Move examples to project root (#40)

README.md

@@ -56,7 +56,7 @@ python -m freeact.cli \
   --skill-modules=freeact_skills.search.google.stream.api
 ```
 
-or an equivalent [quickstart.py](freeact/examples/quickstart.py) script:
+or an equivalent [quickstart.py](examples/quickstart.py) script:
 
 ```python
 import asyncio

docs/integration.md

@@ -39,8 +39,8 @@ Although we could instantiate `GenericModel` directly with these prompt template
 
 Here's a Python example that uses `QwenCoder` as code action model in a `freeact` agent. The model is accessed via the Hugging Face Inference API:
 
-```python title="freeact/examples/qwen.py"
---8<-- "freeact/examples/qwen.py"
+```python title="examples/qwen.py"
+--8<-- "examples/qwen.py"
 ```
 
 1. Your Hugging Face [user access token](https://huggingface.co/docs/hub/en/security-tokens)

docs/quickstart.md

@@ -27,8 +27,8 @@ python -m freeact.cli \
 
 or an equivalent Python script:
 
-```python title="freeact/examples/quickstart.py"
---8<-- "freeact/examples/quickstart.py"
+```python title="examples/quickstart.py"
+--8<-- "examples/quickstart.py"
 ```
 
 Once launched, you can start interacting with the agent:

docs/tutorials/basics.md

@@ -7,14 +7,14 @@ A `freeact` agent system consists of:
 - A code action model that generates *code actions* to be executed by the executor. Models must implement the interfaces defined in the [`freeact.model`](../api/model.md) package. This tutorial uses [`Claude`][freeact.model.claude.model.Claude], configured with `claude-3-5-sonnet-20241022` as model name.
 - A [`CodeActAgent`][freeact.agent.CodeActAgent] configured with both the model and executor. It orchestrates their interaction until a final response is ready.
 
-```python title="freeact/examples/basics.py"
---8<-- "freeact/examples/basics.py"
+```python title="examples/basics.py"
+--8<-- "examples/basics.py"
 ```
 
 1.  
-```python title="freeact/examples/utils.py::stream_conversation"
---8<-- "freeact/examples/utils.py:stream_conversation"
---8<-- "freeact/examples/utils.py:stream_turn"
+```python title="examples/utils.py::stream_conversation"
+--8<-- "examples/utils.py:stream_conversation"
+--8<-- "examples/utils.py:stream_turn"
 ```
 
 2. Tag of the `ipybox` Docker image.
@@ -35,9 +35,9 @@ A `CodeActAgent` can engage in multi-turn conversations with a user. Each turn i
 { .annotate }
 
 1.  
-```python title="freeact/examples/utils.py::stream_conversation"
---8<-- "freeact/examples/utils.py:stream_conversation"
---8<-- "freeact/examples/utils.py:stream_turn"
+```python title="examples/utils.py::stream_conversation"
+--8<-- "examples/utils.py:stream_conversation"
+--8<-- "examples/utils.py:stream_turn"
 ```
 
 This tutorial uses the `freeact_skills.search.google.stream.api` skill module from the [`freeact-skills`](https://gradion-ai.github.io/freeact-skills/) project to process queries that require internet searches. This module provides generative Google search capabilities powered by the Gemini 2 API.
@@ -63,22 +63,30 @@ The tutorials use the prebuilt [`ghcr.io/gradion-ai/ipybox:example`](../environm
 
 ## Running
 
-The Python example above is part of the `freeact` package and can be run with:
+Download the Python example
 
 ```shell
-python -m freeact.examples.basics
+mkdir examples
+curl -o examples/basics.py https://raw.githubusercontent.com/gradion-ai/freeact/refs/heads/main/freeact/examples/basics.py
+curl -o examples/utils.py https://raw.githubusercontent.com/gradion-ai/freeact/refs/heads/main/freeact/examples/utils.py
+```
+
+and run it with:
+
+```shell
+python examples/basics.py
 ```
 
 For formatted and colored console output, as shown in the [example conversation](#example-conversation), you can use the `freeact` [CLI](../cli.md):
 
 ```shell
---8<-- "freeact/examples/commands.txt:cli-basics-claude"
+--8<-- "examples/commands.txt:cli-basics-claude"
 ```
 
 To use Gemini instead of Claude, run:
 
 ```shell
---8<-- "freeact/examples/commands.txt:cli-basics-gemini"
+--8<-- "examples/commands.txt:cli-basics-gemini"
 ```
 
 See also [Supported models](../models.md) for other CLI examples.

docs/tutorials/extend.md

@@ -12,13 +12,13 @@ This tutorial demonstrates how `freeact` agents can be customized through system
 The [example conversation](#example-conversation) below was guided by this system extension:
 
 ```text title="extension.txt"
---8<-- "freeact/examples/extension.txt"
+--8<-- "examples/extension.txt"
 ```
 
 It was initiated with the following `freeact.cli` command, referencing the `extension.txt` file with the `--system-extension` option and reusing the developed `weather.weather_report` skill from the [Skill development](skills.md) tutorial.
 
 ```shell
---8<-- "freeact/examples/commands.txt:cli-extension"
+--8<-- "examples/commands.txt:cli-extension"
 ```
 
 ### Example conversation

docs/tutorials/skills.md

@@ -38,7 +38,7 @@ The [example conversation](#example-conversation) below was initiated with the f
 [^1]: The provided skill modules are not needed in this example but included to demonstrate that their usage is optional.
 
 ```shell
---8<-- "freeact/examples/commands.txt:cli-skills"
+--8<-- "examples/commands.txt:cli-skills"
 ```
 
 ### Example conversation
@@ -64,7 +64,7 @@ The example shows a request for weather data from Paris and Berlin, where the ag
 The example conversation was initiated with the following `freeact.cli` command. The developed skill is is read from `workspace/skills/private/example`. If we moved it to `workspace/skills/shared`, it would be available to all executors regardless of their `executor-key` value.
 
 ```shell
---8<-- "freeact/examples/commands.txt:cli-skills-weather"
+--8<-- "examples/commands.txt:cli-skills-weather"
 ```
 
 !!! Note

freeact/examples/basics.py → examples/basics.py

@@ -3,13 +3,13 @@
 
 from dotenv import load_dotenv
 
+from examples.utils import stream_conversation
 from freeact import (
     Claude,
     CodeActAgent,
     CodeExecutionContainer,
     CodeExecutor,
 )
-from freeact.examples.utils import stream_conversation
 from freeact.logger import Logger