Metadata-Version: 2.4
Name: openagent-app
Version: 0.1.1
Summary: Terminal interface for OpenAgent
Author: OpenAgent contributors
License: Business Source License 1.1
Keywords: agent,ai,cli,coding-agent,terminal
Classifier: Development Status :: 3 - Alpha
Classifier: Environment :: Console
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 :: Software Development :: User Interfaces
Requires-Python: >=3.11
Description-Content-Type: text/markdown
Requires-Dist: rich<15.0,>=14.0
Requires-Dist: anthropic<1.0,>=0.42
Requires-Dist: pydantic-settings<3.0,>=2.6
Requires-Dist: python-dotenv<2.0,>=1.0
Requires-Dist: prompt-toolkit<4.0,>=3.0
Requires-Dist: openagent-core<1.0,>=0.1.1
Provides-Extra: test
Requires-Dist: pytest>=8.0; extra == "test"
Requires-Dist: pytest-asyncio>=0.24; extra == "test"

# OpenAgent CLI

Terminal interface for OpenAgent.

Provider thinking can be enabled per run:

```bash
openagent --thinking --thinking-effort max
```

Or in `~/.openagent/config.toml`:

```toml
thinking_enabled = true
thinking_effort = "max"
```

When enabled, the CLI prints provider thinking before the assistant reply and keeps normal reply streaming behavior intact.

During an interactive session, use slash commands to change it without restarting:

```text
/thinking
/thinking on
/thinking off
/thinking high
/thinking max
```

For the full project overview, setup guide, and architecture notes, see the repository
root [README](../README.md).
