Update TOOLS_GUIDE.md

Merge pull request #630 from Codium-ai/tr/language
2025-07-04 12:50:38 +08:00 · 2024-01-30 08:22:29 +02:00 · 2024-01-30 08:21:43 +02:00 · 2024-01-29 12:11:23 -08:00 · 2024-01-29 22:00:11 +02:00 · 2024-01-29 21:52:54 +02:00
60 changed files with 2652 additions and 914 deletions
--- a/.github/workflows/pr-agent-review.yaml
+++ b/.github/workflows/pr-agent-review.yaml
@ -5,8 +5,9 @@
 name: PR-Agent

 on:
-  pull_request:
-  issue_comment:
+# pull_request:
+# issue_comment:
+  workflow_dispatch:

 permissions:
  issues: write
@ -26,7 +27,9 @@ jobs:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
          PINECONE.API_KEY: ${{ secrets.PINECONE_API_KEY }}
          PINECONE.ENVIRONMENT: ${{ secrets.PINECONE_ENVIRONMENT }}
-          GITHUB_ACTION.AUTO_REVIEW: true
-          GITHUB_ACTION.AUTO_IMPROVE: true
+          GITHUB_ACTION_CONFIG.AUTO_DESCRIBE: true
+          GITHUB_ACTION_CONFIG.AUTO_REVIEW: true
+          GITHUB_ACTION_CONFIG.AUTO_IMPROVE: true
+


--- a/.gitignore
+++ b/.gitignore
@ -6,3 +6,4 @@ dist/
 *.egg-info/
 build/
 review.md
+.DS_Store
--- a/INSTALL.md
+++ b/INSTALL.md
@ -3,8 +3,8 @@

 To get started with PR-Agent quickly, you first need to acquire two tokens:

-1. An OpenAI key from [here](https://platform.openai.com/), with access to GPT-4.
-2. A GitHub\GitLab\BitBucket personal access token (classic) with the repo scope.
+1. An OpenAI key from [here](https://platform.openai.com/api-keys), with access to GPT-4.
+2. A GitHub\GitLab\BitBucket personal access token (classic), with the repo scope. [GitHub from [here](https://github.com/settings/tokens)]

 There are several ways to use PR-Agent:

@ -46,7 +46,7 @@ docker run --rm -it -e OPENAI.KEY=<your key> -e CONFIG.GIT_PROVIDER=gitlab -e GI

 Note: If you have a dedicated GitLab instance, you need to specify the custom url as variable:
 ```
-docker run --rm -it -e OPENAI.KEY=<your key> -e CONFIG.GIT_PROVIDER=gitlab -e GITLAB.PERSONAL_ACCESS_TOKEN=<your token> GITLAB.URL=<your gitlab instance url> codiumai/pr-agent:latest --pr_url <pr_url> review
+docker run --rm -it -e OPENAI.KEY=<your key> -e CONFIG.GIT_PROVIDER=gitlab -e GITLAB.PERSONAL_ACCESS_TOKEN=<your token> -e GITLAB.URL=<your gitlab instance url> codiumai/pr-agent:latest --pr_url <pr_url> review
 ```

 - For BitBucket:
@ -79,12 +79,14 @@ codiumai/pr-agent@v0.9
 git clone https://github.com/Codium-ai/pr-agent.git
 ```

-2. Install the requirements in your favorite virtual environment:
+2. Navigate to the `/pr-agent` folder and install the requirements in your favorite virtual environment:

 ```
-pip install -r requirements.txt
+pip install -e .
 ```

+*Note: If you get an error related to Rust in the dependency installation then make sure Rust is installed and in your `PATH`, instructions: https://rustup.rs*
+
 3. Copy the secrets template file and fill in your OpenAI key and your GitHub user token:

 ```
@ -93,10 +95,9 @@ chmod 600 pr_agent/settings/.secrets.toml
 # Edit .secrets.toml file
 ```

-4. Add the pr_agent folder to your PYTHONPATH, then run the cli.py script:
+4. Run the cli.py script:

