||
<summary>skip this step</summary>
|
||||
|
||||
cp ./walkthrough/03-agent.ts src/agent.ts
|
||||
|
||||
</details>
|
||||
|
||||
Now, lets try it out
|
||||
|
||||
|
||||
npx tsx src/index.ts 'can you add 3 and 4'
|
||||
|
||||
you should see the agent call the tool and then return the result
|
||||
|
||||
{
|
||||
intent: 'done_for_now',
|
||||
message: 'The sum of 3 and 4 is 7.'
|
||||
}
|
||||
|
||||
For the next step, we'll do a more complex calculation, let's turn off the baml logs for more concise output
|
||||
|
||||
export BAML_LOG=off
|
||||
|
||||
Try a multi-step calculation
|
||||
|
||||
npx tsx src/index.ts 'can you add 3 and 4, then add 6 to that result'
|
||||
|
||||
you'll notice that tools like multiply and divide are not available
|
||||
|
||||
npx tsx src/index.ts 'can you multiply 3 and 4'
|
||||
|
||||
next, let's add handlers for the rest of the calculator tools
|
||||
|
||||
|
||||
```diff
|
||||
src/agent.ts
|
||||
-import { b } from "../baml_client";
|
||||
+import { AddTool, SubtractTool, DivideTool, MultiplyTool, b } from "../baml_client";
|
||||
|
||||
-// tool call or a respond to human tool
|
||||
-type AgentResponse = Awaited<ReturnType<typeof b.DetermineNextStep>>;
|
||||
-
|
||||
export interface Event {
|
||||
type: string
|
||||
}
|
||||
|
||||
+export type CalculatorTool = AddTool | SubtractTool | MultiplyTool | DivideTool;
|
||||
|
||||
+export async function handleNextStep(nextStep: CalculatorTool, thread: Thread): Promise<Thread> {
|
||||
+ let result: number;
|
||||
+ switch (nextStep.intent) {
|
||||
+ case "add":
|
||||
+ result = nextStep.a + nextStep.b;
|
||||
+ console.log("tool_response", result);
|
||||
+ thread.events.push({
|
||||
+ "type": "tool_response",
|
||||
+ "data": result
|
||||
+ });
|
||||
+ return thread;
|
||||
+ case "subtract":
|
||||
+ result = nextStep.a - nextStep.b;
|
||||
+ console.log("tool_response", result);
|
||||
+ thread.events.push({
|
||||
+ "type": "tool_response",
|
||||
+ "data": result
|
||||
+ });
|
||||
+ return thread;
|
||||
+ case "multiply":
|
||||
+ result = nextStep.a * nextStep.b;
|
||||
+ console.log("tool_response", result);
|
||||
+ thread.events.push({
|
||||
+ "type": "tool_response",
|
||||
+ "data": result
|
||||
+ });
|
||||
+ return thread;
|
||||
+ case "divide":
|
||||
+ result = nextStep.a / nextStep.b;
|
||||
+ console.log("tool_response", result);
|
||||
+ thread.events.push({
|
||||
+ "type": "tool_response",
|
||||
+ "data": result
|
||||
+ });
|
||||
+ return thread;
|
||||
+ }
|
||||
+}
|
||||
|
||||
export async function agentLoop(thread: Thread): Promise<string> {
|
||||
console.log("nextStep", nextStep);
|
||||
|
||||
+ thread.events.push({
|
||||
+ "type": "tool_call",
|
||||
+ "data": nextStep
|
||||
+ });
|
||||
+
|
||||
switch (nextStep.intent) {
|
||||
case "done_for_now":
|
||||
return nextStep.message;
|
||||
case "add":
|
||||
- thread.events.push({
|
||||
- "type": "tool_call",
|
||||
- "data": nextStep
|
||||
- });
|
||||
- const result = nextStep.a + nextStep.b;
|
||||
- console.log("tool_response", result);
|
||||
- thread.events.push({
|
||||
- "type": "tool_response",
|
||||
- "data": result
|
||||
- });
|
||||
- continue;
|
||||
- default:
|
||||
- throw new Error(`Unknown intent: ${nextStep.intent}`);
|
||||
+ case "subtract":
|
||||
+ case "multiply":
|
||||
+ case "divide":
|
||||
+ thread = await handleNextStep(nextStep, thread);
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
<details>
|
||||
<summary>skip this step</summary>
|
||||
|
||||
cp ./walkthrough/03b-agent.ts src/agent.ts
|
||||
|
||||
</details>
|
||||
|
||||
Test subtraction
|
||||
|
||||
npx tsx src/index.ts 'can you subtract 3 from 4'
|
||||
|
||||
now, let's test the multiplication tool
|
||||
|
||||
|
||||
npx tsx src/index.ts 'can you multiply 3 and 4'
|
||||
|
||||
finally, let's test a more complex calculation with multiple operations
|
||||
|
||||
|
||||
npx tsx src/index.ts 'can you multiply 3 and 4, then divide the result by 2 and then add 12 to that result'
|
||||
|
||||
congratulations, you've taking your first step into hand-rolling an agent loop.
|
||||
|
||||
from here, we're going to start incorporating some more intermediate and advanced
|
||||
concepts for 12-factor agents.
|
||||
|
||||
|
||||
@@ -0,0 +1,49 @@
|
||||
class DoneForNow {
|
||||
intent "done_for_now"
|
||||
message string
|
||||
}
|
||||
|
||||
client<llm> Qwen3 {
|
||||
provider "openai-generic"
|
||||
options {
|
||||
base_url env.BASETEN_BASE_URL
|
||||
api_key env.BASETEN_API_KEY
|
||||
}
|
||||
}
|
||||
|
||||
function DetermineNextStep(
|
||||
thread: string
|
||||
) -> CalculatorTools | DoneForNow {
|
||||
client Qwen3
|
||||
|
||||
// use /nothink for now because the thinking tokens (or streaming thereof) screw with baml (i think (no pun intended))
|
||||
prompt #"
|
||||
{{ _.role("system") }}
|
||||
|
||||
/nothink
|
||||
|
||||
You are a helpful assistant that can help with tasks.
|
||||
|
||||
{{ _.role("user") }}
|
||||
|
||||
You are working on the following thread:
|
||||
|
||||
{{ thread }}
|
||||
|
||||
What should the next step be?
|
||||
|
||||
{{ ctx.output_format }}
|
||||
"#
|
||||
}
|
||||
|
||||
test HelloWorld {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
{
|
||||
"type": "user_input",
|
||||
"data": "hello!"
|
||||
}
|
||||
"#
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,75 @@
|
||||
// Learn more about clients at https://docs.boundaryml.com/docs/snippets/clients/overview
|
||||
|
||||
client<llm> CustomGPT4o {
|
||||
provider openai
|
||||
options {
|
||||
model "gpt-4o"
|
||||
api_key env.OPENAI_API_KEY
|
||||
}
|
||||
}
|
||||
|
||||
client<llm> CustomGPT4oMini {
|
||||
provider openai
|
||||
retry_policy Exponential
|
||||
options {
|
||||
model "gpt-4o-mini"
|
||||
api_key env.OPENAI_API_KEY
|
||||
}
|
||||
}
|
||||
|
||||
client<llm> CustomSonnet {
|
||||
provider anthropic
|
||||
options {
|
||||
model "claude-3-5-sonnet-20241022"
|
||||
api_key env.ANTHROPIC_API_KEY
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
client<llm> CustomHaiku {
|
||||
provider anthropic
|
||||
retry_policy Constant
|
||||
options {
|
||||
model "claude-3-haiku-20240307"
|
||||
api_key env.ANTHROPIC_API_KEY
|
||||
}
|
||||
}
|
||||
|
||||
// https://docs.boundaryml.com/docs/snippets/clients/round-robin
|
||||
client<llm> CustomFast {
|
||||
provider round-robin
|
||||
options {
|
||||
// This will alternate between the two clients
|
||||
strategy [CustomGPT4oMini, CustomHaiku]
|
||||
}
|
||||
}
|
||||
|
||||
// https://docs.boundaryml.com/docs/snippets/clients/fallback
|
||||
client<llm> OpenaiFallback {
|
||||
provider fallback
|
||||
options {
|
||||
// This will try the clients in order until one succeeds
|
||||
strategy [CustomGPT4oMini, CustomGPT4oMini]
|
||||
}
|
||||
}
|
||||
|
||||
// https://docs.boundaryml.com/docs/snippets/clients/retry
|
||||
retry_policy Constant {
|
||||
max_retries 3
|
||||
// Strategy is optional
|
||||
strategy {
|
||||
type constant_delay
|
||||
delay_ms 200
|
||||
}
|
||||
}
|
||||
|
||||
retry_policy Exponential {
|
||||
max_retries 2
|
||||
// Strategy is optional
|
||||
strategy {
|
||||
type exponential_backoff
|
||||
delay_ms 300
|
||||
multiplier 1.5
|
||||
max_delay_ms 10000
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,18 @@
|
||||
// This helps use auto generate libraries you can use in the language of
|
||||
// your choice. You can have multiple generators if you use multiple languages.
|
||||
// Just ensure that the output_dir is different for each generator.
|
||||
generator target {
|
||||
// Valid values: "python/pydantic", "typescript", "ruby/sorbet", "rest/openapi"
|
||||
output_type "typescript"
|
||||
|
||||
// Where the generated code will be saved (relative to baml_src/)
|
||||
output_dir "../"
|
||||
|
||||
// The version of the BAML package you have installed (e.g. same version as your baml-py or @boundaryml/baml).
|
||||
// The BAML VSCode extension version should also match this version.
|
||||
version "0.88.0"
|
||||
|
||||
// Valid values: "sync", "async"
|
||||
// This controls what `b.FunctionName()` will be (sync or async).
|
||||
default_client_mode async
|
||||
}
|
||||
@@ -0,0 +1,27 @@
|
||||
type CalculatorTools = AddTool | SubtractTool | MultiplyTool | DivideTool
|
||||
|
||||
|
||||
class AddTool {
|
||||
intent "add"
|
||||
a int | float
|
||||
b int | float
|
||||
}
|
||||
|
||||
class SubtractTool {
|
||||
intent "subtract"
|
||||
a int | float
|
||||
b int | float
|
||||
}
|
||||
|
||||
class MultiplyTool {
|
||||
intent "multiply"
|
||||
a int | float
|
||||
b int | float
|
||||
}
|
||||
|
||||
class DivideTool {
|
||||
intent "divide"
|
||||
a int | float
|
||||
b int | float
|
||||
}
|
||||
|
||||
32
workshops/2025-05-17/sections/03-tool-loop/src/agent.ts
Normal file
32
workshops/2025-05-17/sections/03-tool-loop/src/agent.ts
Normal file
@@ -0,0 +1,32 @@
|
||||
import { b } from "../baml_client";
|
||||
|
||||
// tool call or a respond to human tool
|
||||
type AgentResponse = Awaited<ReturnType<typeof b.DetermineNextStep>>;
|
||||
|
||||
export interface Event {
|
||||
type: string
|
||||
data: any;
|
||||
}
|
||||
|
||||
export class Thread {
|
||||
events: Event[] = [];
|
||||
|
||||
constructor(events: Event[]) {
|
||||
this.events = events;
|
||||
}
|
||||
|
||||
serializeForLLM() {
|
||||
// can change this to whatever custom serialization you want to do, XML, etc
|
||||
// e.g. https://github.com/got-agents/agents/blob/59ebbfa236fc376618f16ee08eb0f3bf7b698892/linear-assistant-ts/src/agent.ts#L66-L105
|
||||
return JSON.stringify(this.events);
|
||||
}
|
||||
}
|
||||
|
||||
// right now this just runs one turn with the LLM, but
|
||||
// we'll update this function to handle all the agent logic
|
||||
export async function agentLoop(thread: Thread): Promise<AgentResponse> {
|
||||
const nextStep = await b.DetermineNextStep(thread.serializeForLLM());
|
||||
return nextStep;
|
||||
}
|
||||
|
||||
|
||||
23
workshops/2025-05-17/sections/03-tool-loop/src/cli.ts
Normal file
23
workshops/2025-05-17/sections/03-tool-loop/src/cli.ts
Normal file
@@ -0,0 +1,23 @@
|
||||
// cli.ts lets you invoke the agent loop from the command line
|
||||
|
||||
import { agentLoop, Thread, Event } from "./agent";
|
||||
|
||||
export async function cli() {
|
||||
// Get command line arguments, skipping the first two (node and script name)
|
||||
const args = process.argv.slice(2);
|
||||
|
||||
if (args.length === 0) {
|
||||
console.error("Error: Please provide a message as a command line argument");
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
// Join all arguments into a single message
|
||||
const message = args.join(" ");
|
||||
|
||||
// Create a new thread with the user's message as the initial event
|
||||
const thread = new Thread([{ type: "user_input", data: message }]);
|
||||
|
||||
// Run the agent loop with the thread
|
||||
const result = await agentLoop(thread);
|
||||
console.log(result);
|
||||
}
|
||||
11
workshops/2025-05-17/sections/03-tool-loop/src/index.ts
Normal file
11
workshops/2025-05-17/sections/03-tool-loop/src/index.ts
Normal file
@@ -0,0 +1,11 @@
|
||||
import { cli } from "./cli"
|
||||
|
||||
async function hello(): Promise<void> {
|
||||
console.log('hello, world!')
|
||||
}
|
||||
|
||||
async function main() {
|
||||
await cli()
|
||||
}
|
||||
|
||||
main().catch(console.error)
|
||||
@@ -0,0 +1,55 @@
|
||||
import { b } from "../baml_client";
|
||||
|
||||
// tool call or a respond to human tool
|
||||
type AgentResponse = Awaited<ReturnType<typeof b.DetermineNextStep>>;
|
||||
|
||||
export interface Event {
|
||||
type: string
|
||||
data: any;
|
||||
}
|
||||
|
||||
export class Thread {
|
||||
events: Event[] = [];
|
||||
|
||||
constructor(events: Event[]) {
|
||||
this.events = events;
|
||||
}
|
||||
|
||||
serializeForLLM() {
|
||||
// can change this to whatever custom serialization you want to do, XML, etc
|
||||
// e.g. https://github.com/got-agents/agents/blob/59ebbfa236fc376618f16ee08eb0f3bf7b698892/linear-assistant-ts/src/agent.ts#L66-L105
|
||||
return JSON.stringify(this.events);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
export async function agentLoop(thread: Thread): Promise<string> {
|
||||
|
||||
while (true) {
|
||||
const nextStep = await b.DetermineNextStep(thread.serializeForLLM());
|
||||
console.log("nextStep", nextStep);
|
||||
|
||||
switch (nextStep.intent) {
|
||||
case "done_for_now":
|
||||
// response to human, return the next step object
|
||||
return nextStep.message;
|
||||
case "add":
|
||||
thread.events.push({
|
||||
"type": "tool_call",
|
||||
"data": nextStep
|
||||
});
|
||||
const result = nextStep.a + nextStep.b;
|
||||
console.log("tool_response", result);
|
||||
thread.events.push({
|
||||
"type": "tool_response",
|
||||
"data": result
|
||||
});
|
||||
continue;
|
||||
default:
|
||||
throw new Error(`Unknown intent: ${nextStep.intent}`);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -0,0 +1,86 @@
|
||||
import { AddTool, SubtractTool, DivideTool, MultiplyTool, b } from "../baml_client";
|
||||
|
||||
export interface Event {
|
||||
type: string
|
||||
data: any;
|
||||
}
|
||||
|
||||
export class Thread {
|
||||
events: Event[] = [];
|
||||
|
||||
constructor(events: Event[]) {
|
||||
this.events = events;
|
||||
}
|
||||
|
||||
serializeForLLM() {
|
||||
// can change this to whatever custom serialization you want to do, XML, etc
|
||||
// e.g. https://github.com/got-agents/agents/blob/59ebbfa236fc376618f16ee08eb0f3bf7b698892/linear-assistant-ts/src/agent.ts#L66-L105
|
||||
return JSON.stringify(this.events);
|
||||
}
|
||||
}
|
||||
|
||||
export type CalculatorTool = AddTool | SubtractTool | MultiplyTool | DivideTool;
|
||||
|
||||
export async function handleNextStep(nextStep: CalculatorTool, thread: Thread): Promise<Thread> {
|
||||
let result: number;
|
||||
switch (nextStep.intent) {
|
||||
case "add":
|
||||
result = nextStep.a + nextStep.b;
|
||||
console.log("tool_response", result);
|
||||
thread.events.push({
|
||||
"type": "tool_response",
|
||||
"data": result
|
||||
});
|
||||
return thread;
|
||||
case "subtract":
|
||||
result = nextStep.a - nextStep.b;
|
||||
console.log("tool_response", result);
|
||||
thread.events.push({
|
||||
"type": "tool_response",
|
||||
"data": result
|
||||
});
|
||||
return thread;
|
||||
case "multiply":
|
||||
result = nextStep.a * nextStep.b;
|
||||
console.log("tool_response", result);
|
||||
thread.events.push({
|
||||
"type": "tool_response",
|
||||
"data": result
|
||||
});
|
||||
return thread;
|
||||
case "divide":
|
||||
result = nextStep.a / nextStep.b;
|
||||
console.log("tool_response", result);
|
||||
thread.events.push({
|
||||
"type": "tool_response",
|
||||
"data": result
|
||||
});
|
||||
return thread;
|
||||
}
|
||||
}
|
||||
|
||||
export async function agentLoop(thread: Thread): Promise<string> {
|
||||
|
||||
while (true) {
|
||||
const nextStep = await b.DetermineNextStep(thread.serializeForLLM());
|
||||
console.log("nextStep", nextStep);
|
||||
|
||||
thread.events.push({
|
||||
"type": "tool_call",
|
||||
"data": nextStep
|
||||
});
|
||||
|
||||
switch (nextStep.intent) {
|
||||
case "done_for_now":
|
||||
// response to human, return the next step object
|
||||
return nextStep.message;
|
||||
case "add":
|
||||
case "subtract":
|
||||
case "multiply":
|
||||
case "divide":
|
||||
thread = await handleNextStep(nextStep, thread);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -9,12 +9,12 @@ targets:
|
||||
newFiles:
|
||||
cat: false
|
||||
cp: true
|
||||
# - folders:
|
||||
# path: "./build/sections"
|
||||
# skip:
|
||||
# - "cleanup"
|
||||
# final:
|
||||
# dirName: "final"
|
||||
- folders:
|
||||
path: "./build/sections"
|
||||
skip:
|
||||
- "cleanup"
|
||||
final:
|
||||
dirName: "final"
|
||||
|
||||
sections:
|
||||
- name: cleanup
|
||||
@@ -220,3 +220,465 @@ sections:
|
||||
|
||||
from here, we're going to start incorporating some more intermediate and advanced
|
||||
concepts for 12-factor agents.
