xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-04 04:40:38 +08:00
Code Issues Packages Projects Releases Wiki Activity

markdown update

Browse Source
This commit is contained in:
mrT23
2024-09-08 16:43:44 +03:00
parent edef712b6a
commit 332d3a0c5e
2 changed files with 20 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
docs/docs/core-abilities/index.md
View File

@ -1,10 +1,11 @@
# Core Abilities # Core Abilities
PR-Agent utilizes a variety of core abilities to provide a comprehensive and efficient code review experience. These abilities include: PR-Agent utilizes a variety of core abilities to provide a comprehensive and efficient code review experience. These abilities include:
- [Local and global metadata](core-abilities/metadata.md)
- [Line localization](core-abilities/line_localization.md) - [Local and global metadata](/metadata)
- [Dynamic context](core-abilities/dynamic_context.md) - [Line localization](/line_localization)
- [Self-reflection](core-abilities/self_reflection.md) - [Dynamic context](/dynamic_context)
- [Interactivity](core-abilities/interactivity.md) - [Self-reflection](/self_reflection)
- [Compression strategy](core-abilities/compression_strategy.md) - [Interactivity](/interactivity)
- [Code-oriented YAML](core-abilities/code_oriented_yaml.md) - [Compression strategy](/compression_strategy)
- [Static code analysis](core-abilities/static_code_analysis.md) - [Code-oriented YAML](/code_oriented_yaml)
- [Static code analysis](/static_code_analysis)

18
docs/docs/core-abilities/metadata.md
View File

@ -1,24 +1,26 @@
## Overview - Local and global metadata injection with multi-stage analysis ## Local and global metadata injection with multi-stage analysis
(1) (1)
PR-Agent initially retrieves for each PR the following data: PR-Agent initially retrieves for each PR the following data:
- PR title and branch name - PR title and branch name
- PR original description - PR original description
- Commit messages history - Commit messages history
- PR diff patches, in [hunk diff](https://loicpefferkorn.net/2014/02/diff-files-what-are-hunks-and-how-to-extract-them/) format - PR diff patches, in [hunk diff](https://loicpefferkorn.net/2014/02/diff-files-what-are-hunks-and-how-to-extract-them/) format
- The entire content of the files that were modified in the PR - The entire content of the files that were modified in the PR
In addition, PR-Agent is able to receive from the user additional data, like [`extra_instructions` and `best practices`](https://pr-agent-docs.codium.ai/tools/improve/#extra-instructions-and-best-practices) that can be used to enhance the PR analysis. In addition, PR-Agent can incorporate supplementary information provided by the user and more tailored to his specific preferences, like [`extra_instructions` and `organization best practices`](https://pr-agent-docs.codium.ai/tools/improve/#extra-instructions-and-best-practices) that can be used to enhance the PR analysis.
(2) (2)
By default, the first command that PR-Agent executes is [`describe`](https://pr-agent-docs.codium.ai/tools/describe/), which generates three types of outputs: By default, the first command that PR-Agent executes is [`describe`](https://pr-agent-docs.codium.ai/tools/describe/), which generates three types of outputs:
- PR Type (e.g. bug fix, feature, refactor, etc) - PR Type (e.g. bug fix, feature, refactor, etc)
- PR Description - a bullet points summary of the PR - PR Description - a bullet points summary of the PR
- Changes walkthrough - going file-by-file, PR-Agent generate a one-line summary and longer bullet points summary of the changes in the file - Changes walkthrough - going file-by-file, PR-Agent generate a one-line summary and longer bullet points summary of the changes in the file
These AI-generated outputs are now considered part of the PR metadata, and can be used in subsequent commands like `review` and `improve`. These AI-generated outputs are now considered as part of the PR metadata, and can be used in subsequent commands like `review` and `improve`.
This effectively enables chain-of-thought analysis, without doing any additional API calls which will cost time and money. This effectively enables multi-stage chain-of-thought analysis, without doing any additional API calls which will cost time and money.
For example, when generating code suggestions for different files, PR-Agent can inject the AI-generated file summary in the prompt: For example, when generating code suggestions for different files, PR-Agent can inject the AI-generated ["Changes walkthrough"](https://github.com/Codium-ai/pr-agent/pull/1202#issue-2511546839) file summary in the prompt:
``` ```
## File: 'src/file1.py' ## File: 'src/file1.py'
@ -46,6 +48,8 @@ __old hunk__
... ...
``` ```
(3) The entire PR files that were retrieved are used to expand and enhance the PR context (see [Dynamic Context](https://pr-agent-docs.codium.ai/core-abilities/dynamic-context/)). (3) The entire PR files that where retrieved are also used to expand and enhance the PR context (see [Dynamic Context](https://pr-agent-docs.codium.ai/core-abilities/dynamic-context/)).
(4) All the metadata described above represent several level of analysis - from hunk level, to file level, to PR level, and enables PR-Agent AI models to generate more accurate and relevant suggestions and feedbacks.
(4) All the metadata described above represents several level of cumulative analysis - ranging from hunk level, to file level, to PR level, to organization level.
This comprehensive approach enables PR-Agent AI models to generate more precise and contextually relevant suggestions and feedback.