 ```
-export PYTHONPATH=[$PYTHONPATH:]<PATH to pr_agent folder>
 python3 -m pr_agent.cli --pr_url <pr_url> review
 python3 -m pr_agent.cli --pr_url <pr_url> ask <your question>
 python3 -m pr_agent.cli --pr_url <pr_url> describe
@ -107,6 +108,11 @@ python3 -m pr_agent.cli --issue_url <issue_url> similar_issue
 ...
 ```

+[Optional] Add the pr_agent folder to your PYTHONPATH
+```
+export PYTHONPATH=$PYTHONPATH:<PATH to pr_agent folder>
+```
+
 ---

 ### Run as a GitHub Action
--- a/README.md
+++ b/README.md
@ -19,9 +19,81 @@ Making pull requests less painful with an AI agent
    <img alt="GitHub" src="https://img.shields.io/github/last-commit/Codium-ai/pr-agent/main?style=for-the-badge" height="20">
    </a>
 </div>
+
+## Table of Contents
+- [News and Updates](#news-and-updates)
+- [Overview](#overview)
+- [Example results](#example-results)
+- [Try it now](#try-it-now)
+- [Installation](#installation)
+- [PR-Agent Pro 💎](#pr-agent-pro-)
+- [How it works](#how-it-works)
+- [Why use PR-Agent?](#why-use-pr-agent)
+  
+## News and Updates
+### Jan 28, 2024
+- 💎 Test - A new tool, [`/test component_name`](https://github.com/Codium-ai/pr-agent/blob/main/docs/TEST.md), was added to PR-Agent Pro. The tool will generate tests for a selected component, based on the PR code changes.
+- 💎 Analyze - The [`/analyze`](https://github.com/Codium-ai/pr-agent/blob/main/docs/Analyze.md) tool was updated and simplified. It now presents a summary of the code components that were changed in the PR.
+### Jan 21, 2024
+- 💎 Custom suggestions - A new tool, `/custom_suggestions`, was added to PR-Agent Pro. The tool will propose only suggestions that follow specific guidelines defined by the user. 
+See [here](https://github.com/Codium-ai/pr-agent/blob/main/docs/CUSTOM_SUGGESTIONS.md) for more details.
+
+### Jan 17, 2024
+- 💎 Inline file summary - The `describe` tool has a new option `--pr_description.inline_file_summary`, which allows to add a summary of each file changes to the Diffview page. See [here](https://github.com/Codium-ai/pr-agent/blob/main/docs/DESCRIBE.md#inline-file-summary-)
+- The `improve` tool can now present suggestions in a nice collapsible format, which significantly reduces the PR footprint. See [here](https://github.com/Codium-ai/pr-agent/blob/main/docs/IMPROVE.md#summarized-vs-commitable-code-suggestions) for more details. 
+- To accompany the improved interface of the  `improve` tool, we change the [default automation settings](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L116) of our GithupApp to:
+```
+pr_commands = [
+    "/describe --pr_description.add_original_user_description=true --pr_description.keep_original_user_title=true",
+    "/review --pr_reviewer.num_code_suggestions=0",
+    "/improve --pr_code_suggestions.summarize=true",
+]
+```
+Meaning that by default, for each PR the `describe`, `review`, and `improve` tools will be triggered automatically, and the `improve` tool will present the suggestions in a single comment.  
+You can of course overwrite these defaults by adding a `.pr_agent.toml` file to your repo. See [here](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#working-with-github-app).
+
+### Jan 10, 2024
+[LanceDB](https://lancedb.com/) is now supported as a locally hosted VectorDB for the `similar_issue` tool. See [here](./docs/SIMILAR_ISSUE.md) for more details.
+
+
+## Overview
 <div style="text-align:left;">

-CodiumAI `PR-Agent` is an open-source tool for efficient pull request reviewing and handling. It automatically analyzes the pull request and can provide several types of commands:
+CodiumAI PR-Agent is an open-source tool to help efficiently review and handle pull requests. It automatically analyzes the pull request and can provide several types of commands:
+
+|       |                                                                                                                                          | GitHub | Gitlab | Bitbucket |
+|-------|------------------------------------------------------------------------------------------------------------------------------------------|:------:|:------:|:---------:|
+| TOOLS | Review                                                                                                                                   |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       |
+|       | ⮑ Incremental                                                                                                                            |   :white_check_mark:    |                         |                            |
+|       | ⮑ [SOC2 Compliance](https://github.com/Codium-ai/pr-agent/blob/main/docs/REVIEW.md#soc2-ticket-compliance-) 💎                           |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |
+|       | Describe                                                                                                                                 |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |
+|       | ⮑ [Inline File Summary](https://github.com/Codium-ai/pr-agent/blob/main/docs/DESCRIBE.md#inline-file-summary-) 💎                        |   :white_check_mark:    |       |          |
+|       | Improve                                                                                                                                  |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |
+|       | ⮑ Extended                                                                                                                               |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |
+|       | Ask                                                                                                                                      |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |
+|       | [Custom Suggestions](https://github.com/Codium-ai/pr-agent/blob/main/docs/CUSTOM_SUGGESTIONS.md) 💎                                      |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |
+|       | [Test](https://github.com/Codium-ai/pr-agent/blob/main/docs/TEST.md) 💎                                                                  |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |
+|       | Reflect and Review                                                                                                                       |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |
+|       | Update CHANGELOG.md                                                                                                                      |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |
+|       | Find Similar Issue                                                                                                                       |   :white_check_mark:    |                         |                             |
+|       | [Add PR Documentation](https://github.com/Codium-ai/pr-agent/blob/main/docs/ADD_DOCUMENTATION.md) 💎                                     |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |
+|       | [Custom Labels](https://github.com/Codium-ai/pr-agent/blob/main/docs/DESCRIBE.md#handle-custom-labels-from-the-repos-labels-page-gem) 💎 |   :white_check_mark:    |   :white_check_mark:    |         |
+|       | [Analyze](https://github.com/Codium-ai/pr-agent/blob/main/docs/Analyze.md) 💎                                                            |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:      |
+|       |                                                                                                                                          |        |        |      |
+| USAGE | CLI                                                                                                                                      |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       |
+|       | App / webhook                                                                                                                            |   :white_check_mark:    |   :white_check_mark:    |  :white_check_mark:     |
+|       | Tagging bot                                                                                                                              |   :white_check_mark:    |        |           | 
+|       | Actions                                                                                                                                  |   :white_check_mark:    |        |  :white_check_mark:         | 
+|       |                                                                                                                                          |        |        |      |
+| CORE  | PR compression                                                                                                                           |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       |
+|       | Repo language prioritization                                                                                                             |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       |
+|       | Adaptive and token-aware<br />file patch fitting                                                                                         |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:     |
+|       | Multiple models support                                                                                                                  |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       | :white_check_mark: |
+|       | [Static code analysis](https://github.com/Codium-ai/pr-agent/blob/main/docs/Analyze.md) 💎                                               |   :white_check_mark:    |   :white_check_mark:     |    :white_check_mark:    |
+|       | [Global configuration](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#global-configuration-file-) 💎                           |   :white_check_mark:    |   :white_check_mark:     |    :white_check_mark:    |
+- 💎 means this feature is available only in [PR-Agent Pro](https://www.codium.ai/pricing/)
+- Support for additional git providers is described in [here](./docs/Full_environments.md)
+___

 ‣ **Auto Description ([`/describe`](./docs/DESCRIBE.md))**: Automatically generating PR description - title, type, summary, code walkthrough and labels.
 \
@ -35,29 +107,47 @@ CodiumAI `PR-Agent` is an open-source tool for efficient pull request reviewing
 \
 ‣ **Find Similar Issue ([`/similar_issue`](./docs/SIMILAR_ISSUE.md))**: Automatically retrieves and presents similar issues.
 \
-‣ **Add Documentation ([`/add_docs`](./docs/ADD_DOCUMENTATION.md))**: Automatically adds documentation to un-documented functions/classes in the PR.
+‣ **Add Documentation 💎  ([`/add_docs`](./docs/ADD_DOCUMENTATION.md))**: Automatically adds documentation to methods/functions/classes that changed in the PR.
 \
-‣ **Generate Custom Labels ([`/generate_labels`](./docs/GENERATE_CUSTOM_LABELS.md))**: Automatically suggests custom labels based on the PR code changes.
+‣ **Generate Custom Labels 💎 ([`/generate_labels`](./docs/GENERATE_CUSTOM_LABELS.md))**: Automatically suggests custom labels based on the PR code changes.
+\
+‣ **Analyze 💎 ([`/analyze`](./docs/Analyze.md))**: Automatically analyzes the PR, and presents changes walkthrough for each component.
+\
+‣ **Custom Suggestions 💎 ([`/custom_suggestions`](./docs/CUSTOM_SUGGESTIONS.md))**: Automatically generates custom suggestions for improving the PR code, based on specific guidelines defined by the user.
+\
+‣ **Generate Tests 💎 ([`/test component_name`](./docs/TEST.md))**: Automatically generates unit tests for a selected component, based on the PR code changes.

 See the [Installation Guide](./INSTALL.md) for instructions on installing and running the tool on different git platforms.

 See the [Usage Guide](./Usage.md) for running the PR-Agent commands via different interfaces, including _CLI_, _online usage_, or by _automatically triggering_ them when a new PR is opened.

-See the [Tools Guide](./docs/TOOLS_GUIDE.md) for detailed description of the different tools (tools are run via the commands).
+See the [Tools Guide](./docs/TOOLS_GUIDE.md) for a detailed description of the different tools (tools are run via the commands).

-<h3>Example results:</h3>
+
+## Example results
 </div>
-<h4><a href="https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1687561986">/describe:</a></h4>
+<h4><a href="https://github.com/Codium-ai/pr-agent/pull/530">/describe</a></h4>
 <div align="center">
 <p float="center">
-<img src="https://www.codium.ai/images/describe-2.gif" width="800">
+<img src="https://www.codium.ai/images/pr_agent/describe_new_short_main.png" width="800">
 </p>
 </div>
+<hr>
+<h4><a href="https://github.com/Codium-ai/pr-agent/pull/472#discussion_r1435819374">/improve</a></h4>

-<h4><a href="https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695021901">/review:</a></h4>
 <div align="center">
 <p float="center">
-<img src="https://www.codium.ai/images/review-2.gif" width="800">
+<kbd>
+<img src="https://www.codium.ai/images/pr_agent/improve_short_main.png" width="768">
+</kbd>
+</p>
+
+</div>
+<hr>
+<h4><a href="https://github.com/Codium-ai/pr-agent/pull/530">/generate_labels</a></h4>
+<div align="center">
+<p float="center">
+<kbd><img src="https://www.codium.ai/images/pr_agent/geneare_custom_labels_main_short.png" width="300"></kbd>
 </p>
 </div>

@ -98,46 +188,11 @@ See the [Tools Guide](./docs/TOOLS_GUIDE.md) for detailed description of the dif
 [//]: # (</div>)
 <div align="left">

-## Table of Contents
- [Overview](#overview)
- [Try it now](#try-it-now)
- [Installation](#installation)
- [How it works](#how-it-works)
- [Why use PR-Agent?](#why-use-pr-agent)
- [Roadmap](#roadmap)
+
 </div>
+<hr>


-## Overview
-`PR-Agent` offers extensive pull request functionalities across various git providers:
-|       |                                             | GitHub | Gitlab | Bitbucket | CodeCommit | Azure DevOps | Gerrit |
-|-------|---------------------------------------------|:------:|:------:|:---------:|:----------:|:----------:|:----------:|
-| TOOLS | Review                                      |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:    |
-|       | ⮑ Incremental                              |   :white_check_mark:    |       |           |       |          |     |
-|       | Ask                                         |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:          |   :white_check_mark:          | :white_check_mark: |  :white_check_mark:    |
-|       | Auto-Description                            |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |   :white_check_mark:    |   :white_check_mark:    | :white_check_mark:    |
-|       | Improve Code                                |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |   :white_check_mark:    |          |    :white_check_mark:    |
-|       | ⮑ Extended                             |   :white_check_mark:    |   :white_check_mark:    |        :white_check_mark:   |   :white_check_mark:    |          | :white_check_mark:    |
-|       | Reflect and Review                          |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |          |   :white_check_mark:    |    :white_check_mark:    |
-|       | Update CHANGELOG.md                         |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |   :white_check_mark:    |          |       |