|
||||
|
||||
- name: baml-tests
|
||||
title: "Chapter 4 - Add Tests to agent.baml"
|
||||
text: "Let's add some tests to our BAML agent."
|
||||
steps:
|
||||
- text: to start, leave the baml logs enabled
|
||||
command: |
|
||||
export BAML_LOG=debug
|
||||
- text: |
|
||||
next, let's add some tests to the agent
|
||||
|
||||
We'll start with a simple test that checks the agent's ability to handle
|
||||
a basic calculation.
|
||||
|
||||
file: {src: ./walkthrough/04-agent.baml, dest: baml_src/agent.baml}
|
||||
- text: "Run the tests"
|
||||
command: |
|
||||
npx baml-cli test
|
||||
- text: |
|
||||
now, let's improve the test with assertions!
|
||||
|
||||
Assertions are a great way to make sure the agent is working as expected,
|
||||
and can easily be extended to check for more complex behavior.
|
||||
|
||||
file: {src: ./walkthrough/04b-agent.baml, dest: baml_src/agent.baml}
|
||||
- text: "Run the tests"
|
||||
command: |
|
||||
npx baml-cli test
|
||||
- text: |
|
||||
as you add more tests, you can disable the logs to keep the output clean.
|
||||
You may want to turn them on as you iterate on specific tests.
|
||||
command: |
|
||||
export BAML_LOG=off
|
||||
- text: |
|
||||
now, let's add some more complex test cases,
|
||||
where we resume from in the middle of an in-progress
|
||||
agentic context window
|
||||
|
||||
|
||||
file: {src: ./walkthrough/04c-agent.baml, dest: baml_src/agent.baml}
|
||||
- text: |
|
||||
let's try to run it
|
||||
command: |
|
||||
npx baml-cli test
|
||||
|
||||
- name: human-tools
|
||||
title: "Chapter 5 - Multiple Human Tools"
|
||||
text: |
|
||||
In this section, we'll add support for multiple tools that serve to
|
||||
contact humans.
|
||||
steps:
|
||||
- text: "for this section, we'll disable the baml logs. You can optionally enable them if you want to see more details."
|
||||
command: |
|
||||
export BAML_LOG=off
|
||||
- text: |
|
||||
first, let's add a tool that can request clarification from a human
|
||||
|
||||
this will be different from the "done_for_now" tool,
|
||||
and can be used to more flexibly handle different types of human interactions
|
||||
in your agent.
|
||||
|
||||
file: {src: ./walkthrough/05-agent.baml, dest: baml_src/agent.baml}
|
||||
- text: |
|
||||
next, let's re-generate the client code
|
||||
|
||||
NOTE - if you're using the VSCode extension for BAML,
|
||||
the client will be regenerated automatically when you save the file
|
||||
in your editor.
|
||||
|
||||
command: |
|
||||
npx baml-cli generate
|
||||
incremental: true
|
||||
- text: |
|
||||
now, let's update the agent to use the new tool
|
||||
|
||||
file: {src: ./walkthrough/05-agent.ts, dest: src/agent.ts}
|
||||
- text: |
|
||||
next, let's update the CLI to handle clarification requests
|
||||
by requesting input from the user on the CLI
|
||||
|
||||
file: {src: ./walkthrough/05-cli.ts, dest: src/cli.ts}
|
||||
- text: |
|
||||
let's try it out
|
||||
|
||||
command: |
|
||||
npx tsx src/index.ts 'can you multiply 3 and FD*(#F&& '
|
||||
- text: |
|
||||
next, let's add a test that checks the agent's ability to handle
|
||||
a clarification request
|
||||
|
||||
file: {src: ./walkthrough/05b-agent.baml, dest: baml_src/agent.baml}
|
||||
- text: |
|
||||
and now we can run the tests again
|
||||
command: |
|
||||
npx baml-cli test
|
||||
- text: |
|
||||
you'll notice the new test passes, but the hello world test fails
|
||||
|
||||
This is because the agent's default behavior is to return "done_for_now"
|
||||
|
||||
file: {src: ./walkthrough/05c-agent.baml, dest: baml_src/agent.baml}
|
||||
- text: "Verify tests pass"
|
||||
command: |
|
||||
npx baml-cli test
|
||||
|
||||
- name: customize-prompt
|
||||
title: "Chapter 6 - Customize Your Prompt with Reasoning"
|
||||
text: |
|
||||
In this section, we'll explore how to customize the prompt of the agent
|
||||
with reasoning steps.
|
||||
|
||||
this is core to [factor 2 - own your prompts](https://github.com/humanlayer/12-factor-agents/blob/main/content/factor-2-own-your-prompts.md)
|
||||
|
||||
there's a deep dive on reasoning on AI That Works [reasoning models versus reasoning steps](https://github.com/hellovai/ai-that-works/tree/main/2025-04-07-reasoning-models-vs-prompts)
|
||||
|
||||
steps:
|
||||
- text: "for this section, it will be helpful to leave the baml logs enabled"
|
||||
command: |
|
||||
export BAML_LOG=debug
|
||||
- text: |
|
||||
update the agent prompt to include a reasoning step
|
||||
file: {src: ./walkthrough/06-agent.baml, dest: baml_src/agent.baml}
|
||||
- text: generate the updated client
|
||||
command: |
|
||||
npx baml-cli generate
|
||||
incremental: true
|
||||
- text: |
|
||||
now, you can try it out with a simple prompt
|
||||
command: |
|
||||
npx tsx src/index.ts 'can you multiply 3 and 4'
|
||||
results:
|
||||
- text: you should see output from the baml logs showing the reasoning steps
|
||||
- text: |
|
||||
#### optional challenge
|
||||
|
||||
add a field to your tool output format that includes the reasoning steps in the output!
|
||||
|
||||
- name: context-window
|
||||
title: "Chapter 7 - Customize Your Context Window"
|
||||
text: |
|
||||
In this section, we'll explore how to customize the context window
|
||||
of the agent.
|
||||
|
||||
this is core to [factor 3 - own your context window](https://github.com/humanlayer/12-factor-agents/blob/main/content/factor-3-own-your-context-window.md)
|
||||
|
||||
steps:
|
||||
- text: |
|
||||
update the agent to pretty-print the Context window for the model
|
||||
file: {src: ./walkthrough/07-agent.ts, dest: src/agent.ts}
|
||||
- text: "Test the formatting"
|
||||
command: |
|
||||
BAML_LOG=info npx tsx src/index.ts 'can you multiply 3 and 4, then divide the result by 2 and then add 12 to that result'
|
||||
- text: |
|
||||
next, let's update the agent to use XML formatting instead
|
||||
|
||||
this is a very popular format for passing data to a model,
|
||||
|
||||
among other things, because of the token efficiency of XML.
|
||||
|
||||
file: {src: ./walkthrough/07b-agent.ts, dest: src/agent.ts}
|
||||
- text: |
|
||||
let's try it out
|
||||
command: |
|
||||
BAML_LOG=info npx tsx src/index.ts 'can you multiply 3 and 4, then divide the result by 2 and then add 12 to that result'
|
||||
- text: |
|
||||
lets update our tests to match the new output format
|
||||
file: {src: ./walkthrough/07c-agent.baml, dest: baml_src/agent.baml}
|
||||
- text: |
|
||||
check out the updated tests
|
||||
command: |
|
||||
npx baml-cli test
|
||||
|
||||
- name: api-endpoints
|
||||
title: "Chapter 8 - Adding API Endpoints"
|
||||
text: "Add an Express server to expose the agent via HTTP."
|
||||
steps:
|
||||
- text: "for this section, we'll disable the baml logs. You can optionally enable them if you want to see more details."
|
||||
command: |
|
||||
export BAML_LOG=off
|
||||
- text: "Install Express and types"
|
||||
command: |
|
||||
npm install express && npm install --save-dev @types/express supertest
|
||||
incremental: true
|
||||
- text: "Add the server implementation"
|
||||
file: {src: ./walkthrough/08-server.ts, dest: src/server.ts}
|
||||
- text: "Start the server"
|
||||
command: |
|
||||
npx tsx src/server.ts
|
||||
- text: "Test with curl (in another terminal)"
|
||||
command: |
|
||||
curl -X POST http://localhost:3000/thread \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"message":"can you add 3 and 4"}'
|
||||
results:
|
||||
- text: |
|
||||
You should get an answer from the agent which includes the
|
||||
agentic trace, ending in a message like:
|
||||
|
||||
code: |
|
||||
{"intent":"done_for_now","message":"The sum of 3 and 4 is 7."}
|
||||
|
||||
- name: state-management
|
||||
title: "Chapter 9 - In-Memory State and Async Clarification"
|
||||
text: "Add state management and async clarification support."
|
||||
steps:
|
||||
- text: "for this section, we'll disable the baml logs. You can optionally enable them if you want to see more details."
|
||||
command: |
|
||||
export BAML_LOG=off
|
||||
- text: "Add some simple in-memory state management for threads"
|
||||
file: {src: ./walkthrough/09-state.ts, dest: src/state.ts}
|
||||
- text: |
|
||||
update the server to use the state management
|
||||
|
||||
* Add thread state management using `ThreadStore`
|
||||
* return thread IDs and response URLs from the /thread endpoint
|
||||
* implement GET /thread/:id
|
||||
* implement POST /thread/:id/response
|
||||
file: {src: ./walkthrough/09-server.ts, dest: src/server.ts}
|
||||
- text: "Start the server"
|
||||
command: |
|
||||
npx tsx src/server.ts
|
||||
- text: "Test clarification flow"
|
||||
command: |
|
||||
curl -X POST http://localhost:3000/thread \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"message":"can you multiply 3 and xyz"}'
|
||||
|
||||
- name: human-approval
|
||||
title: "Chapter 10 - Adding Human Approval"
|
||||
text: "Add support for human approval of operations."
|
||||
steps:
|
||||
- text: "for this section, we'll disable the baml logs. You can optionally enable them if you want to see more details."
|
||||
command: |
|
||||
export BAML_LOG=off
|
||||
- text: |
|
||||
update the server to handle human approvals
|
||||
|
||||
* Import `handleNextStep` to execute approved actions
|
||||
* Add two payload types to distinguish approvals from responses
|
||||
* Handle responses and approvals differently in the endpoint
|
||||
* Show better error messages when things go wrongs
|
||||
|
||||
file: {src: ./walkthrough/10-server.ts, dest: src/server.ts}
|
||||
- text: "Add a few methods to the agent to handle approvals and responses"
|
||||
file: {src: ./walkthrough/10-agent.ts, dest: src/agent.ts}
|
||||
- text: "Start the server"
|
||||
command: |
|
||||
npx tsx src/server.ts
|
||||
- text: "Test division with approval"
|
||||
command: |
|
||||
curl -X POST http://localhost:3000/thread \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"message":"can you divide 3 by 4"}'
|
||||
results:
|
||||
- text: "You should see:"
|
||||
code: |
|
||||
{
|
||||
"thread_id": "2b243b66-215a-4f37-8bc6-9ace3849043b",
|
||||
"events": [
|
||||
{
|
||||
"type": "user_input",
|
||||
"data": "can you divide 3 by 4"
|
||||
},
|
||||
{
|
||||
"type": "tool_call",
|
||||
"data": {
|
||||
"intent": "divide",
|
||||
"a": 3,
|
||||
"b": 4,
|
||||
"response_url": "/thread/2b243b66-215a-4f37-8bc6-9ace3849043b/response"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
- text: "reject the request with another curl call, changing the thread ID"
|
||||
command: |
|
||||
curl -X POST 'http://localhost:3000/thread/{thread_id}/response' \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"type": "approval", "approved": false, "comment": "I dont think thats right, use 5 instead of 4"}'
|
||||
results:
|
||||
- text: 'You should see: the last tool call is now `"intent":"divide","a":3,"b":5`'
|
||||
code: |
|
||||
{
|
||||
"events": [
|
||||
{
|
||||
"type": "user_input",
|
||||
"data": "can you divide 3 by 4"
|
||||
},
|
||||
{
|
||||
"type": "tool_call",
|
||||
"data": {
|
||||
"intent": "divide",
|
||||
"a": 3,
|
||||
"b": 4,
|
||||
"response_url": "/thread/2b243b66-215a-4f37-8bc6-9ace3849043b/response"
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "tool_response",
|
||||
"data": "user denied the operation with feedback: \"I dont think thats right, use 5 instead of 4\""
|
||||
},
|
||||
{
|
||||
"type": "tool_call",
|
||||
"data": {
|
||||
"intent": "divide",
|
||||
"a": 3,
|
||||
"b": 5,
|
||||
"response_url": "/thread/1f1f5ff5-20d7-4114-97b4-3fc52d5e0816/response"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
- text: "now you can approve the operation"
|
||||
command: |
|
||||
curl -X POST 'http://localhost:3000/thread/{thread_id}/response' \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"type": "approval", "approved": true}'
|
||||
results:
|
||||
- text: "you should see the final message includes the tool response and final result!"
|
||||
code: |
|
||||
...
|
||||
{
|
||||
"type": "tool_response",
|
||||
"data": 0.5
|
||||
},
|
||||
{
|
||||
"type": "done_for_now",
|
||||
"message": "I divided 3 by 6 and the result is 0.5. If you have any more operations or queries, feel free to ask!",
|
||||
"response_url": "/thread/2b469403-c497-4797-b253-043aae830209/response"
|
||||
}
|
||||
|
||||
- name: humanlayer-approval
|
||||
title: "Chapter 11 - Human Approvals over email"
|
||||
text: |
|
||||
in this section, we'll add support for human approvals over email.
