xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-11 00:00:38 +08:00
Code Issues Packages Projects Releases Wiki Activity

Refactor improve.md: Improve image formatting, restructure content, and enhance descriptions

Browse Source
This commit is contained in:
mrT23
2024-03-19 09:56:10 +02:00
parent 728997fd0e
commit 1db58fd028
2 changed files with 57 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files

84
docs/docs/tools/improve.md
View File

@ -9,12 +9,20 @@ The tool can be triggered automatically every time a new PR is [opened](../usage
The code suggestions can be presented as a single comment (via `pr_code_suggestions.summarize=true`):
<kbd><img src=https://codium.ai/images/pr_agent/code_suggestions_as_comment.png width="768"></kbd>
<kbd>
<a href="https://codium.ai/images/pr_agent/code_suggestions_as_comment.png" target="_blank">
<img src="https://codium.ai/images/pr_agent/code_suggestions_as_comment.png" width="512">
</a>
</kbd>
Or as a separate commitable code comment for each suggestion:
<kbd><img src=https://codium.ai/images/pr_agent/improve.png width="768"></kbd>
<kbd>
<a href="https://codium.ai/images/pr_agent/improve.png" target="_blank">
<img src=https://codium.ai/images/pr_agent/improve.png width="512">
</a>
</kbd>
Note that a single comment has a significantly smaller PR footprint. We recommend this mode for most cases.
Also note that collapsible are not supported in _Bitbucket_. Hence, the suggestions are presented there as code comments.
@ -43,47 +51,53 @@ To edit [configurations](https://github.com/Codium-ai/pr-agent/blob/main/pr_agen
/improve --pr_code_suggestions.some_config1=... --pr_code_suggestions.some_config2=...
```
### General options
!!! example "General options"
- `num_code_suggestions`: number of code suggestions provided by the 'improve' tool. Default is 4.
- `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".
- `rank_suggestions`: if set to true, the tool will rank the suggestions, based on importance. Default is false.
- `summarize`: if set to true, the tool will display the suggestions in a single comment. Default is false.
- `enable_help_text`: if set to true, the tool will display a help text in the comment. Default is true.
- `num_code_suggestions`: number of code suggestions provided by the 'improve' tool. Default is 4.
- `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".
- `rank_suggestions`: if set to true, the tool will rank the suggestions, based on importance. Default is false.
- `summarize`: if set to true, the tool will display the suggestions in a single comment. Default is false.
- `enable_help_text`: if set to true, the tool will display a help text in the comment. Default is true.
### params for '/improve --extended' mode
!!! example "params for '/improve --extended' mode"
- `auto_extended_mode`: enable extended mode automatically (no need for the `--extended` option). Default is true.
- `num_code_suggestions_per_chunk`: number of code suggestions provided by the 'improve' tool, per chunk. Default is 8.
- `rank_extended_suggestions`: if set to true, the tool will rank the suggestions, based on importance. Default is true.
- `max_number_of_calls`: maximum number of chunks. Default is 5.
- `final_clip_factor`: factor to remove suggestions with low confidence. Default is 0.9.
- `auto_extended_mode`: enable extended mode automatically (no need for the `--extended` option). Default is true.
- `num_code_suggestions_per_chunk`: number of code suggestions provided by the 'improve' tool, per chunk. Default is 8.
- `rank_extended_suggestions`: if set to true, the tool will rank the suggestions, based on importance. Default is true.
- `max_number_of_calls`: maximum number of chunks. Default is 5.
- `final_clip_factor`: factor to remove suggestions with low confidence. Default is 0.9.
## Usage Tips
### Extra instructions
!!! tip "Extra instructions"
Extra instructions are very important for the `imrpove` tool, since they enable you to guide the model to suggestions that are more relevant to the specific needs of the project.
Be specific, clear, and concise in the instructions. With extra instructions, you are the prompter. Specify relevant aspects that you want the model to focus on.
Examples for extra instructions:
```
[pr_code_suggestions] # /improve #
extra_instructions="""
Emphasize the following aspects:
- Does the code logic cover relevant edge cases?
- Is the code logic clear and easy to understand?
- Is the code logic efficient?
...
"""
```
Use triple quotes to write multi-line instructions. Use bullet points to make the instructions more readable.
Extra instructions are very important for the `imrpove` tool, since they enable you to guide the model to suggestions that are more relevant to the specific needs of the project.
Be specific, clear, and concise in the instructions. With extra instructions, you are the prompter. Specify relevant aspects that you want the model to focus on.
Examples for extra instructions:
```
[pr_code_suggestions] # /improve #
extra_instructions="""
Emphasize the following aspects:
- Does the code logic cover relevant edge cases?
- Is the code logic clear and easy to understand?
- Is the code logic efficient?
...
"""
```
Use triple quotes to write multi-line instructions. Use bullet points to make the instructions more readable.
### A note on code suggestions quality
- While the current AI for code is getting better and better (GPT-4), it's not flawless. Not all the suggestions will be perfect, and a user should not accept all of them automatically.
- Suggestions are not meant to be [simplistic](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/pr_code_suggestions_prompts.toml#L34). Instead, they aim to give deep feedback and raise questions, ideas and thoughts to the user, who can then use his judgment, experience, and understanding of the code base.
- Recommended to use the `exra_instructions` field to guide the model to suggestions that are more relevant to the specific needs of the project.
- Consider also trying the [Custom Suggestions Tool](./custom_suggestions.md) 💎, that will **only** propose suggestions that follow specific guidelines defined by user.
- While the current AI for code is getting better and better (GPT-4), it's not flawless. Not all the suggestions will be perfect, and a user should not accept all of them automatically. Critical reading and judgment are required.
- While mistakes of the AI are rare but can happen, a real benefit of the tool is to catch, with high probability, **mistakes or bugs done by the PR author**, when they happen. So, it's a good practice to spend the needed ~30-60 seconds to review the suggestions, even if not all of them are relevant.
- The hierarchical structure of the suggestions UI-UX is designed to help the user to _quickly_ understand them, and to decide which ones are relevant and which are not:
- Only if the `Category` header is relevant, the user should move to the summarized suggestion description
- Only if the summarized suggestion description is relevant, the user should click on the collpasible, to read the full suggestion description with a code preview example.
In addition, we recommend to use the `exra_instructions` field to guide the model to suggestions that are more relevant to the specific needs of the project.
<br>
Consider also trying the [Custom Suggestions Tool](./custom_suggestions.md) 💎, that will **only** propose suggestions that follow specific guidelines defined by user.