-|       | Find similar issue                          |   :white_check_mark:    |                         |                             |          |          |       |
-|       | Add Documentation                           |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |   :white_check_mark:    |          |    :white_check_mark:    |
-|       | Generate Labels                           |   :white_check_mark:    |   :white_check_mark:    |         |     |          |      |
-|       |                                             |        |        |      |      |      |
-| USAGE | CLI                                         |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       |   :white_check_mark:    |   :white_check_mark:    |
-|       | App / webhook                               |   :white_check_mark:    |   :white_check_mark:    |           |          |          |
-|       | Tagging bot                                 |   :white_check_mark:    |        |           |          |          |
-|       | Actions                                     |   :white_check_mark:    |        |           |          |          |
-|       | Web server                                  |       |        |           |          |          |  :white_check_mark:   |
-|       |                                             |        |        |      |      |      |
-| CORE  | PR compression                              |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       | :white_check_mark: |   :white_check_mark:       | :white_check_mark:       |
-|       | Repo language prioritization                |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       | :white_check_mark: |   :white_check_mark:       | :white_check_mark:       |
-|       | Adaptive and token-aware<br />file patch fitting |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       | :white_check_mark: |   :white_check_mark:       | :white_check_mark:       |
-|       | Multiple models support |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       | :white_check_mark: |   :white_check_mark:       | :white_check_mark:       |
-|       | Incremental PR Review |   :white_check_mark:    |      |      |      |      |      |
-
-Review the [usage guide](./Usage.md) section for detailed instructions how to use the different tools, select the relevant git provider (GitHub, Gitlab, Bitbucket,...), and adjust the configuration file to your needs.
-
 ## Try it now

 Try the GPT-4 powered PR-Agent instantly on _your public GitHub repository_. Just mention `@CodiumAI-Agent` and add the desired command in any PR comment. The agent will generate a response based on your command.
@ -156,8 +211,7 @@ Note that when you set your own PR-Agent or use CodiumAI hosted PR-Agent, there
 ---

 ## Installation
-
-To get started with PR-Agent quickly, you first need to acquire two tokens:
+To use your own version of PR-Agent, you first need to acquire two tokens:

 1. An OpenAI key from [here](https://platform.openai.com/), with access to GPT-4.
 2. A GitHub personal access token (classic) with the repo scope.
@ -176,6 +230,21 @@ There are several ways to use PR-Agent:
 - [Method 8: Run a GitLab webhook server](INSTALL.md#method-8---run-a-gitlab-webhook-server)
 - [Method 9: Run as a Bitbucket Pipeline](INSTALL.md#method-9-run-as-a-bitbucket-pipeline)

+## PR-Agent Pro 💎
+[PR-Agent Pro](https://www.codium.ai/pricing/) is a hosted version of PR-Agent, provided by CodiumAI. It is available for a monthly fee, and provides the following benefits:
+1. **Fully managed** - We take care of everything for you - hosting, models, regular updates, and more. Installation is as simple as signing up and adding the PR-Agent app to your GitHub\BitBucket repo.
+2. **Improved privacy** - No data will be stored or used to train models. PR-Agent Pro will employ zero data retention, and will use an OpenAI account with zero data retention.
+3. **Improved support** - PR-Agent Pro users will receive priority support, and will be able to request new features and capabilities.
+4. **Extra features** -In addition to the benefits listed above, PR-Agent Pro will emphasize more customization, and the usage of static code analysis, in addition to LLM logic, to improve results. It has the following additional features:
+    - [**SOC2 compliance check**](https://github.com/Codium-ai/pr-agent/blob/main/docs/REVIEW.md#soc2-ticket-compliance-)
+    - [**PR documentation**](https://github.com/Codium-ai/pr-agent/blob/main/docs/ADD_DOCUMENTATION.md)
+    - [**Custom labels**](https://github.com/Codium-ai/pr-agent/blob/main/docs/DESCRIBE.md#handle-custom-labels-from-the-repos-labels-page-gem)
+    - [**Global configuration**](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#global-configuration-file-)
+    - [**Analyze PR components**](https://github.com/Codium-ai/pr-agent/blob/main/docs/Analyze.md)
+    - **Custom Code Suggestions** [WIP]
+    - **Chat on Specific Code Lines** [WIP]
+
+
 ## How it works

 The following diagram illustrates PR-Agent tools and their flow:
@ -186,50 +255,22 @@ Check out the [PR Compression strategy](./PR_COMPRESSION.md) page for more detai

 ## Why use PR-Agent?

-A reasonable question that can be asked is: `"Why use PR-Agent? What make it stand out from existing tools?"`
+A reasonable question that can be asked is: `"Why use PR-Agent? What makes it stand out from existing tools?"`

 Here are some advantages of PR-Agent:

 - We emphasize **real-life practical usage**. Each tool (review, improve, ask, ...) has a single GPT-4 call, no more. We feel that this is critical for realistic team usage - obtaining an answer quickly (~30 seconds) and affordably.
 - Our [PR Compression strategy](./PR_COMPRESSION.md)  is a core ability that enables to effectively tackle both short and long PRs.
 - Our JSON prompting strategy enables to have **modular, customizable tools**. For example, the '/review' tool categories can be controlled via the [configuration](pr_agent/settings/configuration.toml) file. Adding additional categories is easy and accessible.
- We support **multiple git providers** (GitHub, Gitlab, Bitbucket, CodeCommit), **multiple ways** to use the tool (CLI, GitHub Action, GitHub App, Docker, ...), and **multiple models** (GPT-4, GPT-3.5, Anthropic, Cohere, Llama2).
- We are open-source, and welcome contributions from the community.
+- We support **multiple git providers** (GitHub, Gitlab, Bitbucket), **multiple ways** to use the tool (CLI, GitHub Action, GitHub App, Docker, ...), and **multiple models** (GPT-4, GPT-3.5, Anthropic, Cohere, Llama2).


-## Roadmap
+## Data privacy

- [x] Support additional models, as a replacement for OpenAI (see [here](https://github.com/Codium-ai/pr-agent/pull/172))
- [x] Develop additional logic for handling large PRs (see [here](https://github.com/Codium-ai/pr-agent/pull/229))
- [ ] Add additional context to the prompt. For example, repo (or relevant files) summarization, with tools such a [ctags](https://github.com/universal-ctags/ctags)
- [x] PR-Agent for issues
- [ ] Adding more tools. Possible directions:
-  - [x] PR description
-  - [x] Inline code suggestions
-  - [x] Reflect and review
-  - [x] Rank the PR (see [here](https://github.com/Codium-ai/pr-agent/pull/89))   
-  - [ ] Enforcing CONTRIBUTING.md guidelines
-  - [ ] Performance (are there any performance issues)
-  - [x] Documentation (is the PR properly documented)
-  - [ ] ...
-
-See the [Release notes](./RELEASE_NOTES.md) for updates on the latest changes.
-
-
-## Similar Projects
-
- [CodiumAI - Meaningful tests for busy devs](https://github.com/Codium-ai/codiumai-vscode-release) (although various capabilities are much more advanced in the CodiumAI IDE plugins)
- [Aider - GPT powered coding in your terminal](https://github.com/paul-gauthier/aider)
- [openai-pr-reviewer](https://github.com/coderabbitai/openai-pr-reviewer)
- [CodeReview BOT](https://github.com/anc95/ChatGPT-CodeReview)
- [AI-Maintainer](https://github.com/merwanehamadi/AI-Maintainer)
-
-## Data Privacy
-
-If you use a self-hosted PR-Agent with your OpenAI API key, it is between you and OpenAI. You can read their API data privacy policy here:
+If you host PR-Agent with your OpenAI API key, it is between you and OpenAI. You can read their API data privacy policy here:
 https://openai.com/enterprise-privacy

-When using a PR-Agent app hosted by CodiumAI, we will not store any of your data, nor will we used it for training.
+When using PR-Agent Pro 💎, hosted by CodiumAI, we will not store any of your data, nor will we use it for training.
 You will also benefit from an OpenAI account with zero data retention.

 ## Links
--- a/Usage.md
+++ b/Usage.md
@ -2,14 +2,12 @@

 ### Table of Contents
 - [Introduction](#introduction)
- [Working from a local repo (CLI)](#working-from-a-local-repo-cli)
- [Online usage](#online-usage)
- [Working with GitHub App](#working-with-github-app)
- [Working with GitHub Action](#working-with-github-action)
- [Working with BitBucket App](#working-with-bitbucket-self-hosted-app)
- [Changing a model](#changing-a-model)
- [Working with large PRs](#working-with-large-prs)
- [Appendix - additional configurations walkthrough](#appendix---additional-configurations-walkthrough)
+- [Local Repo (CLI)](#working-from-a-local-repo-cli)
+- [Online Usage](#online-usage)
+- [GitHub App](#working-with-github-app)
+- [GitHub Action](#working-with-github-action)
+- [BitBucket App](#working-with-bitbucket-self-hosted-app)
+- [Additional Configurations Walkthrough](#appendix---additional-configurations-walkthrough)

 ### Introduction

@ -25,10 +23,36 @@ GitHub App and GitHub Action also enable to run PR-Agent specific tool automatic


 #### The configuration file
-The different tools and sub-tools used by CodiumAI PR-Agent are adjustable via the **[configuration file](pr_agent/settings/configuration.toml)**.
+- The different tools and sub-tools used by CodiumAI PR-Agent are adjustable via the **[configuration file](pr_agent/settings/configuration.toml)**.
 In addition to general configuration options, each tool has its own configurations. For example, the `review` tool will use parameters from the [pr_reviewer](/pr_agent/settings/configuration.toml#L16) section in the configuration file.

-The [Tools Guide](./docs/TOOLS_GUIDE.md) provides a detailed description of the different tools and their configurations.
+- The [Tools Guide](./docs/TOOLS_GUIDE.md) provides a detailed description of the different tools and their configurations.
+
+
+- By uploading a local `.pr_agent.toml` file to the root of the repo's main branch, you can edit and customize any configuration parameter. Note that you need to upload `.pr_agent.toml` prior to creating a PR, in order for the configuration to take effect.
+
+For example, if you set in `.pr_agent.toml`:
+
+```
+[pr_reviewer]
+extra_instructions="""\
+- instruction a
+- instruction b
+...
+"""
+```
+
+Then you can give a list of extra instructions to the `review` tool.
+
+
+#### Global configuration file 💎
+
+If you create a repo called `pr-agent-settings` in your **organization**, it's configuration file `.pr_agent.toml` will be used as a global configuration file for any other repo that belongs to the same organization.
+Parameters from a local `.pr_agent.toml` file, in a specific repo, will override the global configuration parameters.
+
+For example, in the GitHub organization `Codium-ai`:
+- The repo [`https://github.com/Codium-ai/pr-agent-settings`](https://github.com/Codium-ai/pr-agent-settings/blob/main/.pr_agent.toml) contains a `.pr_agent.toml` file that serves as a global configuration file for all the repos in the GitHub organization `Codium-ai`.
+- The repo [`https://github.com/Codium-ai/pr-agent`](https://github.com/Codium-ai/pr-agent/blob/main/.pr_agent.toml) inherits the global configuration file from `pr-agent-settings`.

 #### Ignoring files from analysis
 In some cases, you may want to exclude specific files or directories from the analysis performed by CodiumAI PR-Agent. This can be useful, for example, when you have files that are generated automatically or files that shouldn't be reviewed, like vendored code.
@ -53,18 +77,6 @@ The [git_provider](pr_agent/settings/configuration.toml#L4) field in the configu
 "github", "gitlab", "azure", "codecommit", "local", "gerrit"
 `

-[//]: # (** online usage:**)
-
-[//]: # (Options that are available in the configuration file can be specified at run time when calling actions. Two examples:)
-
-[//]: # (```)
-
-[//]: # (- /review --pr_reviewer.extra_instructions="focus on the file: ...")
-
-[//]: # (- /describe --pr_description.add_original_user_description=false -pr_description.extra_instructions="make sure to mention: ...")
-
-[//]: # (```)
-
 ### Working from a local repo (CLI)
 When running from your local repo (CLI), your local configuration file will be used.
 Examples of invoking the different tools via the CLI:
@ -130,28 +142,20 @@ num_code_suggestions=1
 Then you will overwrite the default number of code suggestions to 1.

 #### GitHub app automatic tools
-The [github_app](pr_agent/settings/configuration.toml#L76) section defines GitHub app-specific configurations.  
-In this section you can define configurations to control the conditions for which tools will **run automatically**.  
+The [github_app](pr_agent/settings/configuration.toml#L108) section defines GitHub app specific configurations.  

 ##### GitHub app automatic tools for PR actions 
-The GitHub app can respond to the following actions on a PR:
-1. `opened` - Opening a new PR
-2. `reopened` - Reopening a closed PR
-3. `ready_for_review` - Moving a PR from Draft to Open
-4. `review_requested` - Specifically requesting review (in the PR reviewers list) from the `github-actions[bot]` user
-
-The configuration parameter `handle_pr_actions` defines the list of actions for which the GitHub app will trigger the PR-Agent.  
-The configuration parameter `pr_commands` defines the list of tools that will be **run automatically** when one of the above actions happens (e.g., a new PR is opened):
+The configuration parameter `pr_commands` defines the list of tools that will be **run automatically** when a new PR is opened.
 ```
 [github_app]
-handle_pr_actions = ['opened', 'reopened', 'ready_for_review', 'review_requested']
 pr_commands = [
    "/describe --pr_description.add_original_user_description=true --pr_description.keep_original_user_title=true",
-    "/auto_review",
+    "/review --pr_reviewer.num_code_suggestions=0",
+    "/improve",
 ]
 ```
-This means that when a new PR is opened/reopened or marked as ready for review, PR-Agent will run the `describe` and `auto_review` tools.  
-For the describe tool, the `add_original_user_description` and `keep_original_user_title` parameters will be set to true.
+This means that when a new PR is opened/reopened or marked as ready for review, PR-Agent will run the `describe`, `review` and `improve` tools.  
+For the `describe` tool, for example, the `add_original_user_description` and `keep_original_user_title` parameters will be set to true.

 You can override the default tool parameters by uploading a local configuration file called `.pr_agent.toml` to the root of your repo.
 For example, if your local `.pr_agent.toml` file contains:
@ -168,7 +172,7 @@ To cancel the automatic run of all the tools, set:
 handle_pr_actions = []
 ```