|
||||
|
||||
This will start a little bit contrived, just to get the concepts down -
|
||||
|
||||
We'll start by invoking the workflow from the CLI but approvals for `divide`
|
||||
and `request_more_information` will be handled over email,
|
||||
then the final `done_for_now` answer will be printed back to the CLI
|
||||
|
||||
While contrived, this is a great example of the flexibility you get from
|
||||
[factor 7 - contact humans with tools](https://github.com/humanlayer/12-factor-agents/blob/main/content/factor-7-contact-humans-with-tools.md)
|
||||
|
||||
steps:
|
||||
- text: "for this section, we'll disable the baml logs. You can optionally enable them if you want to see more details."
|
||||
command: |
|
||||
export BAML_LOG=off
|
||||
- text: "Install HumanLayer"
|
||||
command: |
|
||||
npm install humanlayer
|
||||
incremental: true
|
||||
- text: "Update CLI to send `divide` and `request_more_information` to a human via email"
|
||||
file: {src: ./walkthrough/11-cli.ts, dest: src/cli.ts}
|
||||
- text: "Run the CLI"
|
||||
command: |
|
||||
npx tsx src/index.ts 'can you divide 4 by 5'
|
||||
results:
|
||||
- text: "The last line of your program should mention human review step"
|
||||
code: |
|
||||
nextStep { intent: 'divide', a: 4, b: 5 }
|
||||
HumanLayer: Requested human approval from HumanLayer cloud
|
||||
- text: |
|
||||
go ahead and respond to the email with some feedback:
|
||||
|
||||
|
||||
- text: |
|
||||
you should get another email with an updated attempt based on your feedback!
|
||||
|
||||
You can go ahead and approve this one:
|
||||
|
||||
|
||||
results:
|
||||
- text: and your final output will look like
|
||||
code: |
|
||||
nextStep {
|
||||
intent: 'done_for_now',
|
||||
message: 'The division of 4 by 5 is 0.8. If you have any other calculations or questions, feel free to ask!'
|
||||
}
|
||||
The division of 4 by 5 is 0.8. If you have any other calculations or questions, feel free to ask!
|
||||
- text: |
|
||||
lets implement the `request_more_information` flow as well
|
||||
file: {src: ./walkthrough/11b-cli.ts, dest: src/cli.ts}
|
||||
- text: |
|
||||
lets test the require_approval flow as by asking for a calculation
|
||||
with garbled input:
|
||||
command: |
|
||||
npx tsx src/index.ts 'can you multiply 4 and xyz'
|
||||
- text: "You should get an email with a request for clarification"
|
||||
command: |
|
||||
Can you clarify what 'xyz' represents in this context? Is it a specific number, variable, or something else?
|
||||
- text: you can response with something like
|
||||
command: |
|
||||
use 8 instead of xyz
|
||||
results:
|
||||
- text: you should see a final result on the CLI like
|
||||
code: |
|
||||
I have multiplied 4 and xyz, using the value 8 for xyz, resulting in 32.
|
||||
- text: |
|
||||
as a final step, lets explore using a custom html template for the email
|
||||
file: {src: ./walkthrough/11c-cli.ts, dest: src/cli.ts}
|
||||
- text: |
|
||||
first try with divide:
|
||||
command: |
|
||||
npx tsx src/index.ts 'can you divide 4 by 5'
|
||||
results:
|
||||
- text: |
|
||||
you should see a slightly different email with the custom template
|
||||
|
||||
|
||||
|
||||
feel free to run with the flow and then you can try updating the template to your liking
|
||||
|
||||
(if you're using cursor, something as simple as highlighting the template and asking to "make it better"
|
||||
should do the trick)
|
||||
|
||||
try triggering "request_more_information" as well!
|
||||
- text: |
|
||||
thats it - in the next chapter, we'll build a fully email-driven
|
||||
workflow agent that uses webhooks for human approval
|
||||
|
||||
- name: humanlayer-webhook
|
||||
title: "Chapter XX - HumanLayer Webhook Integration"
|
||||
text: |
|
||||
the previous sections used the humanlayer SDK in "synchronous mode" - that
|
||||
means every time we wait for human approval, we sit in a loop
|
||||
polling until the human response if received.
|
||||
|
||||
That's obviously not ideal, especially for production workloads,
|
||||
so in this section we'll implement [factor 6 - launch / pause / resume with simple APIs](https://github.com/humanlayer/12-factor-agents/blob/main/content/factor-6-launch-pause-resume.md)
|
||||
by updating the server to end processing after contacting a human, and use webhooks to receive the results.
|
||||
|
||||
steps:
|
||||
- text: |
|
||||
add code to initialize humanlayer in the server
|
||||
file: {src: ./walkthrough/12-1-server-init.ts, dest: src/server.ts}
|
||||
- text: |
|
||||
next, lets update the /thread endpoint to
|
||||
|
||||
1. handle requests asynchronously, returning immediately
|
||||
2. create a human contact on request_more_information and done_for_now calls
|
||||
|
||||
# file: {src: }
|
||||
- text: |
|
||||
Update the server to be able to handle request_clarification responses
|
||||
|
||||
- remove the old /response endpoint and types
|
||||
- update the /thread endpoint to run processing asynchronously, return immediately
|
||||
- send a state.threadId when requesting human responses
|
||||
- add a handleHumanResponse function to process the human response
|
||||
- add a /webhook endpoint to handle the webhook response
|
||||
|
||||
file: {src: ./walkthrough/12a-server.ts, dest: src/server.ts}
|
||||
- text: "Start the server in another terminal"
|
||||
command: |
|
||||
npx tsx src/server.ts
|
||||
- text: |
|
||||
now that the server is running, send a payload to the '/thread' endpoint
|
||||
- text: __ do the response step
|
||||
- text: __ now handle approvals for divide
|
||||
- text: __ now also handle done_for_now
|
||||
@@ -15,6 +15,7 @@ function DetermineNextStep(
|
||||
thread: string
|
||||
) -> DoneForNow {
|
||||
client Qwen3
|
||||
// client "openai/gpt-4o"
|
||||
|
||||
// use /nothink for now because the thinking tokens (or streaming thereof) screw with baml (i think (no pun intended))
|
||||
prompt #"
|
||||
|
||||
@@ -3,14 +3,27 @@ class DoneForNow {
|
||||
message string
|
||||
}
|
||||
|
||||
client<llm> Qwen3 {
|
||||
provider "openai-generic"
|
||||
options {
|
||||
base_url env.BASETEN_BASE_URL
|
||||
api_key env.BASETEN_API_KEY
|
||||
}
|
||||
}
|
||||
|
||||
function DetermineNextStep(
|
||||
thread: string
|
||||
) -> CalculatorTools | DoneForNow {
|
||||
client "openai/gpt-4o"
|
||||
client Qwen3
|
||||
|
||||
// client "openai/gpt-4o"
|
||||
|
||||
// use /nothink for now because the thinking tokens (or streaming thereof) screw with baml (i think (no pun intended))
|
||||
prompt #"
|
||||
{{ _.role("system") }}
|
||||
|
||||
/nothink
|
||||
|
||||
You are a helpful assistant that can help with tasks.
|
||||
|
||||
{{ _.role("user") }}
|
||||
|
||||
62
workshops/2025-05-17/walkthrough/04-agent.baml
Normal file
62
workshops/2025-05-17/walkthrough/04-agent.baml
Normal file
@@ -0,0 +1,62 @@
|
||||
class DoneForNow {
|
||||
intent "done_for_now"
|
||||
message string
|
||||
}
|
||||
|
||||
client<llm> Qwen3 {
|
||||
provider "openai-generic"
|
||||
options {
|
||||
base_url env.BASETEN_BASE_URL
|
||||
api_key env.BASETEN_API_KEY
|
||||
}
|
||||
}
|
||||
|
||||
function DetermineNextStep(
|
||||
thread: string
|
||||
) -> CalculatorTools | DoneForNow {
|
||||
client Qwen3
|
||||
// client "openai/gpt-4o"
|
||||
|
||||
prompt #"
|
||||
{{ _.role("system") }}
|
||||
|
||||
/nothink
|
||||
|
||||
You are a helpful assistant that can help with tasks.
|
||||
|
||||
{{ _.role("user") }}
|
||||
|
||||
You are working on the following thread:
|
||||
|
||||
{{ thread }}
|
||||
|
||||
What should the next step be?
|
||||
|
||||
{{ ctx.output_format }}
|
||||
"#
|
||||
}
|
||||
|
||||
test HelloWorld {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
{
|
||||
"type": "user_input",
|
||||
"data": "hello!"
|
||||
}
|
||||
"#
|
||||
}
|
||||
}
|
||||
|
||||
test MathOperation {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
{
|
||||
"type": "user_input",
|
||||
"data": "can you multiply 3 and 4?"
|
||||
}
|
||||
"#
|
||||
}
|
||||
}
|
||||
|
||||
64
workshops/2025-05-17/walkthrough/04b-agent.baml
Normal file
64
workshops/2025-05-17/walkthrough/04b-agent.baml
Normal file
@@ -0,0 +1,64 @@
|
||||
class DoneForNow {
|
||||
intent "done_for_now"
|
||||
message string
|
||||
}
|
||||
|
||||
client<llm> Qwen3 {
|
||||
provider "openai-generic"
|
||||
options {
|
||||
base_url env.BASETEN_BASE_URL
|
||||
api_key env.BASETEN_API_KEY
|
||||
}
|
||||
}
|
||||
|
||||
function DetermineNextStep(
|
||||
thread: string
|
||||
) -> CalculatorTools | DoneForNow {
|
||||
client Qwen3
|
||||
// client "openai/gpt-4o"
|
||||
|
||||
prompt #"
|
||||
{{ _.role("system") }}
|
||||
|
||||
/nothink
|
||||
|
||||
You are a helpful assistant that can help with tasks.
|
||||
|
||||
{{ _.role("user") }}
|
||||
|
||||
You are working on the following thread:
|
||||
|
||||
{{ thread }}
|
||||
|
||||
What should the next step be?
|
||||
|
||||
{{ ctx.output_format }}
|
||||
"#
|
||||
}
|
||||
|
||||
test HelloWorld {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
{
|
||||
"type": "user_input",
|
||||
"data": "hello!"
|
||||
}
|
||||
"#
|
||||
}
|
||||
@@assert(hello, {{this.intent == "done_for_now"}})
|
||||
}
|
||||
|
||||
test MathOperation {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
{
|
||||
"type": "user_input",
|
||||
"data": "can you multiply 3 and 4?"
|
||||
}
|
||||
"#
|
||||
}
|
||||
@@assert(math_operation, {{this.intent == "multiply"}})
|
||||
}
|
||||
|
||||
116
workshops/2025-05-17/walkthrough/04c-agent.baml
Normal file
116
workshops/2025-05-17/walkthrough/04c-agent.baml
Normal file
@@ -0,0 +1,116 @@
|
||||
class DoneForNow {
|
||||
intent "done_for_now"
|
||||
message string
|
||||
}
|
||||
|
||||
client<llm> Qwen3 {
|
||||
provider "openai-generic"
|
||||
options {
|
||||
base_url env.BASETEN_BASE_URL
|
||||
api_key env.BASETEN_API_KEY
|
||||
}
|
||||
}
|
||||
function DetermineNextStep(
|
||||
thread: string
|
||||
) -> CalculatorTools | DoneForNow {
|
||||
client Qwen3
|
||||
|
||||
// client "openai/gpt-4o"
|
||||
|
||||
prompt #"
|
||||
{{ _.role("system") }}
|
||||
|
||||
/nothink
|
||||
|
||||
You are a helpful assistant that can help with tasks.
|
||||
|
||||
{{ _.role("user") }}
|
||||
|
||||
You are working on the following thread:
|
||||
|
||||
{{ thread }}
|
||||
|
||||
What should the next step be?
|
||||
|
||||
{{ ctx.output_format }}
|
||||
"#
|
||||
}
|
||||
|
||||
test HelloWorld {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
{
|
||||
"type": "user_input",
|
||||
"data": "hello!"
|
||||
}
|
||||
"#
|
||||
}
|
||||
@@assert(intent, {{this.intent == "done_for_now"}})
|
||||
}
|
||||
|
||||
test MathOperation {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
{
|
||||
"type": "user_input",
|
||||
"data": "can you multiply 3 and 4?"
|
||||
}
|
||||
"#
|
||||
}
|
||||
@@assert(intent, {{this.intent == "multiply"}})
|
||||
}
|
||||
|
||||
test LongMath {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
[
|
||||
{
|
||||
"type": "user_input",
|
||||
"data": "can you multiply 3 and 4, then divide the result by 2 and then add 12 to that result?"
|
||||
},
|
||||
{
|
||||
"type": "tool_call",
|
||||
"data": {
|
||||
"intent": "multiply",
|
||||
"a": 3,
|
||||
"b": 4
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "tool_response",
|
||||
"data": 12
|
||||
},
|
||||
{
|
||||
"type": "tool_call",
|
||||
"data": {
|
||||
"intent": "divide",
|
||||
"a": 12,
|
||||
"b": 2
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "tool_response",
|
||||
"data": 6
|
||||
},
|
||||
{
|
||||
"type": "tool_call",
|
||||
"data": {
|
||||
"intent": "add",
|
||||
"a": 6,
|
||||
"b": 12
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "tool_response",
|
||||
"data": 18
|
||||
}
|
||||
]
|
||||
"#
|
||||
}
|
||||
@@assert(intent, {{this.intent == "done_for_now"}})
|
||||
@@assert(answer, {{"18" in this.message}})
|
||||
}
|
||||
|
||||
129
workshops/2025-05-17/walkthrough/05-agent.baml
Normal file
129
workshops/2025-05-17/walkthrough/05-agent.baml
Normal file
@@ -0,0 +1,129 @@
|
||||
// human tools are async requests to a human
|
||||
type HumanTools = ClarificationRequest | DoneForNow
|
||||
|
||||
class ClarificationRequest {
|
||||
intent "request_more_information" @description("you can request more information from me")
|
||||
message string
|
||||
}
|
||||
|
||||
class DoneForNow {
|
||||
intent "done_for_now"
|
||||
|
||||
message string @description(#"
|
||||
message to send to the user about the work that was done.
|
||||
"#)
|
||||
}
|
||||
|
||||
client<llm> Qwen3 {
|
||||
provider "openai-generic"
|
||||
options {
|
||||
base_url env.BASETEN_BASE_URL
|
||||
api_key env.BASETEN_API_KEY
|
||||
}
|
||||
}
|
||||
|
||||
function DetermineNextStep(
|
||||
thread: string
|
||||
) -> HumanTools | CalculatorTools {
|
||||
client Qwen3
|
||||
|
||||
// client "openai/gpt-4o"
|
||||
|
||||
prompt #"
|
||||
{{ _.role("system") }}
|
||||
|
||||
/nothink
|
||||
|
||||
You are a helpful assistant that can help with tasks.
|
||||
|
||||
{{ _.role("user") }}
|
||||
|
||||
You are working on the following thread:
|
||||
|
||||
{{ thread }}
|
||||
|
||||
What should the next step be?
|
||||
|
||||
{{ ctx.output_format }}
|
||||
"#
|
||||
}
|
||||
|
||||
test HelloWorld {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
{
|
||||
"type": "user_input",
|
||||
"data": "hello!"
|
||||
}
|
||||
"#
|
||||
}
|
||||
@@assert(intent, {{this.intent == "done_for_now"}})
|
||||
}
|
||||
|
||||
test MathOperation {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
{
|
||||
"type": "user_input",
|
||||
"data": "can you multiply 3 and 4?"
|
||||
}
|
||||
"#
|
||||
}
|
||||
@@assert(intent, {{this.intent == "multiply"}})
|
||||
}
|
||||
|
||||
test LongMath {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
[
|
||||
{
|
||||
"type": "user_input",
|
||||
"data": "can you multiply 3 and 4, then divide the result by 2 and then add 12 to that result?"
