xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-05 05:10:38 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/main'

Browse Source
This commit is contained in:
mrT23
2025-04-30 11:15:00 +03:00
parent 056adc6545 75a047f348
commit ed5b8e7828
5 changed files with 43 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
docs/docs/core-abilities/rag_context_enrichment.md
View File

@ -1,6 +1,6 @@
# RAG Context Enrichment 💎
`Supported Git Platforms: GitHub`
`Supported Git Platforms: GitHub, Bitbucket Data Center`
!!! info "Prerequisites"
- RAG is available only for Qodo enterprise plan users, with single tenant or on-premises setup.
@ -42,26 +42,25 @@ enable_rag=true
### Applications
#### 1\. The `/review` Tool
The following represents the complete list of tools with RAG capability:
The [`/review`](https://qodo-merge-docs.qodo.ai/tools/review/) tool offers the _Focus area from RAG data_ which contains feedback based on the RAG references analysis.
The complete list of references found relevant to the PR will be shown in the _References_ section, helping developers understand the broader context by exploring the provided references.
=== "`/review`"
The [`/review`](https://qodo-merge-docs.qodo.ai/tools/review/) tool offers the _Focus area from RAG data_ which contains feedback based on the RAG references analysis.
The complete list of references found relevant to the PR will be shown in the _References_ section, helping developers understand the broader context by exploring the provided references.
![References](https://codium.ai/images/pr_agent/rag_review.png){width=640}
![RAGed review tool](https://codium.ai/images/pr_agent/rag_review.png){width=640}
#### 2\. The `/implement` Tool
=== "`/implement`"
The [`/implement`](https://qodo-merge-docs.qodo.ai/tools/implement/) tool utilizes the RAG feature to provide comprehensive context of the repository codebase, allowing it to generate more refined code output.
The _References_ section contains links to the content used to support the code generation.
The [`/implement`](https://qodo-merge-docs.qodo.ai/tools/implement/) tool utilizes the RAG feature to provide comprehensive context of the repository codebase, allowing it to generate more refined code output.
The _References_ section contains links to the content used to support the code generation.
![RAGed implement tool](https://codium.ai/images/pr_agent/rag_implement.png){width=640}
![References](https://codium.ai/images/pr_agent/rag_implement.png){width=640}
=== "`/ask`"
The [`/ask`](https://qodo-merge-docs.qodo.ai/tools/ask/) tool can access broader repository context through the RAG feature when answering questions that go beyond the PR scope alone.
The _References_ section displays the additional repository content consulted to formulate the answer.
#### 3\. The `/ask` Tool
The [`/ask`](https://qodo-merge-docs.qodo.ai/tools/ask/) tool can access broader repository context through the RAG feature when answering questions that go beyond the PR scope alone.
The _References_ section displays the additional repository content consulted to formulate the answer.
![References](https://codium.ai/images/pr_agent/rag_ask.png){width=640}
![RAGed ask tool](https://codium.ai/images/pr_agent/rag_ask.png){width=640}
## Limitations

25
docs/docs/tools/improve.md
View File

@ -267,14 +267,35 @@ In such cases, we recommend prioritizing the suggestion's detailed description,
> `💎 feature` Platforms supported: GitHub, GitLab
If you set the following in your configuration file:
Qodo Merge implements an orchestrator agent that enables interactive code discussions, listening and responding to comments without requiring explicit tool calls.
The orchestrator intelligently analyzes your responses to determine if you want to implement a suggestion, ask a question, or request help, then delegates to the appropriate specialized tool.
#### How it works
Enable interactive code discussions by adding the following to your configuration file (default is `True`):
```toml
[pr_code_suggestions]
enable_chat_in_code_suggestions = true
```
The Qodo Merge bot will automatically listen and respond to comments within code suggestion discussions that it has initiated, without requiring explicit tool calls.
!!! info "Activating Dynamic Responses"
To obtain dynamic responses, the following steps are required:
1. Run the `/improve` command (mostly automatic)
2. Tick the `/improve` recommendation checkboxes (_Apply this suggestion_) to have Qodo Merge generate a new inline code suggestion discussion
3. The orchestrator agent will then automatically listen and reply to comments within the discussion without requiring additional commands
#### Explore the available interaction patterns:
=== "Asking for Details"
![Chat on code suggestions ask](https://codium.ai/images/pr_agent/improve_chat_on_code_suggestions_ask.png){width=512}
=== "Implementing Suggestions"
![Chat on code suggestions implement](https://codium.ai/images/pr_agent/improve_chat_on_code_suggestions_implement.png){width=512}
=== "Providing Additional Help"
![Chat on code suggestions help](https://codium.ai/images/pr_agent/improve_chat_on_code_suggestions_help.png){width=512}
### Dual publishing mode

4
docs/docs/usage-guide/changing_a_model.md
View File

@ -172,8 +172,8 @@ To use [Google AI Studio](https://aistudio.google.com/) models, set the relevant
```toml
[config] # in configuration.toml
model="google_ai_studio/gemini-1.5-flash"
fallback_models=["google_ai_studio/gemini-1.5-flash"]
model="gemini/gemini-1.5-flash"
fallback_models=["gemini/gemini-1.5-flash"]
[google_ai_studio] # in .secrets.toml
gemini_api_key = "..."

2
docs/mkdocs.yml
View File

@ -149,6 +149,8 @@ markdown_extensions:
- pymdownx.emoji:
emoji_index: !!python/name:material.extensions.emoji.twemoji
emoji_generator: !!python/name:material.extensions.emoji.to_svg
- pymdownx.tabbed:
alternate_style: true
- toc:
title: On this page
toc_depth: 3

4
pr_agent/git_providers/git_provider.py
View File

@ -133,7 +133,7 @@ class GitProvider(ABC):
def reply_to_comment_from_comment_id(self, comment_id: int, body: str):
pass
def get_pr_description(self, full: bool = True, split_changes_walkthrough=False) -> str or tuple:
def get_pr_description(self, full: bool = True, split_changes_walkthrough=False) -> str | tuple:
from pr_agent.algo.utils import clip_tokens
from pr_agent.config_loader import get_settings
max_tokens_description = get_settings().get("CONFIG.MAX_DESCRIPTION_TOKENS", None)
@ -285,7 +285,7 @@ class GitProvider(ABC):
def get_comment_url(self, comment) -> str:
return ""
def get_review_thread_comments(self, comment_id: int) -> list[dict]:
pass