-##### GitHub app automatic tools for new code (PR push)
+##### GitHub app automatic tools for push actions (commits to an open PR)
 In addition to running automatic tools when a PR is opened, the GitHub app can also respond to new code that is pushed to an open PR.

 The configuration toggle `handle_push_trigger` can be used to enable this feature.  
@ -178,12 +182,12 @@ The configuration parameter `push_commands` defines the list of tools that will
 handle_push_trigger = true
 push_commands = [
    "/describe --pr_description.add_original_user_description=true --pr_description.keep_original_user_title=true",
-    "/auto_review -i --pr_reviewer.remove_previous_review_comment=true",
+    "/review -i --pr_reviewer.remove_previous_review_comment=true",
 ]
 ```
-This means that when new code is pushed to the PR, the PR-Agent will run the `describe` and incremental `auto_review` tools.  
-For the describe tool, the `add_original_user_description` and `keep_original_user_title` parameters will be set to true.  
-For the `auto_review` tool, it will run in incremental mode, and the `remove_previous_review_comment` parameter will be set to true.
+This means that when new code is pushed to the PR, the PR-Agent will run the `describe` and incremental `review` tools.  
+For the `describe` tool, the `add_original_user_description` and `keep_original_user_title` parameters will be set to true.  
+For the `review` tool, it will run in incremental mode, and the `remove_previous_review_comment` parameter will be set to true.

 Much like the configurations for `pr_commands`, you can override the default tool parameters by uploading a local configuration file to the root of your repo.

@ -205,18 +209,19 @@ user="""
 Note that the new prompt will need to generate an output compatible with the relevant [post-process function](./pr_agent/tools/pr_description.py#L137).

 ### Working with GitHub Action
-You can configure settings in GitHub action by adding environment variables under the env section in `.github/workflows/pr_agent.yml` file. 
+`GitHub Action` is a different way to trigger PR-Agent tools, and uses a different configuration mechanism than `GitHub App`.
+You can configure settings for `GitHub Action` by adding environment variables under the env section in `.github/workflows/pr_agent.yml` file. 
 Specifically, start by setting the following environment variables:
 ```yaml
      env:
        OPENAI_KEY: ${{ secrets.OPENAI_KEY }} # Make sure to add your OpenAI key to your repo secrets
        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # Make sure to add your GitHub token to your repo secrets
-        github_action.auto_review: "true" # enable\disable auto review
-        github_action.auto_describe: "true" # enable\disable auto describe
-        github_action.auto_improve: "false" # enable\disable auto improve
+        github_action_config.auto_review: "true" # enable\disable auto review
+        github_action_config.auto_describe: "true" # enable\disable auto describe
+        github_action_config.auto_improve: "true" # enable\disable auto improve
 ```
-`github_action.auto_review`, `github_action.auto_describe` and `github_action.auto_improve` are used to enable/disable automatic tools that run when a new PR is opened.
-If not set, the default option is that only the `review` tool will run automatically when a new PR is opened.
+`github_action_config.auto_review`, `github_action_config.auto_describe` and `github_action_config.auto_improve` are used to enable/disable automatic tools that run when a new PR is opened.
+If not set, the default configuration is for all three tools to run automatically when a new PR is opened.

 Note that you can give additional config parameters by adding environment variables to `.github/workflows/pr_agent.yml`, or by using a `.pr_agent.toml` file in the root of your repo, similar to the GitHub App usage.

@ -256,13 +261,34 @@ If not set, the default option is that only the `review` tool will run automatic
 Note that due to limitations of the bitbucket platform, the `auto_describe` tool will be able to publish a PR description only as a comment. 
 In addition, some subsections like `PR changes walkthrough` will not appear, since they require the usage of collapsible sections, which are not supported by bitbucket.

-### Changing a model
+### Appendix - additional configurations walkthrough
+
+
+#### Extra instructions
+All PR-Agent tools have a parameter called `extra_instructions`, that enables to add free-text extra instructions. Example usage:
+```
+/update_changelog --pr_update_changelog.extra_instructions="Make sure to update also the version ..."
+```
+
+#### Working with large PRs
+
+The default mode of CodiumAI is to have a single call per tool, using GPT-4, which has a token limit of 8000 tokens.
+This mode provide a very good speed-quality-cost tradeoff, and can handle most PRs successfully.
+When the PR is above the token limit, it employs a [PR Compression strategy](./PR_COMPRESSION.md).
+
+However, for very large PRs, or in case you want to emphasize quality over speed and cost, there are 2 possible solutions:
+1) [Use a model](#changing-a-model) with larger context, like GPT-32K, or claude-100K. This solution will be applicable for all the tools.
+2) For the `/improve` tool, there is an ['extended' mode](./docs/IMPROVE.md) (`/improve --extended`),
+which divides the PR to chunks, and process each chunk separately. With this mode, regardless of the model, no compression will be done (but for large PRs, multiple model calls may occur)
+
+
+#### Changing a model

 See [here](pr_agent/algo/__init__.py) for the list of available models.
 To use a different model than the default (GPT-4), you need to edit [configuration file](pr_agent/settings/configuration.toml#L2).
 For models and environments not from OPENAI, you might need to provide additional keys and other parameters. See below for instructions.

-#### Azure
+##### Azure
 To use Azure, set in your `.secrets.toml` (working from CLI), or in the GitHub `Settings > Secrets and variables` (working from GitHub App or GitHub Action):
 ```
 api_key = "" # your azure api key
@ -278,7 +304,7 @@ and set in your configuration file:
 model="" # the OpenAI model you've deployed on Azure (e.g. gpt-3.5-turbo)
 ```

-#### Huggingface
+##### Huggingface

 **Local**
 You can run Huggingface models locally through either [VLLM](https://docs.litellm.ai/docs/providers/vllm) or [Ollama](https://docs.litellm.ai/docs/providers/ollama)
@ -327,7 +353,7 @@ api_base = ... # the base url for your huggingface inference endpoint
 ```
 (you can obtain a Llama2 key from [here](https://replicate.com/replicate/llama-2-70b-chat/api))