|
||||
},
|
||||
{
|
||||
"type": "tool_call",
|
||||
"data": {
|
||||
"intent": "multiply",
|
||||
"a": 3,
|
||||
"b": 4
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "tool_response",
|
||||
"data": 12
|
||||
},
|
||||
{
|
||||
"type": "tool_call",
|
||||
"data": {
|
||||
"intent": "divide",
|
||||
"a": 12,
|
||||
"b": 2
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "tool_response",
|
||||
"data": 6
|
||||
},
|
||||
{
|
||||
"type": "tool_call",
|
||||
"data": {
|
||||
"intent": "add",
|
||||
"a": 6,
|
||||
"b": 12
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "tool_response",
|
||||
"data": 18
|
||||
}
|
||||
]
|
||||
"#
|
||||
}
|
||||
@@assert(intent, {{this.intent == "done_for_now"}})
|
||||
@@assert(answer, {{"18" in this.message}})
|
||||
}
|
||||
|
||||
|
||||
87
workshops/2025-05-17/walkthrough/05-agent.ts
Normal file
87
workshops/2025-05-17/walkthrough/05-agent.ts
Normal file
@@ -0,0 +1,87 @@
|
||||
import { AddTool, SubtractTool, DivideTool, MultiplyTool, b } from "../baml_client";
|
||||
|
||||
export interface Event {
|
||||
type: string
|
||||
data: any;
|
||||
}
|
||||
|
||||
export class Thread {
|
||||
events: Event[] = [];
|
||||
|
||||
constructor(events: Event[]) {
|
||||
this.events = events;
|
||||
}
|
||||
|
||||
serializeForLLM() {
|
||||
// can change this to whatever custom serialization you want to do, XML, etc
|
||||
// e.g. https://github.com/got-agents/agents/blob/59ebbfa236fc376618f16ee08eb0f3bf7b698892/linear-assistant-ts/src/agent.ts#L66-L105
|
||||
return JSON.stringify(this.events);
|
||||
}
|
||||
}
|
||||
|
||||
export type CalculatorTool = AddTool | SubtractTool | MultiplyTool | DivideTool;
|
||||
|
||||
export async function handleNextStep(nextStep: CalculatorTool, thread: Thread): Promise<Thread> {
|
||||
let result: number;
|
||||
switch (nextStep.intent) {
|
||||
case "add":
|
||||
result = nextStep.a + nextStep.b;
|
||||
console.log("tool_response", result);
|
||||
thread.events.push({
|
||||
"type": "tool_response",
|
||||
"data": result
|
||||
});
|
||||
return thread;
|
||||
case "subtract":
|
||||
result = nextStep.a - nextStep.b;
|
||||
console.log("tool_response", result);
|
||||
thread.events.push({
|
||||
"type": "tool_response",
|
||||
"data": result
|
||||
});
|
||||
return thread;
|
||||
case "multiply":
|
||||
result = nextStep.a * nextStep.b;
|
||||
console.log("tool_response", result);
|
||||
thread.events.push({
|
||||
"type": "tool_response",
|
||||
"data": result
|
||||
});
|
||||
return thread;
|
||||
case "divide":
|
||||
result = nextStep.a / nextStep.b;
|
||||
console.log("tool_response", result);
|
||||
thread.events.push({
|
||||
"type": "tool_response",
|
||||
"data": result
|
||||
});
|
||||
return thread;
|
||||
}
|
||||
}
|
||||
|
||||
export async function agentLoop(thread: Thread): Promise<Thread> {
|
||||
|
||||
while (true) {
|
||||
const nextStep = await b.DetermineNextStep(thread.serializeForLLM());
|
||||
console.log("nextStep", nextStep);
|
||||
|
||||
thread.events.push({
|
||||
"type": "tool_call",
|
||||
"data": nextStep
|
||||
});
|
||||
|
||||
switch (nextStep.intent) {
|
||||
case "done_for_now":
|
||||
case "request_more_information":
|
||||
// response to human, return the thread
|
||||
return thread;
|
||||
case "add":
|
||||
case "subtract":
|
||||
case "multiply":
|
||||
case "divide":
|
||||
thread = await handleNextStep(nextStep, thread);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
50
workshops/2025-05-17/walkthrough/05-cli.ts
Normal file
50
workshops/2025-05-17/walkthrough/05-cli.ts
Normal file
@@ -0,0 +1,50 @@
|
||||
// cli.ts lets you invoke the agent loop from the command line
|
||||
|
||||
import { agentLoop, Thread, Event } from "../src/agent";
|
||||
|
||||
|
||||
|
||||
export async function cli() {
|
||||
// Get command line arguments, skipping the first two (node and script name)
|
||||
const args = process.argv.slice(2);
|
||||
|
||||
if (args.length === 0) {
|
||||
console.error("Error: Please provide a message as a command line argument");
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
// Join all arguments into a single message
|
||||
const message = args.join(" ");
|
||||
|
||||
// Create a new thread with the user's message as the initial event
|
||||
const thread = new Thread([{ type: "user_input", data: message }]);
|
||||
|
||||
// Run the agent loop with the thread
|
||||
const result = await agentLoop(thread);
|
||||
let lastEvent = result.events.slice(-1)[0];
|
||||
|
||||
while (lastEvent.data.intent === "request_more_information") {
|
||||
const message = await askHuman(lastEvent.data.message);
|
||||
thread.events.push({ type: "human_response", data: message });
|
||||
const result = await agentLoop(thread);
|
||||
lastEvent = result.events.slice(-1)[0];
|
||||
}
|
||||
|
||||
// print the final result
|
||||
// optional - you could loop here too
|
||||
console.log(lastEvent.data.message);
|
||||
process.exit(0);
|
||||
}
|
||||
|
||||
async function askHuman(message: string) {
|
||||
const readline = require('readline').createInterface({
|
||||
input: process.stdin,
|
||||
output: process.stdout
|
||||
});
|
||||
|
||||
return new Promise((resolve) => {
|
||||
readline.question(`${message}\n> `, (answer: string) => {
|
||||
resolve(answer);
|
||||
});
|
||||
});
|
||||
}
|
||||
157
workshops/2025-05-17/walkthrough/05b-agent.baml
Normal file
157
workshops/2025-05-17/walkthrough/05b-agent.baml
Normal file
@@ -0,0 +1,157 @@
|
||||
// human tools are async requests to a human
|
||||
type HumanTools = ClarificationRequest | DoneForNow
|
||||
|
||||
class ClarificationRequest {
|
||||
intent "request_more_information" @description("you can request more information from me")
|
||||
message string
|
||||
}
|
||||
|
||||
class DoneForNow {
|
||||
intent "done_for_now"
|
||||
|
||||
message string @description(#"
|
||||
message to send to the user about the work that was done.
|
||||
"#)
|
||||
}
|
||||
|
||||
client<llm> Qwen3 {
|
||||
provider "openai-generic"
|
||||
options {
|
||||
base_url env.BASETEN_BASE_URL
|
||||
api_key env.BASETEN_API_KEY
|
||||
}
|
||||
}
|
||||
|
||||
function DetermineNextStep(
|
||||
thread: string
|
||||
) -> HumanTools | CalculatorTools {
|
||||
client Qwen3
|
||||
// client "openai/gpt-4o"
|
||||
|
||||
prompt #"
|
||||
{{ _.role("system") }}
|
||||
|
||||
/nothink
|
||||
|
||||
You are a helpful assistant that can help with tasks.
|
||||
|
||||
{{ _.role("user") }}
|
||||
|
||||
You are working on the following thread:
|
||||
|
||||
{{ thread }}
|
||||
|
||||
What should the next step be?
|
||||
|
||||
{{ ctx.output_format }}
|
||||
"#
|
||||
}
|
||||
|
||||
test HelloWorld {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
{
|
||||
"type": "user_input",
|
||||
"data": "hello!"
|
||||
}
|
||||
"#
|
||||
}
|
||||
@@assert(intent, {{this.intent == "done_for_now"}})
|
||||
}
|
||||
|
||||
test MathOperation {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
{
|
||||
"type": "user_input",
|
||||
"data": "can you multiply 3 and 4?"
|
||||
}
|
||||
"#
|
||||
}
|
||||
@@assert(intent, {{this.intent == "multiply"}})
|
||||
}
|
||||
|
||||
test LongMath {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
[
|
||||
{
|
||||
"type": "user_input",
|
||||
"data": "can you multiply 3 and 4, then divide the result by 2 and then add 12 to that result?"
|
||||
},
|
||||
{
|
||||
"type": "tool_call",
|
||||
"data": {
|
||||
"intent": "multiply",
|
||||
"a": 3,
|
||||
"b": 4
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "tool_response",
|
||||
"data": 12
|
||||
},
|
||||
{
|
||||
"type": "tool_call",
|
||||
"data": {
|
||||
"intent": "divide",
|
||||
"a": 12,
|
||||
"b": 2
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "tool_response",
|
||||
"data": 6
|
||||
},
|
||||
{
|
||||
"type": "tool_call",
|
||||
"data": {
|
||||
"intent": "add",
|
||||
"a": 6,
|
||||
"b": 12
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "tool_response",
|
||||
"data": 18
|
||||
}
|
||||
]
|
||||
"#
|
||||
}
|
||||
@@assert(intent, {{this.intent == "done_for_now"}})
|
||||
@@assert(answer, {{"18" in this.message}})
|
||||
}
|
||||
|
||||
|
||||
|
||||
test MathOperationWithClarification {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
[{"type":"user_input","data":"can you multiply 3 and feee9ff10"}]
|
||||
"#
|
||||
}
|
||||
@@assert(intent, {{this.intent == "request_more_information"}})
|
||||
}
|
||||
|
||||
test MathOperationPostClarification {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
[
|
||||
{"type":"user_input","data":"can you multiply 3 and FD*(#F&& ?"},
|
||||
{"type":"tool_call","data":{"intent":"request_more_information","message":"It seems like there was a typo or mistake in your request. Could you please clarify or provide the correct numbers you would like to multiply?"}},
|
||||
{"type":"human_response","data":"lets try 12 instead"},
|
||||
]
|
||||
"#
|
||||
}
|
||||
@@assert(intent, {{this.intent == "multiply"}})
|
||||
@@assert(a, {{this.b == 12}})
|
||||
@@assert(b, {{this.a == 3}})
|
||||
}
|
||||
|
||||
|
||||
|
||||
158
workshops/2025-05-17/walkthrough/05c-agent.baml
Normal file
158
workshops/2025-05-17/walkthrough/05c-agent.baml
Normal file
@@ -0,0 +1,158 @@
|
||||
// human tools are async requests to a human
|
||||
type HumanTools = ClarificationRequest | DoneForNow
|
||||
|
||||
class ClarificationRequest {
|
||||
intent "request_more_information" @description("you can request more information from me")
|
||||
message string
|
||||
}
|
||||
|
||||
class DoneForNow {
|
||||
intent "done_for_now"
|
||||
|
||||
message string @description(#"
|
||||
message to send to the user about the work that was done.
|
||||
"#)
|
||||
}
|
||||
|
||||
client<llm> Qwen3 {
|
||||
provider "openai-generic"
|
||||
options {
|
||||
base_url env.BASETEN_BASE_URL
|
||||
api_key env.BASETEN_API_KEY
|
||||
}
|
||||
}
|
||||
|
||||
function DetermineNextStep(
|
||||
thread: string
|
||||
) -> HumanTools | CalculatorTools {
|
||||
client Qwen3
|
||||
|
||||
// client "openai/gpt-4o"
|
||||
|
||||
prompt #"
|
||||
{{ _.role("system") }}
|
||||
|
||||
/nothink
|
||||
|
||||
You are a helpful assistant that can help with tasks.
|
||||
|
||||
{{ _.role("user") }}
|
||||
|
||||
You are working on the following thread:
|
||||
|
||||
{{ thread }}
|
||||
|
||||
What should the next step be?
|
||||
|
||||
{{ ctx.output_format }}
|
||||
"#
|
||||
}
|
||||
|
||||
test HelloWorld {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
{
|
||||
"type": "user_input",
|
||||
"data": "hello!"
|
||||
}
|
||||
"#
|
||||
}
|
||||
@@assert(intent, {{this.intent == "request_more_information"}})
|
||||
}
|
||||
|
||||
test MathOperation {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
{
|
||||
"type": "user_input",
|
||||
"data": "can you multiply 3 and 4?"
|
||||
}
|
||||
"#
|
||||
}
|
||||
@@assert(intent, {{this.intent == "multiply"}})
|
||||
}
|
||||
|
||||
test LongMath {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
[
|
||||
{
|
||||
"type": "user_input",
|
||||
"data": "can you multiply 3 and 4, then divide the result by 2 and then add 12 to that result?"
|
||||
},
|
||||
{
|
||||
"type": "tool_call",
|
||||
"data": {
|
||||
"intent": "multiply",
|
||||
"a": 3,
|
||||
"b": 4
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "tool_response",
|
||||
"data": 12
|
||||
},
|
||||
{
|
||||
"type": "tool_call",
|
||||
"data": {
|
||||
"intent": "divide",
|
||||
"a": 12,
|
||||
"b": 2
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "tool_response",
|
||||
"data": 6
|
||||
},
|
||||
{
|
||||
"type": "tool_call",
|
||||
"data": {
|
||||
"intent": "add",
|
||||
"a": 6,
|
||||
"b": 12
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "tool_response",
|
||||
"data": 18
|
||||
}
|
||||
]
|
||||
"#
|
||||
}
|
||||
@@assert(intent, {{this.intent == "done_for_now"}})
|
||||
@@assert(answer, {{"18" in this.message}})
|
||||
}
|
||||
|
||||
|
||||
|
||||
test MathOperationWithClarification {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
[{"type":"user_input","data":"can you multiply 3 and feee9ff10"}]
|
||||
"#
|
||||
}
|
||||
@@assert(intent, {{this.intent == "request_more_information"}})
|
||||
}
|
||||
|
||||
test MathOperationPostClarification {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
[
|
||||
{"type":"user_input","data":"can you multiply 3 and FD*(#F&& ?"},
|
||||
{"type":"tool_call","data":{"intent":"request_more_information","message":"It seems like there was a typo or mistake in your request. Could you please clarify or provide the correct numbers you would like to multiply?"}},
|
||||
{"type":"human_response","data":"lets try 12 instead"},
|
||||
]
|
||||
"#
|
||||
}
|
||||
@@assert(intent, {{this.intent == "multiply"}})
|
||||
@@assert(a, {{this.b == 12}})
|
||||
@@assert(b, {{this.a == 3}})
|
||||
}
|
||||
|
||||
|
||||
|
||||
164
workshops/2025-05-17/walkthrough/06-agent.baml
Normal file
164
workshops/2025-05-17/walkthrough/06-agent.baml
Normal file
@@ -0,0 +1,164 @@
|
||||
// human tools are async requests to a human
|
||||
type HumanTools = ClarificationRequest | DoneForNow
|
||||
|
||||
class ClarificationRequest {
|
||||
intent "request_more_information" @description("you can request more information from me")
|
||||
message string
|
||||
}
|
||||
|
||||
class DoneForNow {
|
||||
intent "done_for_now"
|
||||
|
||||
message string @description(#"
|
||||
message to send to the user about the work that was done.
|
||||
"#)
|
||||
}
|
||||
|
||||
client<llm> Qwen3 {
|
||||
provider "openai-generic"
|
||||
options {
|
||||
base_url env.BASETEN_BASE_URL
|
||||
api_key env.BASETEN_API_KEY
|
||||
}
|
||||
}
|
||||
|
||||
function DetermineNextStep(
|
||||
thread: string
|
||||
) -> HumanTools | CalculatorTools {
|
||||
client Qwen3
|
||||
|
||||
// client "openai/gpt-4o"
|
||||
|
||||
prompt #"
|
||||
{{ _.role("system") }}
|
||||
|
||||
/nothink
|
||||
|
||||
You are a helpful assistant that can help with tasks.
|
||||
|
||||
{{ _.role("user") }}
|
||||
|
||||
You are working on the following thread:
|
||||
|
||||
{{ thread }}
|
||||
|
||||
What should the next step be?
