Metadata-Version: 2.1
Name: pydanticai-zambo
Version: 0.1.0
Summary: PydanticAI function tools for Zambo with automatic verifiable receipt capture
Author: Zambo
License: MIT
Project-URL: Homepage, https://zambo.dev
Keywords: pydanticai,ai agent receipt,verifiable receipt,observability,mcp
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE

# pydanticai-zambo

PydanticAI function tools for [Zambo](https://zambo.dev), with automatic verifiable receipt capture. Every `ask_zambo` call routes a goal through Zambo's 100+ tools over the public MCP endpoint, and every call mints a public verifiable receipt at `https://zambo.dev/run/{id}`.

## Install

```bash
pip install pydanticai-zambo
```

## Ten-line example

```python
from pydanticai_zambo import ZamboToolset
from pydantic_ai import Agent
from pydantic_ai.models.test import TestModel

toolset = ZamboToolset()
agent = Agent(TestModel(), tools=toolset.tools())
result = agent.run_sync("Summarize the Zambo free tier")
toolset.record_run(result.output)
print(toolset.last_receipt_url)
```

The tool prints each public `https://zambo.dev/run/{id}` URL and keeps the most recent URL in `last_receipt_url`. The receipt describes what the endpoint recorded and observed. It does not prove an outside outcome that the endpoint did not observe.

Set `ZAMBO_API_URL` to point at a compatible Zambo host, or `ZAMBO_TIMEOUT` to change the request timeout. Receipt failures land in `receipt_errors` and never break the host agent.

The package imports cleanly without `pydantic-ai` installed; calling `tools()` without it raises an informative `ImportError` telling you to `pip install pydantic-ai`.

Project homepage: [https://zambo.dev](https://zambo.dev)