-#### Replicate
+##### Replicate

 To use Llama2 model with Replicate, for example, set:
 ```
@ -341,7 +367,7 @@ key = ...

 Also review the [AiHandler](pr_agent/algo/ai_handler.py) file for instruction how to set keys for other models.

-#### Vertex AI
+##### Vertex AI

 To use Google's Vertex AI platform and its associated models (chat-bison/codechat-bison) set:

@ -359,7 +385,7 @@ Your [application default credentials](https://cloud.google.com/docs/authenticat

 If you do want to set explicit credentials then you can use the `GOOGLE_APPLICATION_CREDENTIALS` environment variable set to a path to a json credentials file.

-#### Amazon Bedrock
+##### Amazon Bedrock

 To use Amazon Bedrock and its foundational models, add the below configuration:

@ -376,25 +402,6 @@ Note that you have to add access to foundational models before using them. Pleas

 AWS session is automatically authenticated from your environment, but you can also explicitly set `AWS_ACCESS_KEY_ID` and `AWS_SECRET_ACCESS_KEY` environment variables.

-### Working with large PRs
-
-The default mode of CodiumAI is to have a single call per tool, using GPT-4, which has a token limit of 8000 tokens.
-This mode provide a very good speed-quality-cost tradeoff, and can handle most PRs successfully.
-When the PR is above the token limit, it employs a [PR Compression strategy](./PR_COMPRESSION.md).
-
-However, for very large PRs, or in case you want to emphasize quality over speed and cost, there are 2 possible solutions:
-1) [Use a model](#changing-a-model) with larger context, like GPT-32K, or claude-100K. This solution will be applicable for all the tools.
-2) For the `/improve` tool, there is an ['extended' mode](./docs/IMPROVE.md) (`/improve --extended`),
-which divides the PR to chunks, and process each chunk separately. With this mode, regardless of the model, no compression will be done (but for large PRs, multiple model calls may occur)
-
-### Appendix - additional configurations walkthrough
-
-
-#### Extra instructions
-All PR-Agent tools have a parameter called `extra_instructions`, that enables to add free-text extra instructions. Example usage:
-```
-/update_changelog --pr_update_changelog.extra_instructions="Make sure to update also the version ..."
-```

 #### Patch Extra Lines
 By default, around any change in your PR, git patch provides 3 lines of context above and below the change.
--- a/docs/ADD_DOCUMENTATION.md
+++ b/docs/ADD_DOCUMENTATION.md
@ -1,5 +1,5 @@
-# Add Documentation Tool
-The `add_docs` tool scans the PR code changes, and automatically suggests documentation for the undocumented code components (functions, classes, etc.).
+# Add Documentation Tool 💎
+The `add_docs` tool scans the PR code changes, and automatically suggests documentation for any code components that changed in the PR (functions, classes, etc.).

 It can be invoked manually by commenting on any PR:
 ```
@ -7,9 +7,18 @@ It can be invoked manually by commenting on any PR:
 ```
 For example:

-<kbd><img src=https://codium.ai/images/pr_agent/add_docs_comment.png width="768"></kbd>
-<kbd><img src=https://codium.ai/images/pr_agent/add_docs.png width="768"></kbd>
+<kbd><img src=https://codium.ai/images/pr_agent/docs_command.png width="768"></kbd>
+___
+<kbd><img src=https://codium.ai/images/pr_agent/docs_components.png width="768"></kbd>
+___
+<kbd><img src=https://codium.ai/images/pr_agent/docs_single_component.png width="768"></kbd>

 ### Configuration options
 - `docs_style`: The exact style of the documentation (for python docstring). you can choose between: `google`, `numpy`, `sphinx`, `restructuredtext`, `plain`. Default is `sphinx`.
 - `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".
+
+Notes 
+- Language that are currently fully supported: Python, Java, C++, JavaScript, TypeScript.
+- For languages that are not fully supported, the tool will suggest documentation only for new components in the PR.
+- A previous version of the tool, that offered support only for new components, was deprecated.
+
--- a/docs/ASK.md
+++ b/docs/ASK.md
@ -1,11 +1,15 @@
 # ASK Tool

-The `ask` tool answers questions about the PR, based on the PR code changes.
+The `ask` tool answers questions about the PR, based on the PR code changes. Make sure to be specific and clear in your questions.
 It can be invoked manually by commenting on any PR:
 ```
 /ask "..."
 ```
 For example:
-
+___
 <kbd><img src=https://codium.ai/images/pr_agent/ask_comment.png width="768"></kbd>
+___
 <kbd><img src=https://codium.ai/images/pr_agent/ask.png width="768"></kbd>
+___
+
+Note that the tool does not have "memory" of previous questions, and answers each question independently.
--- a/docs/Analyze.md
+++ b/docs/Analyze.md
@ -0,0 +1,21 @@
+# Analyze Tool 💎
+The `analyze` tool combines static code analysis with LLM capabilities to provide a comprehensive analysis of the PR code changes.
+
+The tool scans the PR code changes, find the code components (methods, functions, classes) that changed, and summarizes the changes in each component.
+
+It can be invoked manually by commenting on any PR:
+```
+/analyze
+```
+
+An example [result](https://github.com/Codium-ai/pr-agent/pull/546#issuecomment-1868524805):
+
+<kbd><img src=https://codium.ai/images/pr_agent/analyze_1.png width="768"></kbd>
+___
+<kbd><img src=https://codium.ai/images/pr_agent/analyze_2.png width="768"></kbd>
+___
+<kbd><img src=https://codium.ai/images/pr_agent/analyze_3.png width="768"></kbd>
+
+
+Notes 
+- Language that are currently supported: Python, Java, C++, JavaScript, TypeScript.
--- a/docs/CUSTOM_SUGGESTIONS.md
+++ b/docs/CUSTOM_SUGGESTIONS.md
@ -0,0 +1,65 @@
+# Custom Suggestions Tool 💎
+
+## Table of Contents
+- [Overview](#overview)
+- [Example usage](#example-usage)
+- [Configuration options](#configuration-options)
+
+
+## Overview
+The `custom_suggestions` tool scans the PR code changes, and automatically generates custom suggestions for improving the PR code.
+It shares similarities with the `improve` tool, but with one main difference: the `custom_suggestions` tool will only propose suggestions that follow specific guidelines defined by the prompt in: `pr_custom_suggestions.prompt` configuration.
+
+The tool can be triggered [automatically](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools) every time a new PR is opened, or can be invoked manually by commenting on a PR.
+
+When commenting, use the following template:
+
+```
+/custom_suggestions --pr_custom_suggestions.prompt="The suggestions should focus only on the following:\n-...\n-...\n-..."
+```
+
+With a [configuration file](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#working-with-github-app), use the following template:
+
+```
+[pr_custom_suggestions]
+prompt="""\
+The suggestions should focus only on the following:
+-...
+-...
+-...
+"""
+```
+Using a configuration file is recommended, since it allows to use multi-line instructions.
+
+Don't forget - with this tool, you are the prompter. Be specific, clear, and concise in the instructions. Specify relevant aspects that you want the model to focus on. \
+You might benefit from several trial-and-error iterations, until you get the correct prompt for your use case.
+
+## Example usage
+
+Here is an example of a possible prompt:
+```
+[pr_custom_suggestions]
+prompt="""\
+The suggestions should focus only on the following:
+- look for edge cases when implementing a new function
+- make sure every variable has a meaningful name
+- make sure the code is efficient
+"""
+```     
+
+The instructions above are just an example. We want to emphasize that the prompt should be specific and clear, and be tailored to the needs of your project.
+
+Results obtained with the prompt above:
+___
+<kbd><img src=https://codium.ai/images/pr_agent/custom_suggestions_prompt.png width="512"></kbd>
+___
+<kbd><img src=https://codium.ai/images/pr_agent/custom_suggestions_result.png width="768"></kbd>
+___
+
+## Configuration options
+
+`prompt`: the prompt for the tool. It should be a multi-line string.
+
+`num_code_suggestions`: number of code suggestions provided by the 'custom_suggestions' tool. Default is 4.
+
+`enable_help_text`: if set to true, the tool will display a help text in the comment. Default is true.
--- a/docs/DESCRIBE.md
+++ b/docs/DESCRIBE.md
@ -1,22 +1,35 @@
 # Describe Tool
+## Table of Contents
+- [Overview](#overview)
+  - [Configuration options](#configuration-options)
+  - [Inline file summary 💎](#inline-file-summary-)
+  - [Handle custom labels from the Repo's labels page :gem:](#handle-custom-labels-from-the-repos-labels-page-gem)
+  - [Markers template](#markers-template)
+- [Usage Tips](#usage-tips)
+  - [Automation](#automation)
+  - [Custom labels](#custom-labels)

-The `describe` tool scans the PR code changes, and automatically generates PR description - title, type, summary, walkthrough and labels.
-It can be invoked manually by commenting on any PR:
+## Overview
+The `describe` tool scans the PR code changes, and generates a description for the PR - title, type, summary, walkthrough and labels.
+
+The tool can be triggered automatically every time a new PR is [opened](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools), or it can be invoked manually by commenting on any PR:
 ```
 /describe
 ```
 For example:
-
+___
 <kbd><img src=https://codium.ai/images/pr_agent/describe_comment.png width="768"></kbd>
-
-<kbd><img src=https://codium.ai/images/pr_agent/describe.png width="768"></kbd>
-
-The `describe` tool can also be triggered automatically every time a new PR is opened. See examples for automatic triggers for [GitHub App](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools) and [GitHub Action](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#working-with-github-action)
+___
+<kbd><img src=https://codium.ai/images/pr_agent/describe_new.png width="768"></kbd>
+___
  
 ### Configuration options
+To edit [configurations](./../pr_agent/settings/configuration.toml#L46) related to the describe tool (`pr_description` section), use the following template:
+```
+/describe --pr_description.some_config1=... --pr_description.some_config2=...
+```

-Under the section 'pr_description', the [configuration file](./../pr_agent/settings/configuration.toml#L28) contains options to customize the 'describe' tool:
-
+**Possible configurations:**
 - `publish_labels`: if set to true, the tool will publish the labels to the PR. Default is true.

 - `publish_description_as_comment`: if set to true, the tool will publish the description as a comment to the PR. If false, it will overwrite the origianl description. Default is false.
@ -33,16 +46,49 @@ Under the section 'pr_description', the [configuration file](./../pr_agent/setti

 - `final_update_message`: if set to true, it will add a comment message [`PR Description updated to latest commit...`](https://github.com/Codium-ai/pr-agent/pull/499#issuecomment-1837412176) after finishing calling `/describe`. Default is true.

- `enable_semantic_files_types`: if set to true, "PR changes walkthrough" section will be generated. Default is true.
+- `enable_semantic_files_types`: if set to true, "Changes walkthrough" section will be generated. Default is true.
+- `collapsible_file_list`: if set to true, the file list in the "Changes walkthrough" section will be collapsible. If set to "adaptive", the file list will be collapsible only if there are more than 8 files. Default is "adaptive".
+  
+### Inline file summary 💎
+> This feature is available only in PR-Agent Pro
+
+This will enable you to quickly understand the changes in each file, while reviewing the code changes (diff view).
+To enable inline file summary, set `pr_description.inline_file_summary` in the configuration file, possible values are:
+- `'table'`: File changes walkthrough table will be displayed on the top of the "Files changed" tab, in addition to the "Conversation" tab.
+<kbd><img src=https://codium.ai/images/pr_agent/diffview-table.png width="1024"></kbd>
+- `true`: A collapsable file comment with changes title and a changes summary for each file in the PR.
+<kbd><img src=https://codium.ai/images/pr_agent/diffview_changes.png width="1024"></kbd>
+- `false` (`default`): File changes walkthrough will be added only to the "Conversation" tab.
+
+*Note that this feature is currently available only for GitHub.
+
+
+### Handle custom labels from the Repo's labels page :gem:
+> This feature is available only in PR-Agent Pro 
+
+You can control  the custom labels that will be suggested by the `describe` tool, from the repo's labels page:
+
+* GitHub : go to `https://github.com/{owner}/{repo}/labels` (or click on the "Labels" tab in the issues or PRs page)
+* GitLab : go to `https://gitlab.com/{owner}/{repo}/-/labels` (or click on "Manage" -> "Labels" on the left menu)
+
+Now add/edit the custom labels. they should be formatted as follows:
+* Label name: The name of the custom label.
+* Description: Start the description of with prefix `pr_agent:`, for example: `pr_agent: Description of when AI should suggest this label`.<br>
+
+The description should be comprehensive and detailed, indicating when to add the desired label. For example:
+<kbd><img src=https://codium.ai/images/pr_agent/add_native_custom_labels.png width="880"></kbd>
+

 ### Markers template
-
+To enable markers, set `pr_description.use_description_markers=true`.
 markers enable to easily integrate user's content and auto-generated content, with a template-like mechanism.

 For example, if the PR original description was:
 ```
 User content...