|
||||
|
||||
{{ ctx.output_format }}
|
||||
|
||||
First, always plan out what to do next, for example:
|
||||
|
||||
- ...
|
||||
- ...
|
||||
- ...
|
||||
|
||||
{...} // schema
|
||||
"#
|
||||
}
|
||||
|
||||
test HelloWorld {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
{
|
||||
"type": "user_input",
|
||||
"data": "hello!"
|
||||
}
|
||||
"#
|
||||
}
|
||||
@@assert(intent, {{this.intent == "request_more_information"}})
|
||||
}
|
||||
|
||||
test MathOperation {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
{
|
||||
"type": "user_input",
|
||||
"data": "can you multiply 3 and 4?"
|
||||
}
|
||||
"#
|
||||
}
|
||||
@@assert(intent, {{this.intent == "multiply"}})
|
||||
}
|
||||
|
||||
test LongMath {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
[
|
||||
{
|
||||
"type": "user_input",
|
||||
"data": "can you multiply 3 and 4, then divide the result by 2 and then add 12 to that result?"
|
||||
},
|
||||
{
|
||||
"type": "tool_call",
|
||||
"data": {
|
||||
"intent": "multiply",
|
||||
"a": 3,
|
||||
"b": 4
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "tool_response",
|
||||
"data": 12
|
||||
},
|
||||
{
|
||||
"type": "tool_call",
|
||||
"data": {
|
||||
"intent": "divide",
|
||||
"a": 12,
|
||||
"b": 2
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "tool_response",
|
||||
"data": 6
|
||||
},
|
||||
{
|
||||
"type": "tool_call",
|
||||
"data": {
|
||||
"intent": "add",
|
||||
"a": 6,
|
||||
"b": 12
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "tool_response",
|
||||
"data": 18
|
||||
}
|
||||
]
|
||||
"#
|
||||
}
|
||||
@@assert(intent, {{this.intent == "done_for_now"}})
|
||||
@@assert(answer, {{"18" in this.message}})
|
||||
}
|
||||
|
||||
|
||||
|
||||
test MathOperationWithClarification {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
[{"type":"user_input","data":"can you multiply 3 and feee9ff10"}]
|
||||
"#
|
||||
}
|
||||
@@assert(intent, {{this.intent == "request_more_information"}})
|
||||
}
|
||||
|
||||
test MathOperationPostClarification {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
[
|
||||
{"type":"user_input","data":"can you multiply 3 and FD*(#F&& ?"},
|
||||
{"type":"tool_call","data":{"intent":"request_more_information","message":"It seems like there was a typo or mistake in your request. Could you please clarify or provide the correct numbers you would like to multiply?"}},
|
||||
{"type":"human_response","data":"lets try 12 instead"},
|
||||
]
|
||||
"#
|
||||
}
|
||||
@@assert(intent, {{this.intent == "multiply"}})
|
||||
@@assert(a, {{this.b == 12}})
|
||||
@@assert(b, {{this.a == 3}})
|
||||
}
|
||||
|
||||
87
workshops/2025-05-17/walkthrough/07-agent.ts
Normal file
87
workshops/2025-05-17/walkthrough/07-agent.ts
Normal file
@@ -0,0 +1,87 @@
|
||||
import { AddTool, SubtractTool, DivideTool, MultiplyTool, b } from "../baml_client";
|
||||
|
||||
export interface Event {
|
||||
type: string
|
||||
data: any;
|
||||
}
|
||||
|
||||
export class Thread {
|
||||
events: Event[] = [];
|
||||
|
||||
constructor(events: Event[]) {
|
||||
this.events = events;
|
||||
}
|
||||
|
||||
serializeForLLM() {
|
||||
// can change this to whatever custom serialization you want to do, XML, etc
|
||||
// e.g. https://github.com/got-agents/agents/blob/59ebbfa236fc376618f16ee08eb0f3bf7b698892/linear-assistant-ts/src/agent.ts#L66-L105
|
||||
return JSON.stringify(this.events, null, 2);
|
||||
}
|
||||
}
|
||||
|
||||
export type CalculatorTool = AddTool | SubtractTool | MultiplyTool | DivideTool;
|
||||
|
||||
export async function handleNextStep(nextStep: CalculatorTool, thread: Thread): Promise<Thread> {
|
||||
let result: number;
|
||||
switch (nextStep.intent) {
|
||||
case "add":
|
||||
result = nextStep.a + nextStep.b;
|
||||
console.log("tool_response", result);
|
||||
thread.events.push({
|
||||
"type": "tool_response",
|
||||
"data": result
|
||||
});
|
||||
return thread;
|
||||
case "subtract":
|
||||
result = nextStep.a - nextStep.b;
|
||||
console.log("tool_response", result);
|
||||
thread.events.push({
|
||||
"type": "tool_response",
|
||||
"data": result
|
||||
});
|
||||
return thread;
|
||||
case "multiply":
|
||||
result = nextStep.a * nextStep.b;
|
||||
console.log("tool_response", result);
|
||||
thread.events.push({
|
||||
"type": "tool_response",
|
||||
"data": result
|
||||
});
|
||||
return thread;
|
||||
case "divide":
|
||||
result = nextStep.a / nextStep.b;
|
||||
console.log("tool_response", result);
|
||||
thread.events.push({
|
||||
"type": "tool_response",
|
||||
"data": result
|
||||
});
|
||||
return thread;
|
||||
}
|
||||
}
|
||||
|
||||
export async function agentLoop(thread: Thread): Promise<Thread> {
|
||||
|
||||
while (true) {
|
||||
const nextStep = await b.DetermineNextStep(thread.serializeForLLM());
|
||||
console.log("nextStep", nextStep);
|
||||
|
||||
thread.events.push({
|
||||
"type": "tool_call",
|
||||
"data": nextStep
|
||||
});
|
||||
|
||||
switch (nextStep.intent) {
|
||||
case "done_for_now":
|
||||
case "request_more_information":
|
||||
// response to human, return the thread
|
||||
return thread;
|
||||
case "add":
|
||||
case "subtract":
|
||||
case "multiply":
|
||||
case "divide":
|
||||
thread = await handleNextStep(nextStep, thread);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
99
workshops/2025-05-17/walkthrough/07b-agent.ts
Normal file
99
workshops/2025-05-17/walkthrough/07b-agent.ts
Normal file
@@ -0,0 +1,99 @@
|
||||
import { AddTool, SubtractTool, DivideTool, MultiplyTool, b } from "../baml_client";
|
||||
|
||||
export interface Event {
|
||||
type: string
|
||||
data: any;
|
||||
}
|
||||
|
||||
export class Thread {
|
||||
events: Event[] = [];
|
||||
|
||||
constructor(events: Event[]) {
|
||||
this.events = events;
|
||||
}
|
||||
|
||||
serializeForLLM() {
|
||||
return this.events.map(e => this.serializeOneEvent(e)).join("\n");
|
||||
}
|
||||
|
||||
trimLeadingWhitespace(s: string) {
|
||||
return s.replace(/^[ \t]+/gm, '');
|
||||
}
|
||||
|
||||
serializeOneEvent(e: Event) {
|
||||
return this.trimLeadingWhitespace(`
|
||||
<${e.data?.intent || e.type}>
|
||||
${
|
||||
typeof e.data !== 'object' ? e.data :
|
||||
Object.keys(e.data).filter(k => k !== 'intent').map(k => `${k}: ${e.data[k]}`).join("\n")}
|
||||
</${e.data?.intent || e.type}>
|
||||
`)
|
||||
}
|
||||
}
|
||||
|
||||
export type CalculatorTool = AddTool | SubtractTool | MultiplyTool | DivideTool;
|
||||
|
||||
export async function handleNextStep(nextStep: CalculatorTool, thread: Thread): Promise<Thread> {
|
||||
let result: number;
|
||||
switch (nextStep.intent) {
|
||||
case "add":
|
||||
result = nextStep.a + nextStep.b;
|
||||
console.log("tool_response", result);
|
||||
thread.events.push({
|
||||
"type": "tool_response",
|
||||
"data": result
|
||||
});
|
||||
return thread;
|
||||
case "subtract":
|
||||
result = nextStep.a - nextStep.b;
|
||||
console.log("tool_response", result);
|
||||
thread.events.push({
|
||||
"type": "tool_response",
|
||||
"data": result
|
||||
});
|
||||
return thread;
|
||||
case "multiply":
|
||||
result = nextStep.a * nextStep.b;
|
||||
console.log("tool_response", result);
|
||||
thread.events.push({
|
||||
"type": "tool_response",
|
||||
"data": result
|
||||
});
|
||||
return thread;
|
||||
case "divide":
|
||||
result = nextStep.a / nextStep.b;
|
||||
console.log("tool_response", result);
|
||||
thread.events.push({
|
||||
"type": "tool_response",
|
||||
"data": result
|
||||
});
|
||||
return thread;
|
||||
}
|
||||
}
|
||||
|
||||
export async function agentLoop(thread: Thread): Promise<Thread> {
|
||||
|
||||
while (true) {
|
||||
const nextStep = await b.DetermineNextStep(thread.serializeForLLM());
|
||||
console.log("nextStep", nextStep);
|
||||
|
||||
thread.events.push({
|
||||
"type": "tool_call",
|
||||
"data": nextStep
|
||||
});
|
||||
|
||||
switch (nextStep.intent) {
|
||||
case "done_for_now":
|
||||
case "request_more_information":
|
||||
// response to human, return the thread
|
||||
return thread;
|
||||
case "add":
|
||||
case "subtract":
|
||||
case "multiply":
|
||||
case "divide":
|
||||
thread = await handleNextStep(nextStep, thread);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
165
workshops/2025-05-17/walkthrough/07c-agent.baml
Normal file
165
workshops/2025-05-17/walkthrough/07c-agent.baml
Normal file
@@ -0,0 +1,165 @@
|
||||
// human tools are async requests to a human
|
||||
type HumanTools = ClarificationRequest | DoneForNow
|
||||
|
||||
class ClarificationRequest {
|
||||
intent "request_more_information" @description("you can request more information from me")
|
||||
message string
|
||||
}
|
||||
|
||||
class DoneForNow {
|
||||
intent "done_for_now"
|
||||
|
||||
message string @description(#"
|
||||
message to send to the user about the work that was done.
|
||||
"#)
|
||||
}
|
||||
|
||||
client<llm> Qwen3 {
|
||||
provider "openai-generic"
|
||||
options {
|
||||
base_url env.BASETEN_BASE_URL
|
||||
api_key env.BASETEN_API_KEY
|
||||
}
|
||||
}
|
||||
|
||||
function DetermineNextStep(
|
||||
thread: string
|
||||
) -> HumanTools | CalculatorTools {
|
||||
client Qwen3
|
||||
|
||||
// client "openai/gpt-4o"
|
||||
|
||||
prompt #"
|
||||
{{ _.role("system") }}
|
||||
|
||||
/nothink
|
||||
|
||||
You are a helpful assistant that can help with tasks.
|
||||
|
||||
{{ _.role("user") }}
|
||||
|
||||
You are working on the following thread:
|
||||
|
||||
{{ thread }}
|
||||
|
||||
What should the next step be?
|
||||
|
||||
{{ ctx.output_format }}
|
||||
|
||||
Always think about what to do next first, like:
|
||||
|
||||
- ...
|
||||
- ...
|
||||
- ...
|
||||
|
||||
{...} // schema
|
||||
"#
|
||||
}
|
||||
|
||||
test HelloWorld {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
<user_input>
|
||||
hello!
|
||||
</user_input>
|
||||
"#
|
||||
}
|
||||
@@assert(intent, {{this.intent == "request_more_information"}})
|
||||
}
|
||||
|
||||
test MathOperation {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
<user_input>
|
||||
can you multiply 3 and 4?
|
||||
</user_input>
|
||||
"#
|
||||
}
|
||||
@@assert(intent, {{this.intent == "multiply"}})
|
||||
}
|
||||
|
||||
test LongMath {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
<user_input>
|
||||
can you multiply 3 and 4, then divide the result by 2 and then add 12 to that result?
|
||||
</user_input>
|
||||
|
||||
|
||||
<multiply>
|
||||
a: 3
|
||||
b: 4
|
||||
</multiply>
|
||||
|
||||
|
||||
<tool_response>
|
||||
12
|
||||
</tool_response>
|
||||
|
||||
|
||||
<divide>
|
||||
a: 12
|
||||
b: 2
|
||||
</divide>
|
||||
|
||||
|
||||
<tool_response>
|
||||
6
|
||||
</tool_response>
|
||||
|
||||
|
||||
<add>
|
||||
a: 6
|
||||
b: 12
|
||||
</add>
|
||||
|
||||
|
||||
<tool_response>
|
||||
18
|
||||
</tool_response>
|
||||
|
||||
"#
|
||||
}
|
||||
@@assert(intent, {{this.intent == "done_for_now"}})
|
||||
@@assert(answer, {{"18" in this.message}})
|
||||
}
|
||||
|
||||
|
||||
|
||||
test MathOperationWithClarification {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
<user_input>
|
||||
can you multiply 3 and fe1iiaff10
|
||||
</user_input>
|
||||
"#
|
||||
}
|
||||
@@assert(intent, {{this.intent == "request_more_information"}})
|
||||
}
|
||||
|
||||
test MathOperationPostClarification {
|
||||
functions [DetermineNextStep]
|
||||
args {
|
||||
thread #"
|
||||
<user_input>
|
||||
can you multiply 3 and FD*(#F&& ?
|
||||
</user_input>
|
||||
|
||||
<request_more_information>
|
||||
message: It seems like there was a typo or mistake in your request. Could you please clarify or provide the correct numbers you would like to multiply?
