README.md

# Table of Contents

* [Structure of CodeWriterFlow](#structure-of-codewriterflow)
* [run\_codewriter](#run_codewriter)
* [CodeWriterCtrlFlow](#CodeWriterCtrlFlow)
  * [CodeWriterCtrlFlow](#CodeWriterCtrlFlow.CodeWriterCtrlFlow)
* [CodeWriterAskUserFlow](#CodeWriterAskUserFlow)
  * [CodeWriterAskUserFlow](#CodeWriterAskUserFlow.CodeWriterAskUserFlow)
    * [run](#CodeWriterAskUserFlow.CodeWriterAskUserFlow.run)
* [CodeWriterFlow](#CodeWriterFlow)
  * [CodeWriterFlow](#CodeWriterFlow.CodeWriterFlow)
    * [detect\_finish\_or\_continue](#CodeWriterFlow.CodeWriterFlow.detect_finish_or_continue)
    * [run](#CodeWriterFlow.CodeWriterFlow.run)
* [\_\_init\_\_](#__init__)



# Structure of CodeWriterFlow

```
               goal
                |
                v
        +---------------+
        |  Controller   | --------<<<<-----------+
        +---------------+                        |
                |                                |
                | (command, command args)        |
                |                                |
                v                                |
        +------------------+                     |
        |   Executor       |  Each branch is an  |
        | (Tree Structure) |  executor           |
        +------------------+                     |
                |                                ^
                | (summary)                      |
                |                                |
                v                                |             
                |                                |
                +-> goes back to the Controller>-+

```

Structure of the Executors:
```
         +-------------------+
         |   Branching       |
         |    Executor       |
         +-------------------+
        /          |         \
       /           |          \
      /            |           \
     /             |            \
write_code      ask_user       test

```

About the branches:
- [ask_user](https://huggingface.co/aiflows/CodeWriterFlowModule/blob/main/CodeWriterAskUserFlow.py): Ask user for info / confirmation, etc.
- [write_code](https://huggingface.co/aiflows/InteractiveCodeGenFlowModule): Generates code (user edit is allowed) and fetches user feedback.
- [test](https://huggingface.co/aiflows/TestCodeFlowModule): Test the code, user can provide test suites, if nothing is provided, syntax of the code is checked.

How it works:
Controller calls write_code until user is satisfied in the feedback, then controller calls test to test the code, if test passes, finish.




<a id="run_codewriter"></a>

# run\_codewriter

<a id="CodeWriterCtrlFlow"></a>

# CodeWriterCtrlFlow

<a id="CodeWriterCtrlFlow.CodeWriterCtrlFlow"></a>

## CodeWriterCtrlFlow Objects

```python
class CodeWriterCtrlFlow(ChatAtomicFlow)
```

refer to https://huggingface.co/aiflows/JarvisFlowModule/blob/main/Controller_JarvisFlow.py

This class controls the execution of the CodeWriterFlow.

*Input Interface Non Initialized*:
- `goal`

*Input Interface Initialized*:
- `goal`
- `code`
- `feedback`

*Output Interface*:
- `command`
- `command_args`

*Config Parameters*:
- `backend`: the backend used to call the LLM.
- `commands`: a list of commands that the controller can use.
- `system_message_prompt_template`: the template of the system message prompt.
- `init_human_message_prompt_template`: the template of the init human (user) message prompt.
- `human_message_prompt_template`: the template of the human (user) message prompt.
- `previous_messages`: the sliding window of previous messages.

<a id="CodeWriterAskUserFlow"></a>

# CodeWriterAskUserFlow

<a id="CodeWriterAskUserFlow.CodeWriterAskUserFlow"></a>

## CodeWriterAskUserFlow Objects

```python
class CodeWriterAskUserFlow(HumanStandardInputFlow)
```

This class is used to ask for user feedback whenever the controller is unsure of something, or need confirmation, etc.
*Expected Input*:
- `question`: The question asked by the controller
*Expected Behaviour*:
- The question is displayed, and the user gives feedback by inputing string.
*Expected Ouput*:
- `feedback`: The input of the user.
- `code`: No code was written.

<a id="CodeWriterAskUserFlow.CodeWriterAskUserFlow.run"></a>

#### run

```python
def run(input_data: Dict[str, Any]) -> Dict[str, Any]
```

Run the flow.

**Arguments**:

- `input_data`: The input data.

**Returns**:

The output data.

<a id="CodeWriterFlow"></a>

# CodeWriterFlow

<a id="CodeWriterFlow.CodeWriterFlow"></a>

## CodeWriterFlow Objects

```python
class CodeWriterFlow(ContentWriterFlow)
```

This flow inherits from ContentWriterFlow, it is used to write code in an interactive way.
In the subflow of the executor, we specify an InteractiveCodeGenFlow (https://huggingface.co/aiflows/InteractiveCodeGenFlowModule)

*Input Interface*:
- `goal`

*Output Interface*:
- `code`
- `result`
- `summary`
- `status`

*Configuration Parameters*:
- `name`: Name of the flow
- `description`: Description of the flow
- `_target_`: The instantiation target of the flow
- `input_interface`: The input to the flow. Inherited from ContentWriterFlow, in this case, it is `goal`.
- `output_interface`: The output of the flow.
- `subflows_config`: Configurations of subflows
- `early_exit_keys`: The keys that will trigger an early exit of the flow
- `topology`: Configures the topology of the subflows, please have a special look at the I/O interfaces of the subflows.

<a id="CodeWriterFlow.CodeWriterFlow.detect_finish_or_continue"></a>

#### detect\_finish\_or\_continue

```python
@CircularFlow.output_msg_payload_processor
def detect_finish_or_continue(output_payload: Dict[str, Any],
                              src_flow) -> Dict[str, Any]
```

This function is used to detect whether the code generation process is finished or not.

It is configured in the topology of the subflows, see CodeWriterFlow.yaml for more details.

**Arguments**:

- `output_payload`: The output payload of the subflow
- `src_flow`: The subflow that generated the output payload

**Returns**:

The output payload of the subflow

<a id="CodeWriterFlow.CodeWriterFlow.run"></a>

#### run

```python
def run(input_data: Dict[str, Any]) -> Dict[str, Any]
```

The run function of the flow.

**Arguments**:

- `input_data`: The input data of the flow

**Returns**:

The output data of the flow

<a id="__init__"></a>

# \_\_init\_\_