+## PR Type:
+pr_agent:type

 ## PR Description:
 pr_agent:summary
@ -50,13 +96,7 @@ pr_agent:summary
 ## PR Walkthrough:
 pr_agent:walkthrough
 ```
-The marker `pr_agent:summary` will be replaced with the PR summary, and `pr_agent:walkthrough` will be replaced with the PR walkthrough.
-
-##### Example:
-```
-        env:
-          pr_description.use_description_markers: 'true'
-```          
+The marker `pr_agent:type` will be replaced with the PR type, `pr_agent:summary` will be replaced with the PR summary, and `pr_agent:walkthrough` will be replaced with the PR walkthrough.

 <kbd><img src=https://codium.ai/images/pr_agent/describe_markers_before.png width="768"></kbd>

@ -64,7 +104,52 @@ The marker `pr_agent:summary` will be replaced with the PR summary, and `pr_agen

 <kbd><img src=https://codium.ai/images/pr_agent/describe_markers_after.png width="768"></kbd>

-##### Configuration params:
+**Configuration params:**

 - `use_description_markers`: if set to true, the tool will use markers template. It replaces every marker of the form `pr_agent:marker_name` with the relevant content. Default is false.
 - `include_generated_by_header`: if set to true, the tool will add a dedicated header: 'Generated by PR Agent at ...' to any automatic content. Default is true.
+
+
+## Usage Tips
+1)  [Automation](#automation)
+2) [Custom labels](#custom-labels)
+### Automation
+- When you first install the app, the [default mode](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools) for the describe tool is:
+```
+pr_commands = ["/describe --pr_description.add_original_user_description=true" 
+                         "--pr_description.keep_original_user_title=true", ...]
+```
+meaning the `describe` tool will run automatically on every PR, will keep the original title, and will add the original user description above the generated description. 
+<br> This default settings aim to strike a good balance between automation and control:
+If you want more automation, just give the PR a title, and the tool will auto-write a full description; If you want more control, you can add a detailed description, and the tool will add the complementary description below it.
+- For maximal automation, you can change the default mode to:
+```
+pr_commands = ["/describe --pr_description.add_original_user_description=false" 
+                         "--pr_description.keep_original_user_title=true", ...]
+```
+so the title will be auto-generated as well.
+- Markers are an alternative way to control the generated description, to give maximal control to the user. If you set:
+```
+pr_commands = ["/describe --pr_description.use_description_markers=true", ...]
+```
+the tool will replace every marker of the form `pr_agent:marker_name` in the PR description with the relevant content, where `marker_name` is one of the following:
+  - `type`: the PR type.
+  - `summary`: the PR summary.
+  - `walkthrough`: the PR walkthrough.
+
+Note that when markers are enabled, if the original PR description does not contain any markers, the tool will not alter the description at all.
+
+### Custom labels
+The default labels of the describe tool are quite generic, since they are meant to be used in any repo: [`Bug fix`, `Tests`, `Enhancement`, `Documentation`, `Other`].
+
+If you specify [custom labels](#handle-custom-labels-from-the-repos-labels-page-gem) in the repo's labels page, you can get tailored labels for your use cases.
+Examples for custom labels:
+- `Main topic:performance` -  pr_agent:The main topic of this PR is performance
+- `New endpoint` -  pr_agent:A new endpoint was added in this PR
+- `SQL query` -  pr_agent:A new SQL query was added in this PR
+- `Dockerfile changes` - pr_agent:The PR contains changes in the Dockerfile
+- ...
+
+The list above is eclectic, and aims to give an idea of different possibilities. Define custom labels that are relevant for your repo and use cases.
+Note that Labels are not mutually exclusive, so you can add multiple label categories.
+<br>Make sure to provide proper title, and a detailed and well-phrased description for each label, so the tool will know when to suggest it.
--- a/docs/Full_environments.md
+++ b/docs/Full_environments.md
@ -0,0 +1,27 @@
+## Overview
+`PR-Agent` offers extensive pull request functionalities across various git providers:
+|       |                                             | GitHub | Gitlab | Bitbucket | CodeCommit | Azure DevOps | Gerrit |
+|-------|---------------------------------------------|:------:|:------:|:---------:|:----------:|:----------:|:----------:|
+| TOOLS | Review                                      |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:    |
+|       | ⮑ Incremental                              |   :white_check_mark:    |       |           |       |          |     |
+|       | Ask                                         |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:          |   :white_check_mark:          | :white_check_mark: |  :white_check_mark:    |
+|       | Auto-Description                            |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |   :white_check_mark:    |   :white_check_mark:    | :white_check_mark:    |
+|       | Improve Code                                |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |   :white_check_mark:    |          |    :white_check_mark:    |
+|       | ⮑ Extended                             |   :white_check_mark:    |   :white_check_mark:    |        :white_check_mark:   |   :white_check_mark:    |          | :white_check_mark:    |
+|       | Reflect and Review                          |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |          |   :white_check_mark:    |    :white_check_mark:    |
+|       | Update CHANGELOG.md                         |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |   :white_check_mark:    |          |       |
+|       | Find similar issue                          |   :white_check_mark:    |                         |                             |          |          |       |
+|       | Add Documentation                           |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |   :white_check_mark:    |          |    :white_check_mark:    |
+|       | Generate Custom Labels 💎                   |   :white_check_mark:    |   :white_check_mark:    |         |     |          |      |
+|       |                                             |        |        |      |      |      |
+| USAGE | CLI                                         |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       |   :white_check_mark:    |   :white_check_mark:    |
+|       | App / webhook                               |   :white_check_mark:    |   :white_check_mark:    |           |          |          |
+|       | Tagging bot                                 |   :white_check_mark:    |        |           |          |          |
+|       | Actions                                     |   :white_check_mark:    |        |           |          |          |
+|       | Web server                                  |       |        |           |          |          |  :white_check_mark:   |
+|       |                                             |        |        |      |      |      |
+| CORE  | PR compression                              |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       | :white_check_mark: |   :white_check_mark:       | :white_check_mark:       |
+|       | Repo language prioritization                |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       | :white_check_mark: |   :white_check_mark:       | :white_check_mark:       |
+|       | Adaptive and token-aware<br />file patch fitting |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       | :white_check_mark: |   :white_check_mark:       | :white_check_mark:       |
+|       | Multiple models support |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       | :white_check_mark: |   :white_check_mark:       | :white_check_mark:       |
+|       | Incremental PR Review |   :white_check_mark:    |      |      |      |      |      |
--- a/docs/GENERATE_CUSTOM_LABELS.md
+++ b/docs/GENERATE_CUSTOM_LABELS.md
@ -1,4 +1,4 @@
-# Generate Custom Labels
+# Generate Custom Labels 💎
 The `generate_labels` tool scans the PR code changes, and given a list of labels and their descriptions, it automatically suggests labels that match the PR code changes.

 It can be invoked manually by commenting on any PR:
@ -14,16 +14,32 @@ If we wish to add detect changes to SQL queries in a given PR, we can add the fo
 When running the `generate_labels` tool on a PR that includes changes in SQL queries, it will automatically suggest the custom label:
 <kbd><img src=https://codium.ai/images/pr_agent/custom_label_published.png width="768"></kbd>

+Note that in addition to the dedicated tool `generate_labels`, the custom labels will also be used by the `describe` tool.
+
 ### How to enable custom labels
+There are 3 ways to enable custom labels:

-Note that in addition to the dedicated tool `generate_labels`, the custom labels will also be used by the `review` and `describe` tools.
+#### 1. CLI (local configuration file)
+When working from CLI, you need to apply the [configuration changes](#configuration-changes) to the [custom_labels file](./../pr_agent/settings/custom_labels.toml):

-#### CLI
-To enable custom labels, you need to apply the [configuration changes](#configuration-changes) to the [custom_labels file](./../pr_agent/settings/custom_labels.toml):
-
-#### GitHub Action and GitHub App
+#### 2. Repo configuration file
 To enable custom labels, you need to apply the [configuration changes](#configuration-changes) to the local `.pr_agent.toml` file in you repository.

+#### 3. Handle custom labels from the Repo's labels page 
+> This feature is available only in PR-Agent Pro 
+* GitHub : `https://github.com/{owner}/{repo}/labels`, or click on the "Labels" tab in the issues or PRs page.
+* GitLab : `https://gitlab.com/{owner}/{repo}/-/labels`, or click on "Manage" -> "Labels" on the left menu.
+
+b. Add/edit the custom labels. It should be formatted as follows:
+* Label name: The name of the custom label.
+* Description: Start the description of with prefix `pr_agent:`, for example: `pr_agent: Description of when AI should suggest this label`.<br>
+The description should be comprehensive and detailed, indicating when to add the desired label.
+<kbd><img src=https://codium.ai/images/pr_agent/add_native_custom_labels.png width="880"></kbd>
+
+c. Now the custom labels will be included in the `generate_labels` tool.
+
+*This feature is supported in GitHub and GitLab.
+
 #### Configuration changes
 - Change `enable_custom_labels` to True: This will turn off the default labels and enable the custom labels provided in the custom_labels.toml file.
 - Add the custom labels. It should be formatted as follows:
--- a/docs/IMPROVE.md
+++ b/docs/IMPROVE.md
@ -1,57 +1,90 @@
 # Improve Tool

-The `improve` tool scans the PR code changes, and automatically generates committable suggestions for improving the PR code.
-It can be invoked manually by commenting on any PR:
+## Table of Contents
+- [Overview](#overview)
+  - [Configuration options](#configuration-options)
+  - [Summarize mode](#summarize-mode)
+- [Usage Tips](#usage-tips)
+    - [Extra instructions](#extra-instructions)
+    - [PR footprint - regular vs summarize mode](#pr-footprint---regular-vs-summarize-mode)
+    - [A note on code suggestions quality](#a-note-on-code-suggestions-quality)
+
+## Overview
+The `improve` tool scans the PR code changes, and automatically generates suggestions for improving the PR code.
+The tool can be triggered automatically every time a new PR is [opened](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools), or it can be invoked manually by commenting on any PR:
 ```
 /improve
 ```
-For example:

-<kbd><img src=https://codium.ai/images/pr_agent/improve_comment.png width="768"></kbd>
+### Summarized vs commitable code suggestions
+
+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>
+___
+
+Or as a separate commitable code comment for each suggestion:
+___
 <kbd><img src=https://codium.ai/images/pr_agent/improve.png width="768"></kbd>

-The `improve` tool can also be triggered automatically every time a new PR is opened. See examples for automatic triggers for [GitHub App](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools) and [GitHub Action](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#working-with-github-action)
+---
+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.
+
+### Extended mode

 An extended mode, which does not involve PR Compression and provides more comprehensive suggestions, can be invoked by commenting on any PR:
 ```
 /improve --extended
 ```
-Note that the extended mode divides the PR code changes into chunks, up to the token limits, where each chunk is handled separately (multiple calls to GPT-4).
+Note that the extended mode divides the PR code changes into chunks, up to the token limits, where each chunk is handled separately (might use multiple calls to GPT-4 for large PRs).
 Hence, the total number of suggestions is proportional to the number of chunks, i.e., the size of the PR.

 ### Configuration options

-Under the section 'pr_code_suggestions', the [configuration file](./../pr_agent/settings/configuration.toml#L40) contains options to customize the 'improve' tool:
+To edit [configurations](./../pr_agent/settings/configuration.toml#L66) related to the improve tool (`pr_code_suggestions` section), use the following template:
+```
+/improve --pr_code_suggestions.some_config1=... --pr_code_suggestions.some_config2=...
+```

+#### 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.
 #### params for '/improve --extended' mode
+- `auto_extended_mode`: enable extended mode automatically (no need for the `--extended` option). Default is false.
 - `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.

-#### summarize mode
- `summarize`: if set to true, the tool will present the code suggestions in a compact way. Default is false.

-In this mode, instead of presenting committable suggestions, the different suggestions will be combined into a single compact comment, with significantly smaller PR footprint.
+## Usage Tips

-For example:
+### 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.

-`/improve --pr_code_suggestions.summarize=true`
+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.

-<kbd><img src=https://codium.ai/images/pr_agent/improved_summerize_open.png width="768"></kbd>
-
-___
+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](./../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 'extra_instructions' field to guide the model to suggestions that are more relevant to the specific needs of the project.
-
 - Best quality will be obtained by using 'improve --extended' mode.
+
--- a/docs/REVIEW.md
+++ b/docs/REVIEW.md
@ -1,40 +1,59 @@
 # Review Tool

+## Table of Contents
+- [Overview](#overview)
+  - [Configuration options](#configuration-options)
+  - [Incremental Mode](#incremental-mode)
+  - [PR Reflection](#pr-reflection)
+- [Usage Tips](#usage-tips)
+  - [General guidelines](#general-guidelines)
+  - [Code suggestions](#code-suggestions)
+  - [Automation](#automation)
+  - [Auto-labels](#auto-labels)
+  - [Extra instructions](#extra-instructions)
+
+## Overview
 The `review` tool scans the PR code changes, and automatically generates a PR review.
-It can be invoked manually by commenting on any PR:
+The tool can be triggered automatically every time a new PR is [opened](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools), or can be invoked manually by commenting on any PR:
 ```
 /review
 ```
 For example:
-
+___
 <kbd><img src=https://codium.ai/images/pr_agent/review_comment.png width="768"></kbd>
+___
 <kbd><img src=https://codium.ai/images/pr_agent/review.png width="768"></kbd>
-
-The `review` tool can also be triggered automatically every time a new PR is opened. See examples for automatic triggers for [GitHub App](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools) and [GitHub Action](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#working-with-github-action)
+___

 ### Configuration options

-Under the section 'pr_reviewer', the [configuration file](./../pr_agent/settings/configuration.toml#L16) contains options to customize the 'review' tool:
+To edit [configurations](./../pr_agent/settings/configuration.toml#L19)  related to the review tool (`pr_reviewer` section), use the following template:
+```
+/review --pr_reviewer.some_config1=... --pr_reviewer.some_config2=...
+```

-#### enable\\disable features
+#### General options
+- `num_code_suggestions`: number of code suggestions provided by the 'review' tool. Default is 4.
+- `inline_code_comments`: if set to true, the tool will publish the code suggestions as comments on the code diff. Default is false.
+- `persistent_comment`: if set to true, the review comment will be persistent, meaning that every new review request will edit the previous one. Default is true.
+- `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".
+#### Enable\\disable features
 - `require_focused_review`: if set to true, the tool will add a section - 'is the PR a focused one'. Default is false.
 - `require_score_review`: if set to true, the tool will add a section that scores the PR. Default is false.
 - `require_tests_review`: if set to true, the tool will add a section that checks if the PR contains tests. Default is true.
 - `require_security_review`: if set to true, the tool will add a section that checks if the PR contains security issues. Default is true.
- `require_estimate_effort_to_review`: if set to true, the tool will add a section that estimates thed effort needed to review the PR. Default is true.
-#### general options
- `num_code_suggestions`: number of code suggestions provided by the 'review' tool. Default is 4.
- `inline_code_comments`: if set to true, the tool will publish the code suggestions as comments on the code diff. Default is false.
- `automatic_review`: if set to false, no automatic reviews will be done. Default is true.
- `remove_previous_review_comment`: if set to true, the tool will remove the previous review comment before adding a new one. Default is false.
- `persistent_comment`: if set to true, the review comment will be persistent, meaning that every new review request will edit the previous one. Default is true.
- `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".
-#### review labels
+- `require_estimate_effort_to_review`: if set to true, the tool will add a section that estimates the effort needed to review the PR. Default is true.
+#### SOC2 ticket compliance 💎
+This sub-tool checks if the PR description properly contains a ticket to a project management system (e.g., Jira, Asana, Trello, etc.), as required by SOC2 compliance. If not, it will add a label to the PR: "Missing SOC2 ticket".
+- `require_soc2_ticket`: If set to true, the SOC2 ticket checker sub-tool will be enabled. Default is false.
+- `soc2_ticket_prompt`: The prompt for the SOC2 ticket review. Default is: `Does the PR description include a link to ticket in a project management system (e.g., Jira, Asana, Trello, etc.) ?`. Edit this field if your compliance requirements are different.
+#### Adding PR labels
 - `enable_review_labels_security`: if set to true, the tool will publish a 'possible security issue' label if it detects a security issue. Default is true.
- `enable_review_labels_effort`: if set to true, the tool will publish a 'Review effort [1-5]: x' label. Default is false.
- To enable `custom labels`, apply the configuration changes described [here](./GENERATE_CUSTOM_LABELS.md#configuration-changes) 
-####  Incremental Mode
-For an incremental review, which only considers changes since the last PR-Agent review, this can be useful when working on the PR in an iterative manner, and you want to focus on the changes since the last review instead of reviewing the entire PR again, the following command can be used:
+- `enable_review_labels_effort`: if set to true, the tool will publish a 'Review effort [1-5]: x' label. Default is true.
+
+###  Incremental Mode
+Incremental review only considers changes since the last PR-Agent review. This can be useful when working on the PR in an iterative manner, and you want to focus on the changes since the last review instead of reviewing the entire PR again.
+For invoking the incremental mode, the following command can be used:
 ```
 /review -i
 ```
@ -42,7 +61,7 @@ Note that the incremental mode is only available for GitHub.

 <kbd><img src=https://codium.ai/images/pr_agent/incremental_review.png width="768"></kbd>

-Under the section 'pr_reviewer', the [configuration file](./../pr_agent/settings/configuration.toml#L16) contains options to customize the 'review -i' tool.  
+Under the section 'pr_reviewer', the [configuration file](./../pr_agent/settings/configuration.toml#L19) contains options to customize the 'review -i' tool.  
 These configurations can be used to control the rate at which the incremental review tool will create new review comments when invoked automatically, to prevent making too much noise in the PR.
 - `minimal_commits_for_incremental_review`: Minimal number of commits since the last review that are required to create incremental review.
 If there are less than the specified number of commits since the last review, the tool will not perform any action.
@ -55,25 +74,75 @@ For example, if `minimal_commits_for_incremental_review=2` and `minimal_minutes_
 When `require_all_thresholds_for_incremental_review=true` the incremental review __will not__ run, because only 1 out of 2 conditions were met (we have enough commits but the last review is too recent),
 but when `require_all_thresholds_for_incremental_review=false` the incremental review __will__ run, because one condition is enough (we have 3 commits which is more than the configured 2).
 Default is false - the tool will run as long as at least once conditions is met.
+- `remove_previous_review_comment`: if set to true, the tool will remove the previous review comment before adding a new one. Default is false.

-#### PR Reflection
+### PR Reflection
 By invoking:
 ```
 /reflect_and_review
 ```
-The tool will first ask the author questions about the PR, and will guide the review based on his answers.
+The tool will first ask the author questions about the PR, and will guide the review based on their answers.

 <kbd><img src=https://codium.ai/images/pr_agent/reflection_questions.png width="768"></kbd>
+___
 <kbd><img src=https://codium.ai/images/pr_agent/reflection_answers.png width="768"></kbd>
+___
 <kbd><img src=https://codium.ai/images/pr_agent/reflection_insights.png width="768"></kbd>
+___


-#### A note on code suggestions quality
+## Usage Tips
+1) [General guidelines](#general-guidelines)
+2) [Code suggestions](#code-suggestions)
+3) [Automation](#automation)
+4) [Auto-labels](#auto-labels)
+5) [Extra instructions](#extra-instructions)

- With current level of AI for code (GPT-4), mistakes can happen. Not all the suggestions will be perfect, and a user should not accept all of them automatically.
+### General guidelines
+The `review` tool provides a collection of possible feedbacks about a PR.
+It is recommended to review the [Configuration options](#configuration-options) section, and choose the relevant options for your use case.

- Suggestions are not meant to be [simplistic](./../pr_agent/settings/pr_reviewer_prompts.toml#L29). 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.
+Some of the feature that are disabled by default are quite useful, and should be considered for enabling. For example: 
+`require_score_review`, `require_soc2_ticket`, and more.

- Recommended to use the 'extra_instructions' field to guide the model to suggestions that are more relevant to the specific needs of the project.
+On the other hand, if you find one of the enabled features to be irrelevant for your use case, disable it. No default configuration can fit all use cases.
+
+### Code suggestions
+The `review` tool provides several type of feedbacks, one of them is code suggestions.
+If you are interested **only** in the code suggestions, it is recommended to use the [`improve`](./IMPROVE.md) feature instead, since it dedicated only to code suggestions, and usually gives better results.
+Use the `review` tool if you want to get a more comprehensive feedback, which includes code suggestions as well.
+
+### Automation
+- When you first install the app, the [default mode](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools) for the `review` tool is:
+```
+pr_commands = ["/review", ...]
+```
+meaning the `review` tool will run automatically on every PR, with the default configuration.
+Edit this field to enable/disable the tool, or to change the used configurations
+
+### Auto-labels
+The `review` tool can auto-generate two specific types of labels for a PR:
+- a `possible security issue` label that detects a possible [security issue](https://github.com/Codium-ai/pr-agent/blob/tr/user_description/pr_agent/settings/pr_reviewer_prompts.toml#L136) (`enable_review_labels_security` flag)
+- a `Review effort [1-5]: x` label, where x is the estimated effort to review the PR (`enable_review_labels_effort` flag)
+
+Both modes are useful, and we recommended to enable them.
+
+### Extra instructions
+Extra instruction are important.
+The `review` tool can be configured with extra instructions, which can be used to guide the model to a feedback tailored to the needs of your project.
+
+Be specific, clear, and concise in the instructions. With extra instructions, you are the prompter. Specify the relevant sub-tool, and the relevant aspects of the PR that you want to emphasize.
+
+Examples for extra instructions:
+```
+[pr_reviewer] # /review #
+extra_instructions="""
+In the code feedback section, emphasize the following:
+- 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.

- Unlike the 'review' feature, which does a lot of things, the ['improve --extended'](./IMPROVE.md) feature is dedicated only to suggestions, and usually gives better results.
--- a/docs/SIMILAR_ISSUE.md
+++ b/docs/SIMILAR_ISSUE.md
@ -12,7 +12,15 @@ For example:

 Note that to perform retrieval, the `similar_issue` tool indexes all the repo previous issues (once).

-To enable usage of the '**similar issue**' tool, you need to set the following keys in `.secrets.toml` (or in the relevant environment variables):
+
+**Select VectorDBs** by changing `pr_similar_issue` parameter in `configuration.toml` file 
+
+2 VectorDBs are available to switch in
+1. LanceDB
+2. Pinecone
+
+To enable usage of the '**similar issue**' tool for Pinecone, you need to set the following keys in `.secrets.toml` (or in the relevant environment variables):
+
 ```
 [pinecone]
 api_key = "..."
--- a/docs/TEST.md
+++ b/docs/TEST.md
@ -0,0 +1,30 @@
+# Test Tool 💎
+By combining LLM abilities with static code analysis, the `test` tool  generate tests for a selected component, based on the PR code changes.
+It can be invoked manually by commenting on any PR:
+```
+/test component_name
+```
+where 'component_name' is the name of a specific component in the PR.
+To get a list of the components that changed in the PR, use the [`analyze`](https://github.com/Codium-ai/pr-agent/blob/main/docs/Analyze.md) tool.
+
+
+An example [result](https://github.com/Codium-ai/pr-agent/pull/598#issuecomment-1913679429):
+
+<kbd><img src=https://codium.ai/images/pr_agent/test1.png width="704"></kbd>
+___
+<kbd><img src=https://codium.ai/images/pr_agent/test2.png width="768"></kbd>
+___
+<kbd><img src=https://codium.ai/images/pr_agent/test3.png width="768"></kbd>
+
+Language that are currently supported by the tool: Python, Java, C++, JavaScript, TypeScript.
+
+
+
+### Configuration options
+- `num_tests`: number of tests to generate. Default is 3.
+- `testing_framework`: the testing framework to use. If not set, for Python it will use `pytest`, for Java it will use `JUnit`, for C++ it will use `Catch2`, and for JavaScript and TypeScript it will use `jest`.
+- `avoid_mocks`: if set to true, the tool will try to avoid using mocks in the generated tests. Note that even if this option is set to true, the tool might still use mocks if it cannot generate a test without them. Default is true.
+- `extra_instructions`: Optional extra instructions to the tool. For example: "use the following mock injection scheme: ...".
+- `file`: in case there are several components with the same name, you can specify the relevant file.
+- `class_name`: in case there are several methods with the same name in the same file, you can specify the relevant class name.
+- `enable_help_text`: if set to true, the tool will add a help text to the PR comment. Default is true.
--- a/docs/TOOLS_GUIDE.md
+++ b/docs/TOOLS_GUIDE.md
@ -5,7 +5,9 @@
 - [ASK](./ASK.md)
 - [SIMILAR_ISSUE](./SIMILAR_ISSUE.md)
 - [UPDATE CHANGELOG](./UPDATE_CHANGELOG.md)
- [ADD DOCUMENTATION](./ADD_DOCUMENTATION.md)
- [GENERATE CUSTOM LABELS](./GENERATE_CUSTOM_LABELS.md)
+- [ADD DOCUMENTATION](./ADD_DOCUMENTATION.md) 💎
+- [GENERATE CUSTOM LABELS](./GENERATE_CUSTOM_LABELS.md) 💎
+- [Analyze](./Analyze.md) 💎
+- [Test](./TEST.md) 💎