|
||||
</request_more_information>
|
||||
|
||||
<human_response>
|
||||
lets try 12 instead
|
||||
</human_response>
|
||||
"#
|
||||
}
|
||||
@@assert(intent, {{this.intent == "multiply"}})
|
||||
@@assert(b, {{this.a == 3}})
|
||||
@@assert(a, {{this.b == 12}})
|
||||
}
|
||||
|
||||
29
workshops/2025-05-17/walkthrough/08-server.ts
Normal file
29
workshops/2025-05-17/walkthrough/08-server.ts
Normal file
@@ -0,0 +1,29 @@
|
||||
import express from 'express';
|
||||
import { Thread, agentLoop } from '../src/agent';
|
||||
|
||||
const app = express();
|
||||
app.use(express.json());
|
||||
app.set('json spaces', 2);
|
||||
|
||||
// POST /thread - Start new thread
|
||||
app.post('/thread', async (req, res) => {
|
||||
const thread = new Thread([{
|
||||
type: "user_input",
|
||||
data: req.body.message
|
||||
}]);
|
||||
const result = await agentLoop(thread);
|
||||
res.json(result);
|
||||
});
|
||||
|
||||
// GET /thread/:id - Get thread status
|
||||
app.get('/thread/:id', (req, res) => {
|
||||
// optional - add state
|
||||
res.status(404).json({ error: "Not implemented yet" });
|
||||
});
|
||||
|
||||
const port = process.env.PORT || 3000;
|
||||
app.listen(port, () => {
|
||||
console.log(`Server running on port ${port}`);
|
||||
});
|
||||
|
||||
export { app };
|
||||
75
workshops/2025-05-17/walkthrough/09-server.ts
Normal file
75
workshops/2025-05-17/walkthrough/09-server.ts
Normal file
@@ -0,0 +1,75 @@
|
||||
import express from 'express';
|
||||
import { Thread, agentLoop } from '../src/agent';
|
||||
import { ThreadStore } from '../src/state';
|
||||
|
||||
const app = express();
|
||||
app.use(express.json());
|
||||
app.set('json spaces', 2);
|
||||
|
||||
const store = new ThreadStore();
|
||||
|
||||
// POST /thread - Start new thread
|
||||
app.post('/thread', async (req, res) => {
|
||||
const thread = new Thread([{
|
||||
type: "user_input",
|
||||
data: req.body.message
|
||||
}]);
|
||||
|
||||
const threadId = store.create(thread);
|
||||
const newThread = await agentLoop(thread);
|
||||
|
||||
store.update(threadId, newThread);
|
||||
|
||||
const lastEvent = newThread.events[newThread.events.length - 1];
|
||||
// If we exited the loop, include the response URL so the client can
|
||||
// push a new message onto the thread
|
||||
lastEvent.data.response_url = `/thread/${threadId}/response`;
|
||||
|
||||
console.log("returning last event from endpoint", lastEvent);
|
||||
|
||||
res.json({
|
||||
thread_id: threadId,
|
||||
...newThread
|
||||
});
|
||||
});
|
||||
|
||||
// GET /thread/:id - Get thread status
|
||||
app.get('/thread/:id', (req, res) => {
|
||||
const thread = store.get(req.params.id);
|
||||
if (!thread) {
|
||||
return res.status(404).json({ error: "Thread not found" });
|
||||
}
|
||||
res.json(thread);
|
||||
});
|
||||
|
||||
// POST /thread/:id/response - Handle clarification response
|
||||
app.post('/thread/:id/response', async (req, res) => {
|
||||
let thread = store.get(req.params.id);
|
||||
if (!thread) {
|
||||
return res.status(404).json({ error: "Thread not found" });
|
||||
}
|
||||
|
||||
thread.events.push({
|
||||
type: "human_response",
|
||||
data: req.body.message
|
||||
});
|
||||
|
||||
// loop until stop event
|
||||
const newThread = await agentLoop(thread);
|
||||
|
||||
store.update(req.params.id, newThread);
|
||||
|
||||
const lastEvent = newThread.events[newThread.events.length - 1];
|
||||
lastEvent.data.response_url = `/thread/${req.params.id}/response`;
|
||||
|
||||
console.log("returning last event from endpoint", lastEvent);
|
||||
|
||||
res.json(newThread);
|
||||
});
|
||||
|
||||
const port = process.env.PORT || 3000;
|
||||
app.listen(port, () => {
|
||||
console.log(`Server running on port ${port}`);
|
||||
});
|
||||
|
||||
export { app };
|
||||
23
workshops/2025-05-17/walkthrough/09-state.ts
Normal file
23
workshops/2025-05-17/walkthrough/09-state.ts
Normal file
@@ -0,0 +1,23 @@
|
||||
import crypto from 'crypto';
|
||||
import { Thread } from '../src/agent';
|
||||
|
||||
|
||||
// you can replace this with any simple state management,
|
||||
// e.g. redis, sqlite, postgres, etc
|
||||
export class ThreadStore {
|
||||
private threads: Map<string, Thread> = new Map();
|
||||
|
||||
create(thread: Thread): string {
|
||||
const id = crypto.randomUUID();
|
||||
this.threads.set(id, thread);
|
||||
return id;
|
||||
}
|
||||
|
||||
get(id: string): Thread | undefined {
|
||||
return this.threads.get(id);
|
||||
}
|
||||
|
||||
update(id: string, thread: Thread): void {
|
||||
this.threads.set(id, thread);
|
||||
}
|
||||
}
|
||||
111
workshops/2025-05-17/walkthrough/10-agent.ts
Normal file
111
workshops/2025-05-17/walkthrough/10-agent.ts
Normal file
@@ -0,0 +1,111 @@
|
||||
import { AddTool, SubtractTool, DivideTool, MultiplyTool, b } from "../baml_client";
|
||||
|
||||
export interface Event {
|
||||
type: string
|
||||
data: any;
|
||||
}
|
||||
|
||||
export class Thread {
|
||||
events: Event[] = [];
|
||||
|
||||
constructor(events: Event[]) {
|
||||
this.events = events;
|
||||
}
|
||||
|
||||
serializeForLLM() {
|
||||
return this.events.map(e => this.serializeOneEvent(e)).join("\n");
|
||||
}
|
||||
|
||||
trimLeadingWhitespace(s: string) {
|
||||
return s.replace(/^[ \t]+/gm, '');
|
||||
}
|
||||
|
||||
serializeOneEvent(e: Event) {
|
||||
return this.trimLeadingWhitespace(`
|
||||
<${e.data?.intent || e.type}>
|
||||
${
|
||||
typeof e.data !== 'object' ? e.data :
|
||||
Object.keys(e.data).filter(k => k !== 'intent').map(k => `${k}: ${e.data[k]}`).join("\n")}
|
||||
</${e.data?.intent || e.type}>
|
||||
`)
|
||||
}
|
||||
|
||||
awaitingHumanResponse(): boolean {
|
||||
const lastEvent = this.events[this.events.length - 1];
|
||||
return ['request_more_information', 'done_for_now'].includes(lastEvent.data.intent);
|
||||
}
|
||||
|
||||
awaitingHumanApproval(): boolean {
|
||||
const lastEvent = this.events[this.events.length - 1];
|
||||
return lastEvent.data.intent === 'divide';
|
||||
}
|
||||
}
|
||||
|
||||
export type CalculatorTool = AddTool | SubtractTool | MultiplyTool | DivideTool;
|
||||
|
||||
export async function handleNextStep(nextStep: CalculatorTool, thread: Thread): Promise<Thread> {
|
||||
let result: number;
|
||||
switch (nextStep.intent) {
|
||||
case "add":
|
||||
result = nextStep.a + nextStep.b;
|
||||
console.log("tool_response", result);
|
||||
thread.events.push({
|
||||
"type": "tool_response",
|
||||
"data": result
|
||||
});
|
||||
return thread;
|
||||
case "subtract":
|
||||
result = nextStep.a - nextStep.b;
|
||||
console.log("tool_response", result);
|
||||
thread.events.push({
|
||||
"type": "tool_response",
|
||||
"data": result
|
||||
});
|
||||
return thread;
|
||||
case "multiply":
|
||||
result = nextStep.a * nextStep.b;
|
||||
console.log("tool_response", result);
|
||||
thread.events.push({
|
||||
"type": "tool_response",
|
||||
"data": result
|
||||
});
|
||||
return thread;
|
||||
case "divide":
|
||||
result = nextStep.a / nextStep.b;
|
||||
console.log("tool_response", result);
|
||||
thread.events.push({
|
||||
"type": "tool_response",
|
||||
"data": result
|
||||
});
|
||||
return thread;
|
||||
}
|
||||
}
|
||||
|
||||
export async function agentLoop(thread: Thread): Promise<Thread> {
|
||||
|
||||
while (true) {
|
||||
const nextStep = await b.DetermineNextStep(thread.serializeForLLM());
|
||||
console.log("nextStep", nextStep);
|
||||
|
||||
thread.events.push({
|
||||
"type": "tool_call",
|
||||
"data": nextStep
|
||||
});
|
||||
|
||||
switch (nextStep.intent) {
|
||||
case "done_for_now":
|
||||
case "request_more_information":
|
||||
// response to human, return the thread
|
||||
return thread;
|
||||
case "divide":
|
||||
// divide is scary, return it for human approval
|
||||
return thread;
|
||||
case "add":
|
||||
case "subtract":
|
||||
case "multiply":
|
||||
thread = await handleNextStep(nextStep, thread);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
112
workshops/2025-05-17/walkthrough/10-server.ts
Normal file
112
workshops/2025-05-17/walkthrough/10-server.ts
Normal file
@@ -0,0 +1,112 @@
|
||||
import express from 'express';
|
||||
import { Thread, agentLoop, handleNextStep } from '../src/agent';
|
||||
import { ThreadStore } from '../src/state';
|
||||
|
||||
const app = express();
|
||||
app.use(express.json());
|
||||
app.set('json spaces', 2);
|
||||
|
||||
const store = new ThreadStore();
|
||||
|
||||
// POST /thread - Start new thread
|
||||
app.post('/thread', async (req, res) => {
|
||||
const thread = new Thread([{
|
||||
type: "user_input",
|
||||
data: req.body.message
|
||||
}]);
|
||||
|
||||
const threadId = store.create(thread);
|
||||
const newThread = await agentLoop(thread);
|
||||
|
||||
store.update(threadId, newThread);
|
||||
|
||||
const lastEvent = newThread.events[newThread.events.length - 1];
|
||||
// If we exited the loop, include the response URL so the client can
|
||||
// push a new message onto the thread
|
||||
lastEvent.data.response_url = `/thread/${threadId}/response`;
|
||||
|
||||
console.log("returning last event from endpoint", lastEvent);
|
||||
|
||||
res.json({
|
||||
thread_id: threadId,
|
||||
...newThread
|
||||
});
|
||||
});
|
||||
|
||||
// GET /thread/:id - Get thread status
|
||||
app.get('/thread/:id', (req, res) => {
|
||||
const thread = store.get(req.params.id);
|
||||
if (!thread) {
|
||||
return res.status(404).json({ error: "Thread not found" });
|
||||
}
|
||||
res.json(thread);
|
||||
});
|
||||
|
||||
|
||||
type ApprovalPayload = {
|
||||
type: "approval";
|
||||
approved: boolean;
|
||||
comment?: string;
|
||||
}
|
||||
|
||||
type ResponsePayload = {
|
||||
type: "response";
|
||||
response: string;
|
||||
}
|
||||
|
||||
type Payload = ApprovalPayload | ResponsePayload;
|
||||
|
||||
// POST /thread/:id/response - Handle clarification response
|
||||
app.post('/thread/:id/response', async (req, res) => {
|
||||
let thread = store.get(req.params.id);
|
||||
if (!thread) {
|
||||
return res.status(404).json({ error: "Thread not found" });
|
||||
}
|
||||
|
||||
const body: Payload = req.body;
|
||||
|
||||
let lastEvent = thread.events[thread.events.length - 1];
|
||||
|
||||
if (thread.awaitingHumanResponse() && body.type === 'response') {
|
||||
thread.events.push({
|
||||
type: "human_response",
|
||||
data: body.response
|
||||
});
|
||||
} else if (thread.awaitingHumanApproval() && body.type === 'approval' && !body.approved) {
|
||||
// push feedback onto the thread
|
||||
thread.events.push({
|
||||
type: "tool_response",
|
||||
data: `user denied the operation with feedback: "${body.comment}"`
|
||||
});
|
||||
} else if (thread.awaitingHumanApproval() && body.type === 'approval' && body.approved) {
|
||||
// approved, run the tool, pushing results onto the thread
|
||||
await handleNextStep(lastEvent.data, thread);
|
||||
} else {
|
||||
res.status(400).json({
|
||||
error: "Invalid request: " + body.type,
|
||||
awaitingHumanResponse: thread.awaitingHumanResponse(),
|
||||
awaitingHumanApproval: thread.awaitingHumanApproval()
|
||||
});
|
||||
return;
|
||||
}
|
||||
|
||||
|
||||
// loop until stop event
|
||||
const newThread = await agentLoop(thread);
|
||||
|
||||
store.update(req.params.id, newThread);
|
||||
|
||||
lastEvent = newThread.events[newThread.events.length - 1];
|
||||
lastEvent.data.response_url = `/thread/${req.params.id}/response`;
|
||||
|
||||
console.log("returning last event from endpoint", lastEvent);
|
||||
|
||||
res.json(newThread);
|
||||
});
|
||||
|
||||
const port = process.env.PORT || 3000;
|
||||
app.listen(port, () => {
|
||||
console.log(`Server running on port ${port}`);
|
||||
});
|
||||
|
||||
export { app };
|
||||
103
workshops/2025-05-17/walkthrough/11-cli.ts
Normal file
103
workshops/2025-05-17/walkthrough/11-cli.ts
Normal file
@@ -0,0 +1,103 @@
|
||||
// cli.ts lets you invoke the agent loop from the command line
|
||||
|
||||
import { humanlayer } from "humanlayer";
|
||||
import { agentLoop, Thread, Event } from "../src/agent";
|
||||
|
||||
export async function cli() {
|
||||
// Get command line arguments, skipping the first two (node and script name)
|
||||
const args = process.argv.slice(2);
|
||||
|
||||
if (args.length === 0) {
|
||||
console.error("Error: Please provide a message as a command line argument");
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
// Join all arguments into a single message
|
||||
const message = args.join(" ");
|
||||
|
||||
// Create a new thread with the user's message as the initial event
|
||||
const thread = new Thread([{ type: "user_input", data: message }]);
|
||||
|
||||
// Run the agent loop with the thread
|
||||
let newThread = await agentLoop(thread);
|
||||
let lastEvent = newThread.events.slice(-1)[0];
|
||||
|
||||
while (lastEvent.data.intent !== "done_for_now") {
|
||||
const responseEvent = await askHuman(lastEvent);
|
||||
thread.events.push(responseEvent);
|
||||
newThread = await agentLoop(thread);
|
||||
lastEvent = newThread.events.slice(-1)[0];
|
||||
}
|
||||
|
||||
// print the final result
|
||||
// optional - you could loop here too
|
||||
console.log(lastEvent.data.message);
|
||||
process.exit(0);
|
||||
}
|
||||
|
||||
async function askHuman(lastEvent: Event): Promise<Event> {
|
||||
if (process.env.HUMANLAYER_API_KEY) {
|
||||
return await askHumanEmail(lastEvent);
|
||||
} else {
|
||||
return await askHumanCLI(lastEvent.data.message);
|
||||
}
|
||||
}
|
||||
|
||||
async function askHumanCLI(message: string): Promise<Event> {
|
||||
const readline = require('readline').createInterface({
|
||||
input: process.stdin,
|
||||
output: process.stdout
|
||||
});
|
||||
|
||||
return new Promise((resolve) => {
|
||||
readline.question(`${message}\n> `, (answer: string) => {
|
||||
resolve({ type: "human_response", data: answer });
|
||||
});
|
||||
});
|
||||
}
|
||||
|
||||
export async function askHumanEmail(lastEvent: Event): Promise<Event> {
|
||||
if (!process.env.HUMANLAYER_EMAIL) {
|
||||
throw new Error("missing or invalid parameters: HUMANLAYER_EMAIL");
|
||||
}
|
||||
const hl = humanlayer({ //reads apiKey from env
|
||||
// name of this agent
|
||||
runId: "12fa-cli-agent",
|
||||
verbose: true,
|
||||
contactChannel: {
|
||||
// agent should request permission via email
|
||||
email: {
|
||||
address: process.env.HUMANLAYER_EMAIL,
|
||||
}
|
||||
}
|
||||
})
|
||||
|
||||
if (lastEvent.data.intent === "divide") {
|
||||
// fetch approval synchronously - this will block until reply
|
||||
