Metadata-Version: 2.4
Name: swarm-agents
Version: 0.1.0
Summary: Lightweight framework for LLM agents with tools, hooks, guardrails, and provider routing
Project-URL: Homepage, https://github.com/logarith-ms/swarm-agents
Project-URL: Repository, https://github.com/logarith-ms/swarm-agents
Project-URL: Issues, https://github.com/logarith-ms/swarm-agents/issues
Project-URL: Releases, https://github.com/logarith-ms/swarm-agents/releases
Keywords: agents,guardrails,llm,routing,tools
Classifier: Development Status :: 2 - Pre-Alpha
Classifier: Framework :: AsyncIO
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Typing :: Typed
Requires-Python: >=3.11
Requires-Dist: httpx<0.28,>=0.27
Requires-Dist: litellm>=1.77.1
Requires-Dist: openai>=1.107.2
Requires-Dist: pydantic>=2.7
Provides-Extra: dev
Requires-Dist: build==1.4.0; extra == 'dev'
Requires-Dist: mypy==1.12.1; extra == 'dev'
Requires-Dist: pytest-asyncio==0.24.0; extra == 'dev'
Requires-Dist: pytest==8.3.2; extra == 'dev'
Requires-Dist: ruff==0.6.4; extra == 'dev'
Provides-Extra: image
Requires-Dist: numpy>=2.1; extra == 'image'
Description-Content-Type: text/markdown

# Swarm Agents

`swarm-agents` is a standalone Python package for building LLM agents with:

- provider-agnostic model routing
- function/tool execution
- lifecycle hooks
- input/output guardrails
- streaming dialogue execution
- autonomous batch execution

The import path is `swarm`.

## Package Docs

- Architecture: [`docs/architecture.md`](docs/architecture.md)
- Error handling: [`docs/error-handling.md`](docs/error-handling.md)

## Releases

Versions are derived from Git tags. A pushed `vX.Y.Z` tag creates:

- a GitHub Release with generated notes and attached build artifacts
- a PyPI publish job via Trusted Publishing

## Install

Base package:

```bash
pip install swarm-agents
```

With optional image helpers:

```bash
pip install "swarm-agents[image]"
```

From Git:

```bash
pip install "swarm-agents[dev] @ git+ssh://git@github.com/logarith-ms/swarm-agents.git@vX.Y.Z"
```

PyPI is the primary distribution channel. Git installs remain useful for pinned previews or local validation.

## Quick Start

`Swarm` is the beginner-facing entry point. It handles provider configuration and model-router wiring for you.

```python
from swarm import Agent, Swarm

client = Swarm()  # loads config from environment via ConfigLoader.load()

agent = Agent(
    name="Assistant",
    model="openai/gpt-4o",
    instructions="You are a helpful assistant.",
)

async for chunk in client.run_streamed(
    agent,
    deps=your_context,
    stream_manager=your_stream_manager,
    message_store=your_message_store,
    retry_policy=your_retry_policy,
    max_turns=10,
):
    print(chunk)
```

Batch execution:

```python
from swarm import Agent, Swarm

client = Swarm(
    config={
        "openai_api_key": "...",
        "openai_organization": "...",
        "openai_project": "...",
        "anthropic_api_key": "...",
        "google_api_key": "...",
        "vertex_project": "...",
        "vertex_location": "us-east1",
    }
)

agent = Agent(
    name="Planner",
    model="openai/gpt-4o",
    instructions="Work through the task step by step.",
)

result = await client.run_batch(
    agent,
    deps=your_context,
    stream_manager=your_stream_manager,
    message_store=your_message_store,
    retry_policy=your_retry_policy,
    max_turns=5,
)
print(result.signal)
```

## What The Facade Does

`Swarm(...)` removes only the provider/router wiring:

- `ConfigLoader.load()`
- `ProviderFactory(config=...)`
- `ModelRouter(factory=...)`
- `RunContext(..., router=...)`

You still provide implementations for the runtime protocols:

- `ContextProtocol`
- `StreamManagerProtocol`
- `MessageStoreProtocol`
- optionally `RetryPolicyProtocol`

Those implementations are application-specific and are intentionally not bundled as defaults in this package.

## Model Fallback

`Agent.model` supports either:

- a single model string
- a list of models in fallback order

Example:

```python
from swarm import Agent

agent = Agent(
    name="FallbackAgent",
    model=[
        "openai/gpt-4o",
        "anthropic/claude-3-5-sonnet",
        "google/gemini-2.0-flash",
    ],
    instructions="Try providers in order until one succeeds.",
)
```

The router will try each model in sequence until one succeeds or all fail.

## Provider Configuration

`ConfigLoader.load()` reads these environment variables and maps them to the config keys expected by `ProviderFactory`:

- `OPENAI_API_KEY`
- `OPENAI_ORGANIZATION`
- `OPENAI_PROJECT`
- `ANTHROPIC_API_KEY`
- `GOOGLE_API_KEY`
- `VERTEX_PROJECT_ID` -> `vertex_project`
- `VERTEX_LOCATION` -> `vertex_location`

## Advanced / Explicit Wiring

If you want full control, keep using the manual path directly:

```python
from swarm import Agent, ConfigLoader, DialogueRunner, ModelRouter, ProviderFactory
from swarm.context import RunContext

config = ConfigLoader.load()
router = ModelRouter(factory=ProviderFactory(config=config))

agent = Agent(
    name="Assistant",
    model="openai/gpt-4o",
    instructions="You are a helpful assistant.",
)

run_context = RunContext(
    deps=your_context,
    stream_manager=your_stream_manager,
    message_store=your_message_store,
    router=router,
    retry_policy=your_retry_policy,
)

runner = DialogueRunner()
async for chunk in runner.run_streamed(agent=agent, run_context=run_context, max_turns=10):
    print(chunk)
```

## Optional Image Support

`swarm.util.image_to_base64(...)` is available behind the `image` extra.

If you call it without installing the extra, it raises an `ImportError` with the install command:

```bash
pip install "swarm-agents[image]"
```

## Hooks And Guardrails

- Hooks are observational and never alter execution flow.
- Input guardrails run before the first LLM call.
- Output guardrails are blocking in `AgentRunner` and advisory in `DialogueRunner`.

See:

- `swarm.hooks`
- `swarm.guardrails`
- `swarm.runners.agent`
- `swarm.runners.dialogue`

## Development

```bash
pip install -e ".[dev]"
ruff format --check .
ruff check .
mypy swarm
pytest tests -q
python -m build
```

## Maintainer Release Flow

1. Merge conventional commits to `main`.
2. Wait for `CI` to pass and `Auto Tag` to create the next semantic `vX.Y.Z` tag.
3. The pushed tag triggers both:
   - `Release` for the GitHub Release page and attached wheel/sdist
   - `Publish PyPI` for Trusted Publishing to PyPI
4. Verify the new version on:
   - `https://github.com/logarith-ms/swarm-agents/releases`
   - `https://pypi.org/project/swarm-agents/`

## Notes

- `swarm_task/` is intentionally not part of this package.
- `swarm/ERROR_HANDLING.md` is intentionally not promoted into the package root.