-See the **[installation guide](/INSTALL.md)** for instructions on how to setup PR-Agent.
+See the **[installation guide](/INSTALL.md)** for instructions on setting up PR-Agent.
--- a/pr_agent/agent/pr_agent.py
+++ b/pr_agent/agent/pr_agent.py
@ -1,8 +1,13 @@
 import shlex
+from functools import partial
+
+from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
+from pr_agent.algo.ai_handlers.litellm_ai_handler import LiteLLMAIHandler

 from pr_agent.algo.utils import update_settings_from_args
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers.utils import apply_repo_settings
+from pr_agent.log import get_logger
 from pr_agent.tools.pr_add_docs import PRAddDocs
 from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
 from pr_agent.tools.pr_config import PRConfig
@ -38,8 +43,8 @@ command2class = {
 commands = list(command2class.keys())

 class PRAgent:
-    def __init__(self):
-        pass
+    def __init__(self, ai_handler: partial[BaseAiHandler,] = LiteLLMAIHandler):
+        self.ai_handler = ai_handler # will be initialized in run_action

    async def handle_request(self, pr_url, request, notify=None) -> bool:
        # First, apply repo specific settings if exists
@ -61,13 +66,14 @@ class PRAgent:
        if action == "answer":
            if notify:
                notify()
-            await PRReviewer(pr_url, is_answer=True, args=args).run()
+            await PRReviewer(pr_url, is_answer=True, args=args, ai_handler=self.ai_handler).run()
        elif action == "auto_review":
-            await PRReviewer(pr_url, is_auto=True, args=args).run()
+            await PRReviewer(pr_url, is_auto=True, args=args, ai_handler=self.ai_handler).run()
        elif action in command2class:
            if notify:
                notify()
-            await command2class[action](pr_url, args=args).run()
+                
+            await command2class[action](pr_url, ai_handler=self.ai_handler, args=args).run()
        else:
            return False
        return True
--- a/pr_agent/algo/ai_handlers/base_ai_handler.py
+++ b/pr_agent/algo/ai_handlers/base_ai_handler.py
@ -0,0 +1,28 @@
+from abc import ABC, abstractmethod
+
+class BaseAiHandler(ABC):
+    """
+    This class defines the interface for an AI handler to be used by the PR Agents.  
+    """
+
+    @abstractmethod
+    def __init__(self):
+        pass
+
+    @property
+    @abstractmethod
+    def deployment_id(self):
+        pass
+
+    @abstractmethod   
+    async def chat_completion(self, model: str, system: str, user: str, temperature: float = 0.2):
+        """
+        This method should be implemented to return a chat completion from the AI model.
+        Args:
+            model (str): the name of the model to use for the chat completion
+            system (str): the system message string to use for the chat completion
+            user (str): the user message string to use for the chat completion
+            temperature (float): the temperature to use for the chat completion    
+        """
+        pass
+
--- a/pr_agent/algo/ai_handlers/langchain_ai_handler.py
+++ b/pr_agent/algo/ai_handlers/langchain_ai_handler.py
@ -0,0 +1,67 @@
+try:
+    from langchain.chat_models import ChatOpenAI, AzureChatOpenAI
+    from langchain.schema import SystemMessage, HumanMessage
+except: # we don't enforce langchain as a dependency, so if it's not installed, just move on
+    pass
+
+from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
+from pr_agent.config_loader import get_settings
+from pr_agent.log import get_logger
+
+from openai.error import APIError, RateLimitError, Timeout, TryAgain
+from retry import retry
+import functools
+
+OPENAI_RETRIES = 5
+
+class LangChainOpenAIHandler(BaseAiHandler):
+    def __init__(self):
+        # Initialize OpenAIHandler specific attributes here
+        super().__init__()
+        self.azure = get_settings().get("OPENAI.API_TYPE", "").lower() == "azure"
+        try:
+            if self.azure:
+                # using a partial function so we can set the deployment_id later to support fallback_deployments
+                # but still need to access the other settings now so we can raise a proper exception if they're missing
+                self._chat = functools.partial(
+                    lambda **kwargs: AzureChatOpenAI(**kwargs),
+                    openai_api_key=get_settings().openai.key,
+                    openai_api_base=get_settings().openai.api_base,
+                    openai_api_version=get_settings().openai.api_version,
+                )
+            else:
+                self._chat = ChatOpenAI(openai_api_key=get_settings().openai.key)
+        except AttributeError as e:
+            if getattr(e, "name"):
+                raise ValueError(f"OpenAI {e.name} is required") from e
+            else:
+                raise e
+    
+    @property
+    def chat(self):
+        if self.azure:
+            # we must set the deployment_id only here (instead of the __init__ method) to support fallback_deployments
+            return self._chat(deployment_name=self.deployment_id)
+        else:
+            return self._chat
+
+    @property
+    def deployment_id(self):
+        """
+        Returns the deployment ID for the OpenAI API.
+        """
+        return get_settings().get("OPENAI.DEPLOYMENT_ID", None)
+    @retry(exceptions=(APIError, Timeout, TryAgain, AttributeError, RateLimitError),
+           tries=OPENAI_RETRIES, delay=2, backoff=2, jitter=(1, 3))
+    async def chat_completion(self, model: str, system: str, user: str, temperature: float = 0.2):
+        try:
+            messages=[SystemMessage(content=system), HumanMessage(content=user)]
+            
+            # get a chat completion from the formatted messages
+            resp = self.chat(messages, model=model, temperature=temperature)
+            finish_reason="completed"
+            return resp.content, finish_reason
+        
+        except (Exception) as e:
+            get_logger().error("Unknown error during OpenAI inference: ", e)
+            raise e
--- a/pr_agent/algo/ai_handlers/litellm_ai_handler.py
+++ b/pr_agent/algo/ai_handlers/litellm_ai_handler.py
@ -6,13 +6,14 @@ import openai
 from litellm import acompletion
 from openai.error import APIError, RateLimitError, Timeout, TryAgain
 from retry import retry
+from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
 from pr_agent.config_loader import get_settings
 from pr_agent.log import get_logger