const response = await hl.fetchHumanApproval({
|
||||
spec: {
|
||||
fn: "divide",
|
||||
kwargs: {
|
||||
a: lastEvent.data.a,
|
||||
b: lastEvent.data.b
|
||||
}
|
||||
}
|
||||
})
|
||||
|
||||
if (response.approved) {
|
||||
const result = lastEvent.data.a / lastEvent.data.b;
|
||||
console.log("tool_response", result);
|
||||
return {
|
||||
"type": "tool_response",
|
||||
"data": result
|
||||
};
|
||||
} else {
|
||||
return {
|
||||
"type": "tool_response",
|
||||
"data": `user denied operation ${lastEvent.data.intent}
|
||||
with feedback: ${response.comment}`
|
||||
};
|
||||
}
|
||||
}
|
||||
throw new Error(`unknown tool: ${lastEvent.data.intent}`)
|
||||
}
|
||||
BIN
workshops/2025-05-17/walkthrough/11-email-approve.png
Normal file
BIN
workshops/2025-05-17/walkthrough/11-email-approve.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 178 KiB |
BIN
workshops/2025-05-17/walkthrough/11-email-custom.png
Normal file
BIN
workshops/2025-05-17/walkthrough/11-email-custom.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 66 KiB |
BIN
workshops/2025-05-17/walkthrough/11-email-reject.png
Normal file
BIN
workshops/2025-05-17/walkthrough/11-email-reject.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 182 KiB |
116
workshops/2025-05-17/walkthrough/11b-cli.ts
Normal file
116
workshops/2025-05-17/walkthrough/11b-cli.ts
Normal file
@@ -0,0 +1,116 @@
|
||||
// cli.ts lets you invoke the agent loop from the command line
|
||||
|
||||
import { humanlayer } from "humanlayer";
|
||||
import { agentLoop, Thread, Event } from "../src/agent";
|
||||
|
||||
export async function cli() {
|
||||
// Get command line arguments, skipping the first two (node and script name)
|
||||
const args = process.argv.slice(2);
|
||||
|
||||
if (args.length === 0) {
|
||||
console.error("Error: Please provide a message as a command line argument");
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
// Join all arguments into a single message
|
||||
const message = args.join(" ");
|
||||
|
||||
// Create a new thread with the user's message as the initial event
|
||||
const thread = new Thread([{ type: "user_input", data: message }]);
|
||||
|
||||
// Run the agent loop with the thread
|
||||
let newThread = await agentLoop(thread);
|
||||
let lastEvent = newThread.events.slice(-1)[0];
|
||||
|
||||
while (lastEvent.data.intent !== "done_for_now") {
|
||||
const responseEvent = await askHuman(lastEvent);
|
||||
thread.events.push(responseEvent);
|
||||
newThread = await agentLoop(thread);
|
||||
lastEvent = newThread.events.slice(-1)[0];
|
||||
}
|
||||
|
||||
// print the final result
|
||||
// optional - you could loop here too
|
||||
console.log(lastEvent.data.message);
|
||||
process.exit(0);
|
||||
}
|
||||
|
||||
async function askHuman(lastEvent: Event): Promise<Event> {
|
||||
if (process.env.HUMANLAYER_API_KEY) {
|
||||
return await askHumanEmail(lastEvent);
|
||||
} else {
|
||||
return await askHumanCLI(lastEvent.data.message);
|
||||
}
|
||||
}
|
||||
|
||||
async function askHumanCLI(message: string): Promise<Event> {
|
||||
const readline = require('readline').createInterface({
|
||||
input: process.stdin,
|
||||
output: process.stdout
|
||||
});
|
||||
|
||||
return new Promise((resolve) => {
|
||||
readline.question(`${message}\n> `, (answer: string) => {
|
||||
resolve({ type: "human_response", data: answer });
|
||||
});
|
||||
});
|
||||
}
|
||||
|
||||
export async function askHumanEmail(lastEvent: Event): Promise<Event> {
|
||||
if (!process.env.HUMANLAYER_EMAIL) {
|
||||
throw new Error("missing or invalid parameters: HUMANLAYER_EMAIL");
|
||||
}
|
||||
const hl = humanlayer({ //reads apiKey from env
|
||||
// name of this agent
|
||||
runId: "12fa-cli-agent",
|
||||
verbose: true,
|
||||
contactChannel: {
|
||||
// agent should request permission via email
|
||||
email: {
|
||||
address: process.env.HUMANLAYER_EMAIL,
|
||||
}
|
||||
}
|
||||
})
|
||||
|
||||
if (lastEvent.data.intent === "request_more_information") {
|
||||
// fetch response synchronously - this will block until reply
|
||||
const response = await hl.fetchHumanResponse({
|
||||
spec: {
|
||||
msg: lastEvent.data.message
|
||||
}
|
||||
})
|
||||
return {
|
||||
"type": "tool_response",
|
||||
"data": response
|
||||
}
|
||||
}
|
||||
|
||||
if (lastEvent.data.intent === "divide") {
|
||||
// fetch approval synchronously - this will block until reply
|
||||
const response = await hl.fetchHumanApproval({
|
||||
spec: {
|
||||
fn: "divide",
|
||||
kwargs: {
|
||||
a: lastEvent.data.a,
|
||||
b: lastEvent.data.b
|
||||
}
|
||||
}
|
||||
})
|
||||
|
||||
if (response.approved) {
|
||||
const result = lastEvent.data.a / lastEvent.data.b;
|
||||
console.log("tool_response", result);
|
||||
return {
|
||||
"type": "tool_response",
|
||||
"data": result
|
||||
};
|
||||
} else {
|
||||
return {
|
||||
"type": "tool_response",
|
||||
"data": `user denied operation ${lastEvent.data.intent}
|
||||
with feedback: ${response.comment}`
|
||||
};
|
||||
}
|
||||
}
|
||||
throw new Error(`unknown tool: ${lastEvent.data.intent}`)
|
||||
}
|
||||
125
workshops/2025-05-17/walkthrough/11c-cli.ts
Normal file
125
workshops/2025-05-17/walkthrough/11c-cli.ts
Normal file
@@ -0,0 +1,125 @@
|
||||
// cli.ts lets you invoke the agent loop from the command line
|
||||
|
||||
import { humanlayer } from "humanlayer";
|
||||
import { agentLoop, Thread, Event } from "../src/agent";
|
||||
|
||||
export async function cli() {
|
||||
// Get command line arguments, skipping the first two (node and script name)
|
||||
const args = process.argv.slice(2);
|
||||
|
||||
if (args.length === 0) {
|
||||
console.error("Error: Please provide a message as a command line argument");
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
// Join all arguments into a single message
|
||||
const message = args.join(" ");
|
||||
|
||||
// Create a new thread with the user's message as the initial event
|
||||
const thread = new Thread([{ type: "user_input", data: message }]);
|
||||
|
||||
// Run the agent loop with the thread
|
||||
let newThread = await agentLoop(thread);
|
||||
let lastEvent = newThread.events.slice(-1)[0];
|
||||
|
||||
while (lastEvent.data.intent !== "done_for_now") {
|
||||
const responseEvent = await askHuman(lastEvent);
|
||||
thread.events.push(responseEvent);
|
||||
newThread = await agentLoop(thread);
|
||||
lastEvent = newThread.events.slice(-1)[0];
|
||||
}
|
||||
|
||||
// print the final result
|
||||
// optional - you could loop here too
|
||||
console.log(lastEvent.data.message);
|
||||
process.exit(0);
|
||||
}
|
||||
|
||||
async function askHuman(lastEvent: Event): Promise<Event> {
|
||||
if (process.env.HUMANLAYER_API_KEY) {
|
||||
return await askHumanEmail(lastEvent);
|
||||
} else {
|
||||
return await askHumanCLI(lastEvent.data.message);
|
||||
}
|
||||
}
|
||||
|
||||
async function askHumanCLI(message: string): Promise<Event> {
|
||||
const readline = require('readline').createInterface({
|
||||
input: process.stdin,
|
||||
output: process.stdout
|
||||
});
|
||||
|
||||
return new Promise((resolve) => {
|
||||
readline.question(`${message}\n> `, (answer: string) => {
|
||||
resolve({ type: "human_response", data: answer });
|
||||
});
|
||||
});
|
||||
}
|
||||
|
||||
export async function askHumanEmail(lastEvent: Event): Promise<Event> {
|
||||
if (!process.env.HUMANLAYER_EMAIL) {
|
||||
throw new Error("missing or invalid parameters: HUMANLAYER_EMAIL");
|
||||
}
|
||||
const hl = humanlayer({ //reads apiKey from env
|
||||
// name of this agent
|
||||
runId: "12fa-cli-agent",
|
||||
verbose: true,
|
||||
contactChannel: {
|
||||
// agent should request permission via email
|
||||
email: {
|
||||
address: process.env.HUMANLAYER_EMAIL,
|
||||
// custom email body - jinja
|
||||
template: `{% if type == 'request_more_information' %}
|
||||
{{ event.spec.msg }}
|
||||
{% else %}
|
||||
agent {{ event.run_id }} is requesting approval for {{event.spec.fn}}
|
||||
with args: {{event.spec.kwargs}}
|
||||
<br><br>
|
||||
reply to this email to approve
|
||||
{% endif %}`
|
||||
}
|
||||
}
|
||||
})
|
||||
|
||||
if (lastEvent.data.intent === "request_more_information") {
|
||||
// fetch response synchronously - this will block until reply
|
||||
const response = await hl.fetchHumanResponse({
|
||||
spec: {
|
||||
msg: lastEvent.data.message
|
||||
}
|
||||
})
|
||||
return {
|
||||
"type": "tool_response",
|
||||
"data": response
|
||||
}
|
||||
}
|
||||
|
||||
if (lastEvent.data.intent === "divide") {
|
||||
// fetch approval synchronously - this will block until reply
|
||||
const response = await hl.fetchHumanApproval({
|
||||
spec: {
|
||||
fn: "divide",
|
||||
kwargs: {
|
||||
a: lastEvent.data.a,
|
||||
b: lastEvent.data.b
|
||||
}
|
||||
}
|
||||
})
|
||||
|
||||
if (response.approved) {
|
||||
const result = lastEvent.data.a / lastEvent.data.b;
|
||||
console.log("tool_response", result);
|
||||
return {
|
||||
"type": "tool_response",
|
||||
"data": result
|
||||
};
|
||||
} else {
|
||||
return {
|
||||
"type": "tool_response",
|
||||
"data": `user denied operation ${lastEvent.data.intent}
|
||||
with feedback: ${response.comment}`
|
||||
};
|
||||
}
|
||||
}
|
||||
throw new Error(`unknown tool: ${lastEvent.data.intent}`)
|
||||
}
|
||||
131
workshops/2025-05-17/walkthrough/12-1-server-init.ts
Normal file
131
workshops/2025-05-17/walkthrough/12-1-server-init.ts
Normal file
@@ -0,0 +1,131 @@
|
||||
import express from 'express';
|
||||
import { Thread, agentLoop, handleNextStep } from '../src/agent';
|
||||
import { ThreadStore } from '../src/state';
|
||||
import { humanlayer } from 'humanlayer';
|
||||
|
||||
const app = express();
|
||||
app.use(express.json());
|
||||
app.set('json spaces', 2);
|
||||
|
||||
const store = new ThreadStore();
|
||||
|
||||
const getHumanlayer = () => {
|
||||
const HUMANLAYER_EMAIL = process.env.HUMANLAYER_EMAIL;
|
||||
if (!HUMANLAYER_EMAIL) {
|
||||
throw new Error("missing or invalid parameters: HUMANLAYER_EMAIL");
|
||||
}
|
||||
|
||||
const HUMANLAYER_API_KEY = process.env.HUMANLAYER_API_KEY;
|
||||
if (!HUMANLAYER_API_KEY) {
|
||||
throw new Error("missing or invalid parameters: HUMANLAYER_API_KEY");
|
||||
}
|
||||
return humanlayer({
|
||||
runId: `12fa-agent`,
|
||||
contactChannel: {
|
||||
email: { address: HUMANLAYER_EMAIL }
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
// POST /thread - Start new thread
|
||||
app.post('/thread', async (req, res) => {
|
||||
const thread = new Thread([{
|
||||
type: "user_input",
|
||||
data: req.body.message
|
||||
}]);
|
||||
|
||||
const threadId = store.create(thread);
|
||||
const newThread = await agentLoop(thread);
|
||||
|
||||
store.update(threadId, newThread);
|
||||
|
||||
const lastEvent = newThread.events[newThread.events.length - 1];
|
||||
// If we exited the loop, include the response URL so the client can
|
||||
// push a new message onto the thread
|
||||
lastEvent.data.response_url = `/thread/${threadId}/response`;
|
||||
|
||||
console.log("returning last event from endpoint", lastEvent);
|
||||
|
||||
res.json({
|
||||
thread_id: threadId,
|
||||
...newThread
|
||||
});
|
||||
});
|
||||
|
||||
// GET /thread/:id - Get thread status
|
||||
app.get('/thread/:id', (req, res) => {
|
||||
const thread = store.get(req.params.id);
|
||||
if (!thread) {
|
||||
return res.status(404).json({ error: "Thread not found" });
|
||||
}
|
||||
res.json(thread);
|
||||
});
|
||||
|
||||
|
||||
type ApprovalPayload = {
|
||||
type: "approval";
|
||||
approved: boolean;
|
||||
comment?: string;
|
||||
}
|
||||
|
||||
type ResponsePayload = {
|
||||
type: "response";
|
||||
response: string;
|
||||
}
|
||||
|
||||
type Payload = ApprovalPayload | ResponsePayload;
|
||||
|
||||
// POST /thread/:id/response - Handle clarification response
|
||||
app.post('/thread/:id/response', async (req, res) => {
|
||||
let thread = store.get(req.params.id);
|
||||
if (!thread) {
|
||||
return res.status(404).json({ error: "Thread not found" });
|
||||
}
|
||||
|
||||
const body: Payload = req.body;
|
||||
|
||||
let lastEvent = thread.events[thread.events.length - 1];
|
||||
|
||||
if (thread.awaitingHumanResponse() && body.type === 'response') {
|
||||
thread.events.push({
|
||||
type: "human_response",
|
||||
data: body.response
|
||||
});
|
||||
} else if (thread.awaitingHumanApproval() && body.type === 'approval' && !body.approved) {
|
||||
// push feedback onto the thread
|
||||
thread.events.push({
|
||||
type: "tool_response",
|
||||
data: `user denied the operation with feedback: "${body.comment}"`
|
||||
});
|
||||
} else if (thread.awaitingHumanApproval() && body.type === 'approval' && body.approved) {
|
||||
// approved, run the tool, pushing results onto the thread
|
||||
await handleNextStep(lastEvent.data, thread);
|
||||
} else {
|
||||
res.status(400).json({
|
||||
error: "Invalid request: " + body.type,
|
||||
awaitingHumanResponse: thread.awaitingHumanResponse(),
|
||||
awaitingHumanApproval: thread.awaitingHumanApproval()
|
||||
});
|
||||
return;
|
||||
}
|
||||
|
||||
|
||||
// loop until stop event
|
||||
const result = await agentLoop(thread);
|
||||
|
||||
store.update(req.params.id, result);
|
||||
|
||||
lastEvent = result.events[result.events.length - 1];
|
||||
lastEvent.data.response_url = `/thread/${req.params.id}/response`;
|
||||
|
||||
console.log("returning last event from endpoint", lastEvent);
|
||||
|
||||
res.json(result);
|
||||
});
|
||||
|
||||
const port = process.env.PORT || 3000;
|
||||
app.listen(port, () => {
|
||||
console.log(`Server running on port ${port}`);
|
||||
});
|
||||
|
||||
export { app };
|
||||
106
workshops/2025-05-17/walkthrough/12-server.ts
Normal file
106
workshops/2025-05-17/walkthrough/12-server.ts
Normal file
@@ -0,0 +1,106 @@
|
||||
import express, { Request, Response } from 'express';
|
||||
import { Thread, agentLoop, handleNextStep } from '../src/agent';
|
||||
import { ThreadStore } from '../src/state';
|
||||
import { humanlayer, V1Beta2HumanContactCompleted } from 'humanlayer';
|
||||
|
||||
const app = express();
|
||||
app.use(express.json());
|
||||
app.set('json spaces', 2);
|
||||
|
||||
const store = new ThreadStore();
|
||||
|
||||
|
||||
const getHumanlayer = () => {
|
||||
const HUMANLAYER_EMAIL = process.env.HUMANLAYER_EMAIL;
|
||||
if (!HUMANLAYER_EMAIL) {
|
||||
throw new Error("missing or invalid parameters: HUMANLAYER_EMAIL");
|
||||
}
|
||||
|
||||
const HUMANLAYER_API_KEY = process.env.HUMANLAYER_API_KEY;
|
||||
if (!HUMANLAYER_API_KEY) {
|
||||
