Starstruk Logo MarkStarstruk

python_1.1.0

2FastLabs/agent-squadpython_1.1.0Jul 1, 2026by cornelcroi

AI Summary

Python implementation of the GroundedAgent anti-hallucination pattern, mirroring the functionality of the TypeScript release.

Key Highlights

  • Same two-LLM architecture (gatherer/presenter) to prevent hallucinations.
  • Support for ToolOutputCurator and PresenterPrompt classes.
  • Comprehensive documentation and runnable chatbot example included.

New Features

  • GroundedAgent implementation
  • ToolOutputCurator system
  • PresenterPrompt configuration

Full Release Notes

## GroundedAgent (two-LLM anti-hallucination pattern)

Adds `GroundedAgent`: a gatherer LLM calls tools and sees the raw results but never speaks; an isolated presenter LLM writes the reply from **only** the curated tool output, so it can't invent values beyond what was fetched. A no-tool turn is answered by the gatherer directly, skipping the presenter.

- `GroundedAgent` / `GroundedAgentOptions`, `ToolOutputCurator` (`DataBlockCurator`, `PerToolCurator`), `PresenterPrompt`
- Docs: Built-in Agents → Grounded Agent
- Runnable example: `examples/grounded-agent-chatbot`

Feature merged in #551.