Metadata-Version: 2.4
Name: wbal
Version: 0.4.0
Summary: Weights & Biases Agent Library - A minimal framework for building LLM agents
Requires-Python: <3.14,>=3.13
Requires-Dist: openai<1.100.0,>=1.0.0
Requires-Dist: pydantic>=2.12.5
Requires-Dist: pytest>=9.0.2
Requires-Dist: pyyaml>=6.0.0
Requires-Dist: weave>=0.52.22
Description-Content-Type: text/markdown

# WBAL

**W**eights & **B**iases **A**gent **L**ibrary - A minimal framework for building LLM agents.

## Overview

WBAL provides three core primitives:

- **Agent** - Orchestrates the perceive-invoke-do loop
- **Environment** - Provides tools and context
- **LM** - Language model interface

All components inherit from `WBALObject` (Pydantic BaseModel + `observe()` method).

## Quick Start

Requires `OPENAI_API_KEY` in your environment.

```python
import weave
from wbal import Environment, OpenAIWBAgent, weaveTool, GPT5MiniTester

weave.init('my-project')

class MyEnv(Environment):
    env = "You are a helpful assistant."
    include_tools_in_observe = True

    @weaveTool
    def greet(self, name: str) -> str:
        """Greet someone by name."""
        return f"Hello, {name}!"

agent = OpenAIWBAgent(
    lm=GPT5MiniTester(),
    env=MyEnv(task="Say hello to Alice"),
    maxSteps=5,
    system_prompt="Use tools when helpful. Call exit() when you're done.",
)
agent.run()
```

## Installation

From PyPI:

```bash
pip install wbal
```

From source (for local development):

```bash
git clone <this-repo>
cd wbal
uv sync
```

## Documentation

| Document | Description |
|----------|-------------|
| [USER.md](USER.md) | Usage guide, API reference, examples |
| [DEVELOPER.md](DEVELOPER.md) | Architecture, contributing, testing |
| [Agent_Instructions.md](Agent_Instructions.md) | Agent/environment guidance |

## CLI

```bash
# Run (baseline, non-interactive)
wbal run --project my-project --task "Say hello to Alice, then call exit()"

# Chat (interactive via tool calls)
wbal chat --project my-project --task "Say hello to Alice"

# Poll (runs once or on an interval)
wbal poll --project my-project --task "Check status" --interval 300

# Run from a YAML agent manifest
wbal run --project my-project --agent-spec path/to/agent.yaml --task "Do the thing"
```

## YAML Agents

WBAL supports YAML-based agent manifests that let you configure:
- model + max steps
- prompt files (YAML)
- tool modules to attach to the agent/env
- explicit subagent delegation (DAG) via `run_agent`

See `examples/agents/README.md`.

## Agent Bundles (WandBSwarm-compatible)

WBAL can run “agent bundles” that expose `run.sh` (required) and `install.sh` (optional),
with the same env var contract as WandBSwarm (`AGENT_DIR`, `TASK_DIR`, `WORKSPACE`, etc.).

```bash
wbal bundle validate --agent-dir path/to/agent
wbal bundle run --agent-dir path/to/agent --task-dir path/to/task --workspace-dir ./workspace
```

## API

```python
from wbal import (
    # Core
    Agent, Environment, StatefulEnvironment, LM,

    # Models
    GPT5Large, GPT5MiniTester,

    # Decorators
    weaveTool, tool,

    # Mixins
    ExitableAgent,

    # Helpers
    tool_timeout, format_openai_tool_response,
)
```

## Examples

See [`examples/`](examples/) for complete implementations.
- `examples/zagent_v1.py` - Orchestrator-style agent with persistent notes + bash tool

Run locally:
```bash
uv run python examples/zagent_v1.py --task "Inspect this repo, take notes, then exit()"
```

## Structure

```
wbal/
├── wbal/
│   ├── agent.py        # Agent class
│   ├── environment.py  # Environment, StatefulEnvironment
│   ├── lm.py           # LM, GPT5Large, GPT5MiniTester
│   ├── helper.py       # Tool decorators and utilities
│   └── mixins.py       # ExitableAgent
├── tests/
└── examples/
```