throw new Error("missing or invalid parameters: HUMANLAYER_API_KEY");
|
||||
}
|
||||
return humanlayer({
|
||||
runId: `12fa-agent`,
|
||||
contactChannel: {
|
||||
email: { address: HUMANLAYER_EMAIL }
|
||||
}
|
||||
});
|
||||
}
|
||||
// POST /thread - Start new thread
|
||||
app.post('/thread', async (req: Request, res: Response) => {
|
||||
const thread = new Thread([{
|
||||
type: "user_input",
|
||||
data: req.body.message
|
||||
}]);
|
||||
|
||||
// run agent loop asynchronously, return immediately
|
||||
Promise.resolve().then(async () => {
|
||||
const threadId = store.create(thread);
|
||||
const newThread = await agentLoop(thread);
|
||||
|
||||
store.update(threadId, newThread);
|
||||
|
||||
const lastEvent = newThread.events[newThread.events.length - 1];
|
||||
|
||||
if (thread.awaitingHumanResponse()) {
|
||||
const hl = getHumanlayer();
|
||||
// create a human contact - returns immediately
|
||||
hl.createHumanContact({
|
||||
spec: {
|
||||
msg: lastEvent.data.message,
|
||||
state: {
|
||||
thread_id: threadId,
|
||||
}
|
||||
}
|
||||
});
|
||||
}
|
||||
});
|
||||
|
||||
res.json({ status: "processing" });
|
||||
});
|
||||
|
||||
// GET /thread/:id - Get thread status
|
||||
app.get('/thread/:id', (req: Request, res: Response) => {
|
||||
const thread = store.get(req.params.id);
|
||||
if (!thread) {
|
||||
return res.status(404).json({ error: "Thread not found" });
|
||||
}
|
||||
res.json(thread);
|
||||
});
|
||||
|
||||
type WebhookResponse = V1Beta2HumanContactCompleted;
|
||||
|
||||
const handleHumanResponse = async (req: Request, res: Response) => {
|
||||
|
||||
}
|
||||
|
||||
app.post('/webhook', async (req: Request, res: Response) => {
|
||||
console.log("webhook response", req.body);
|
||||
const response = req.body as WebhookResponse;
|
||||
|
||||
// response is guaranteed to be set on a webhook
|
||||
const humanResponse: string = response.event.status?.response as string;
|
||||
|
||||
const threadId = response.event.spec.state?.thread_id;
|
||||
if (!threadId) {
|
||||
return res.status(400).json({ error: "Thread ID not found" });
|
||||
}
|
||||
|
||||
const thread = store.get(threadId);
|
||||
if (!thread) {
|
||||
return res.status(404).json({ error: "Thread not found" });
|
||||
}
|
||||
|
||||
if (!thread.awaitingHumanResponse()) {
|
||||
return res.status(400).json({ error: "Thread is not awaiting human response" });
|
||||
}
|
||||
|
||||
});
|
||||
|
||||
const port = process.env.PORT || 3000;
|
||||
app.listen(port, () => {
|
||||
console.log(`Server running on port ${port}`);
|
||||
});
|
||||
|
||||
export { app };
|
||||
105
workshops/2025-05-17/walkthrough/12a-server.ts
Normal file
105
workshops/2025-05-17/walkthrough/12a-server.ts
Normal file
@@ -0,0 +1,105 @@
|
||||
import express, { Request, Response } from 'express';
|
||||
import { Thread, agentLoop, handleNextStep } from '../src/agent';
|
||||
import { ThreadStore } from '../src/state';
|
||||
import { humanlayer, V1Beta2HumanContactCompleted } from 'humanlayer';
|
||||
|
||||
const app = express();
|
||||
app.use(express.json());
|
||||
app.set('json spaces', 2);
|
||||
|
||||
const store = new ThreadStore();
|
||||
|
||||
const getHumanlayer = () => {
|
||||
const HUMANLAYER_EMAIL = process.env.HUMANLAYER_EMAIL;
|
||||
if (!HUMANLAYER_EMAIL) {
|
||||
throw new Error("missing or invalid parameters: HUMANLAYER_EMAIL");
|
||||
}
|
||||
|
||||
const HUMANLAYER_API_KEY = process.env.HUMANLAYER_API_KEY;
|
||||
if (!HUMANLAYER_API_KEY) {
|
||||
throw new Error("missing or invalid parameters: HUMANLAYER_API_KEY");
|
||||
}
|
||||
return humanlayer({
|
||||
runId: `12fa-agent`,
|
||||
contactChannel: {
|
||||
email: { address: HUMANLAYER_EMAIL }
|
||||
}
|
||||
});
|
||||
}
|
||||
// POST /thread - Start new thread
|
||||
app.post('/thread', async (req: Request, res: Response) => {
|
||||
const thread = new Thread([{
|
||||
type: "user_input",
|
||||
data: req.body.message
|
||||
}]);
|
||||
|
||||
// run agent loop asynchronously, return immediately
|
||||
Promise.resolve().then(async () => {
|
||||
const threadId = store.create(thread);
|
||||
const newThread = await agentLoop(thread);
|
||||
|
||||
store.update(threadId, newThread);
|
||||
|
||||
const lastEvent = newThread.events[newThread.events.length - 1];
|
||||
|
||||
if (thread.awaitingHumanResponse()) {
|
||||
const hl = getHumanlayer();
|
||||
// create a human contact - returns immediately
|
||||
hl.createHumanContact({
|
||||
spec: {
|
||||
msg: lastEvent.data.message,
|
||||
state: {
|
||||
thread_id: threadId,
|
||||
}
|
||||
}
|
||||
});
|
||||
}
|
||||
});
|
||||
|
||||
res.json({ status: "processing" });
|
||||
});
|
||||
|
||||
// GET /thread/:id - Get thread status
|
||||
app.get('/thread/:id', (req: Request, res: Response) => {
|
||||
const thread = store.get(req.params.id);
|
||||
if (!thread) {
|
||||
return res.status(404).json({ error: "Thread not found" });
|
||||
}
|
||||
res.json(thread);
|
||||
});
|
||||
|
||||
type WebhookResponse = V1Beta2HumanContactCompleted;
|
||||
|
||||
const handleHumanResponse = async (req: Request, res: Response) => {
|
||||
|
||||
}
|
||||
|
||||
app.post('/webhook', async (req: Request, res: Response) => {
|
||||
console.log("webhook response", req.body);
|
||||
const response = req.body as WebhookResponse;
|
||||
|
||||
// response is guaranteed to be set on a webhook
|
||||
const humanResponse: string = response.event.status?.response as string;
|
||||
|
||||
const threadId = response.event.spec.state?.thread_id;
|
||||
if (!threadId) {
|
||||
return res.status(400).json({ error: "Thread ID not found" });
|
||||
}
|
||||
|
||||
const thread = store.get(threadId);
|
||||
if (!thread) {
|
||||
return res.status(404).json({ error: "Thread not found" });
|
||||
}
|
||||
|
||||
if (!thread.awaitingHumanResponse()) {
|
||||
return res.status(400).json({ error: "Thread is not awaiting human response" });
|
||||
}
|
||||
|
||||
});
|
||||
|
||||
const port = process.env.PORT || 3000;
|
||||
app.listen(port, () => {
|
||||
console.log(`Server running on port ${port}`);
|
||||
});
|
||||
|
||||
export { app };
|
||||
106
workshops/2025-05-17/walkthrough/12aa-server.ts
Normal file
106
workshops/2025-05-17/walkthrough/12aa-server.ts
Normal file
@@ -0,0 +1,106 @@
|
||||
import express, { Request, Response } from 'express';
|
||||
import { Thread, agentLoop, handleNextStep } from '../src/agent';
|
||||
import { ThreadStore } from '../src/state';
|
||||
import { humanlayer, V1Beta2HumanContactCompleted } from 'humanlayer';
|
||||
|
||||
const app = express();
|
||||
app.use(express.json());
|
||||
app.set('json spaces', 2);
|
||||
|
||||
const store = new ThreadStore();
|
||||
|
||||
|
||||
const getHumanlayer = () => {
|
||||
const HUMANLAYER_EMAIL = process.env.HUMANLAYER_EMAIL;
|
||||
if (!HUMANLAYER_EMAIL) {
|
||||
throw new Error("missing or invalid parameters: HUMANLAYER_EMAIL");
|
||||
}
|
||||
|
||||
const HUMANLAYER_API_KEY = process.env.HUMANLAYER_API_KEY;
|
||||
if (!HUMANLAYER_API_KEY) {
|
||||
throw new Error("missing or invalid parameters: HUMANLAYER_API_KEY");
|
||||
}
|
||||
return humanlayer({
|
||||
runId: `12fa-agent`,
|
||||
contactChannel: {
|
||||
email: { address: HUMANLAYER_EMAIL }
|
||||
}
|
||||
});
|
||||
}
|
||||
// POST /thread - Start new thread
|
||||
app.post('/thread', async (req: Request, res: Response) => {
|
||||
const thread = new Thread([{
|
||||
type: "user_input",
|
||||
data: req.body.message
|
||||
}]);
|
||||
|
||||
// run agent loop asynchronously, return immediately
|
||||
Promise.resolve().then(async () => {
|
||||
const threadId = store.create(thread);
|
||||
const newThread = await agentLoop(thread);
|
||||
|
||||
store.update(threadId, newThread);
|
||||
|
||||
const lastEvent = newThread.events[newThread.events.length - 1];
|
||||
|
||||
if (thread.awaitingHumanResponse()) {
|
||||
const hl = getHumanlayer();
|
||||
// create a human contact - returns immediately
|
||||
hl.createHumanContact({
|
||||
spec: {
|
||||
msg: lastEvent.data.message,
|
||||
state: {
|
||||
thread_id: threadId,
|
||||
}
|
||||
}
|
||||
});
|
||||
}
|
||||
});
|
||||
|
||||
res.json({ status: "processing" });
|
||||
});
|
||||
|
||||
// GET /thread/:id - Get thread status
|
||||
app.get('/thread/:id', (req: Request, res: Response) => {
|
||||
const thread = store.get(req.params.id);
|
||||
if (!thread) {
|
||||
return res.status(404).json({ error: "Thread not found" });
|
||||
}
|
||||
res.json(thread);
|
||||
});
|
||||
|
||||
type WebhookResponse = V1Beta2HumanContactCompleted;
|
||||
|
||||
const handleHumanResponse = async (req: Request, res: Response) => {
|
||||
|
||||
}
|
||||
|
||||
app.post('/webhook', async (req: Request, res: Response) => {
|
||||
console.log("webhook response", req.body);
|
||||
const response = req.body as WebhookResponse;
|
||||
|
||||
// response is guaranteed to be set on a webhook
|
||||
const humanResponse: string = response.event.status?.response as string;
|
||||
|
||||
const threadId = response.event.spec.state?.thread_id;
|
||||
if (!threadId) {
|
||||
return res.status(400).json({ error: "Thread ID not found" });
|
||||
}
|
||||
|
||||
const thread = store.get(threadId);
|
||||
if (!thread) {
|
||||
return res.status(404).json({ error: "Thread not found" });
|
||||
}
|
||||
|
||||
if (!thread.awaitingHumanResponse()) {
|
||||
return res.status(400).json({ error: "Thread is not awaiting human response" });
|
||||
}
|
||||
|
||||
});
|
||||
|
||||
const port = process.env.PORT || 3000;
|
||||
app.listen(port, () => {
|
||||
console.log(`Server running on port ${port}`);
|
||||
});
|
||||
|
||||
export { app };
|
||||
143
workshops/2025-05-17/walkthrough/12b-server.ts
Normal file
143
workshops/2025-05-17/walkthrough/12b-server.ts
Normal file
@@ -0,0 +1,143 @@
|
||||
import express from 'express';
|
||||
import { Thread, agentLoop, handleNextStep } from '../src/agent';
|
||||
import { ThreadStore } from '../src/state';
|
||||
import { V1Beta2EmailEventReceived, V1Beta2FunctionCallCompleted, V1Beta2HumanContactCompleted } from 'humanlayer';
|
||||
|
||||
const app = express();
|
||||
app.use(express.json());
|
||||
app.set('json spaces', 2);
|
||||
|
||||
const store = new ThreadStore();
|
||||
|
||||
// POST /thread - Start new thread
|
||||
app.post('/thread', async (req, res) => {
|
||||
const thread = new Thread([{
|
||||
type: "user_input",
|
||||
data: req.body.message
|
||||
}]);
|
||||
|
||||
const threadId = store.create(thread);
|
||||
const newThread = await agentLoop(thread);
|
||||
|
||||
store.update(threadId, newThread);
|
||||
|
||||
const lastEvent = newThread.events[newThread.events.length - 1];
|
||||
// If we exited the loop, include the response URL so the client can
|
||||
// push a new message onto the thread
|
||||
lastEvent.data.response_url = `/thread/${threadId}/response`;
|
||||
|
||||
console.log("returning last event from endpoint", lastEvent);
|
||||
|
||||
res.json({
|
||||
thread_id: threadId,
|
||||
...newThread
|
||||
});
|
||||
});
|
||||
|
||||
// GET /thread/:id - Get thread status
|
||||
app.get('/thread/:id', (req, res) => {
|
||||
const thread = store.get(req.params.id);
|
||||
if (!thread) {
|
||||
return res.status(404).json({ error: "Thread not found" });
|
||||
}
|
||||
res.json(thread);
|
||||
});
|
||||
|
||||
|
||||
type ApprovalPayload = {
|
||||
type: "approval";
|
||||
approved: boolean;
|
||||
comment?: string;
|
||||
}
|
||||
|
||||
type ResponsePayload = {
|
||||
type: "response";
|
||||
response: string;
|
||||
}
|
||||
|
||||
type Payload = ApprovalPayload | ResponsePayload;
|
||||
|
||||
// POST /thread/:id/response - Handle clarification response
|
||||
app.post('/thread/:id/response', async (req, res) => {
|
||||
let thread = store.get(req.params.id);
|
||||
if (!thread) {
|
||||
return res.status(404).json({ error: "Thread not found" });
|
||||
}
|
||||
|
||||
const body: Payload = req.body;
|
||||
|
||||
let lastEvent = thread.events[thread.events.length - 1];
|
||||
|
||||
if (thread.awaitingHumanResponse() && body.type === 'response') {
|
||||
thread.events.push({
|
||||
type: "human_response",
|
||||
data: body.response
|
||||
});
|
||||
} else if (thread.awaitingHumanApproval() && body.type === 'approval' && !body.approved) {
|
||||
// push feedback onto the thread
|
||||
thread.events.push({
|
||||
type: "tool_response",
|
||||
data: `user denied the operation with feedback: "${body.comment}"`
|
||||
});
|
||||
} else if (thread.awaitingHumanApproval() && body.type === 'approval' && body.approved) {
|
||||
// approved, run the tool, pushing results onto the thread
|
||||
await handleNextStep(lastEvent.data, thread);
|
||||
} else {
|
||||
res.status(400).json({
|
||||
error: "Invalid request: " + body.type,
|
||||
awaitingHumanResponse: thread.awaitingHumanResponse(),
|
||||
awaitingHumanApproval: thread.awaitingHumanApproval()
|
||||
});
|
||||
return;
|
||||
}
|
||||
|
||||
|
||||
// loop until stop event
|
||||
const result = await agentLoop(thread);
|
||||
|
||||
store.update(req.params.id, result);
|
||||
|
||||
lastEvent = result.events[result.events.length - 1];
|
||||
lastEvent.data.response_url = `/thread/${req.params.id}/response`;
|
||||
|
||||
console.log("returning last event from endpoint", lastEvent);
|
||||
|
||||
res.json(result);
|
||||
});
|
||||
|
||||
type WebhookResponse = V1Beta2HumanContactCompleted;
|
||||
|
||||
app.post('/webhook/response', async (req, res) => {
|
||||
console.log("webhook response", req.body);
|
||||
const response = req.body as WebhookResponse;
|
||||
|
||||
// response is guaranteed to be set on a webhook
|
||||
const humanResponse: string = response.event.status?.response as string;
|
||||
|
||||
const threadId = response.event.spec.state?.thread_id;
|
||||
if (!threadId) {
|
||||
return res.status(400).json({ error: "Thread ID not found" });
|
||||
}
|
||||
|
||||
const thread = store.get(threadId);
|
||||
if (!thread) {
|
||||
return res.status(404).json({ error: "Thread not found" });
|
||||
}
|
||||
|
||||
if (!thread.awaitingHumanResponse()) {
|
||||
return res.status(400).json({ error: "Thread is not awaiting human response" });
|
||||
}
|
||||
|
||||
thread.events.push({
|
||||
type: "human_response",
|
||||
data: response.event.status?.response
|
||||
});
|
||||
|
||||
});
|
||||
|
||||
const port = process.env.PORT || 3000;
|
||||
app.listen(port, () => {
|
||||
console.log(`Server running on port ${port}`);
|
||||
});
|
||||
|
||||
export { app };
|
||||
Reference in New Issue
Block a user