 OPENAI_RETRIES = 5


-class AiHandler:
+class LiteLLMAIHandler(BaseAiHandler):
    """
    This class handles interactions with the OpenAI API for chat completions.
    It initializes the API key and other settings from a configuration file,
@ -100,11 +101,6 @@ class AiHandler:
        """
        try:
            deployment_id = self.deployment_id
-            if get_settings().config.verbosity_level >= 2:
-                get_logger().debug(
-                    f"Generating completion with {model}"
-                    f"{(' from deployment ' + deployment_id) if deployment_id else ''}"
-                )
            if self.azure:
                model = 'azure/' + model
            messages = [{"role": "system", "content": system}, {"role": "user", "content": user}]
--- a/pr_agent/algo/ai_handlers/openai_ai_handler.py
+++ b/pr_agent/algo/ai_handlers/openai_ai_handler.py
@ -0,0 +1,67 @@
+from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
+import openai
+from openai.error import APIError, RateLimitError, Timeout, TryAgain
+from retry import retry
+
+from pr_agent.config_loader import get_settings
+from pr_agent.log import get_logger
+
+OPENAI_RETRIES = 5
+
+
+class OpenAIHandler(BaseAiHandler):
+    def __init__(self):
+        # Initialize OpenAIHandler specific attributes here
+        try:
+            super().__init__()
+            openai.api_key = get_settings().openai.key
+            if get_settings().get("OPENAI.ORG", None):
+                openai.organization = get_settings().openai.org
+            if get_settings().get("OPENAI.API_TYPE", None):
+                if get_settings().openai.api_type == "azure":
+                    self.azure = True
+                    openai.azure_key = get_settings().openai.key
+            if get_settings().get("OPENAI.API_VERSION", None):
+                openai.api_version = get_settings().openai.api_version
+            if get_settings().get("OPENAI.API_BASE", None):
+                openai.api_base = get_settings().openai.api_base
+
+        except AttributeError as e:
+            raise ValueError("OpenAI key is required") from e
+    @property
+    def deployment_id(self):
+        """
+        Returns the deployment ID for the OpenAI API.
+        """
+        return get_settings().get("OPENAI.DEPLOYMENT_ID", None)
+    
+    @retry(exceptions=(APIError, Timeout, TryAgain, AttributeError, RateLimitError),
+           tries=OPENAI_RETRIES, delay=2, backoff=2, jitter=(1, 3))
+    async def chat_completion(self, model: str, system: str, user: str, temperature: float = 0.2):
+        try:
+            deployment_id = self.deployment_id
+            get_logger().info("System: ", system)
+            get_logger().info("User: ", user)
+            messages = [{"role": "system", "content": system}, {"role": "user", "content": user}]
+
+            chat_completion = await openai.ChatCompletion.acreate(
+                model=model,
+                deployment_id=deployment_id,
+                messages=messages,
+                temperature=temperature,
+            )
+            resp = chat_completion["choices"][0]['message']['content']
+            finish_reason = chat_completion["choices"][0]["finish_reason"]
+            usage = chat_completion.get("usage")
+            get_logger().info("AI response", response=resp, messages=messages, finish_reason=finish_reason,
+                            model=model, usage=usage)
+            return resp, finish_reason       
+        except (APIError, Timeout, TryAgain) as e:
+            get_logger().error("Error during OpenAI inference: ", e)
+            raise
+        except (RateLimitError) as e:
+            get_logger().error("Rate limit error during OpenAI inference: ", e)
+            raise
+        except (Exception) as e:
+            get_logger().error("Unknown error during OpenAI inference: ", e)
+            raise TryAgain from e        
--- a/pr_agent/algo/git_patch_processing.py
+++ b/pr_agent/algo/git_patch_processing.py
@ -181,7 +181,7 @@ __old hunk__
           ...
    """
    
-    patch_with_lines_str = f"\n\n## {file.filename}\n"
+    patch_with_lines_str = f"\n\n## file: '{file.filename.strip()}'\n"
    patch_lines = patch.splitlines()
    RE_HUNK_HEADER = re.compile(
        r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
@ -202,11 +202,11 @@ __old hunk__
                if new_content_lines:
                    if prev_header_line:
                        patch_with_lines_str += f'\n{prev_header_line}\n'
-                    patch_with_lines_str += '__new hunk__\n'
+                    patch_with_lines_str = patch_with_lines_str.rstrip()+'\n__new hunk__\n'
                    for i, line_new in enumerate(new_content_lines):
                        patch_with_lines_str += f"{start2 + i} {line_new}\n"
                if old_content_lines:
-                    patch_with_lines_str += '__old hunk__\n'
+                    patch_with_lines_str = patch_with_lines_str.rstrip()+'\n__old hunk__\n'
                    for line_old in old_content_lines:
                        patch_with_lines_str += f"{line_old}\n"
                new_content_lines = []
@ -236,11 +236,11 @@ __old hunk__
    if match and new_content_lines:
        if new_content_lines:
            patch_with_lines_str += f'\n{header_line}\n'
-            patch_with_lines_str += '\n__new hunk__\n'
+            patch_with_lines_str = patch_with_lines_str.rstrip()+ '\n__new hunk__\n'
            for i, line_new in enumerate(new_content_lines):
                patch_with_lines_str += f"{start2 + i} {line_new}\n"
        if old_content_lines:
-            patch_with_lines_str += '\n__old hunk__\n'
+            patch_with_lines_str = patch_with_lines_str.rstrip() + '\n__old hunk__\n'
            for line_old in old_content_lines:
                patch_with_lines_str += f"{line_old}\n"

--- a/pr_agent/algo/pr_processing.py
+++ b/pr_agent/algo/pr_processing.py
@ -209,9 +209,9 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, mo

        if patch:
            if not convert_hunks_to_line_numbers:
-                patch_final = f"## {file.filename}\n\n{patch}\n"
+                patch_final = f"\n\n## file: '{file.filename.strip()}\n\n{patch.strip()}\n'"
            else:
-                patch_final = patch
+                patch_final = "\n\n" + patch.strip()
            patches.append(patch_final)
            total_tokens += token_handler.count_tokens(patch_final)
            if get_settings().config.verbosity_level >= 2:
@ -226,6 +226,11 @@ async def retry_with_fallback_models(f: Callable):
    # try each (model, deployment_id) pair until one is successful, otherwise raise exception
    for i, (model, deployment_id) in enumerate(zip(all_models, all_deployments)):
        try:
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().debug(
+                    f"Generating prediction with {model}"
+                    f"{(' from deployment ' + deployment_id) if deployment_id else ''}"
+                )
            get_settings().set("openai.deployment_id", deployment_id)
            return await f(model)
        except Exception as e:
@ -264,19 +269,10 @@ def _get_all_deployments(all_models: List[str]) -> List[str]:

 def find_line_number_of_relevant_line_in_file(diff_files: List[FilePatchInfo],
                                              relevant_file: str,
-                                              relevant_line_in_file: str) -> Tuple[int, int]:
-    """
-    Find the line number and absolute position of a relevant line in a file.
-
-    Args:
-        diff_files (List[FilePatchInfo]): A list of FilePatchInfo objects representing the patches of files.
-        relevant_file (str): The name of the file where the relevant line is located.
-        relevant_line_in_file (str): The content of the relevant line.
-
-    Returns:
-        Tuple[int, int]: A tuple containing the line number and absolute position of the relevant line in the file.
-    """
+                                              relevant_line_in_file: str,
+                                              absolute_position: int = None) -> Tuple[int, int]:
    position = -1
+    if absolute_position is None:
        absolute_position = -1
    re_hunk_header = re.compile(
        r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
@ -285,15 +281,32 @@ def find_line_number_of_relevant_line_in_file(diff_files: List[FilePatchInfo],
        if file.filename and (file.filename.strip() == relevant_file):
            patch = file.patch
            patch_lines = patch.splitlines()
+            delta = 0
+            start1, size1, start2, size2 = 0, 0, 0, 0
+            if absolute_position != -1: # matching absolute to relative
+                for i, line in enumerate(patch_lines):
+                    # new hunk
+                    if line.startswith('@@'):
+                        delta = 0
+                        match = re_hunk_header.match(line)
+                        start1, size1, start2, size2 = map(int, match.groups()[:4])
+                    elif not line.startswith('-'):
+                        delta += 1

+                    #
+                    absolute_position_curr = start2 + delta - 1
+
+                    if absolute_position_curr == absolute_position:
+                        position = i
+                        break
+            else:
                # try to find the line in the patch using difflib, with some margin of error
                matches_difflib: list[str | Any] = difflib.get_close_matches(relevant_line_in_file,
                                                                             patch_lines, n=3, cutoff=0.93)
                if len(matches_difflib) == 1 and matches_difflib[0].startswith('+'):
                    relevant_line_in_file = matches_difflib[0]

-            delta = 0
-            start1, size1, start2, size2 = 0, 0, 0, 0
+
                for i, line in enumerate(patch_lines):
                    if line.startswith('@@'):
                        delta = 0
@ -362,6 +375,13 @@ def get_pr_multi_diffs(git_provider: GitProvider,
    for lang in pr_languages:
        sorted_files.extend(sorted(lang['files'], key=lambda x: x.tokens, reverse=True))

+
+    # try first a single run with standard diff string, with patch extension, and no deletions
+    patches_extended, total_tokens, patches_extended_tokens = pr_generate_extended_diff(
+        pr_languages, token_handler, add_line_numbers_to_hunks=True)
+    if total_tokens + OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD < get_max_tokens(model):
+        return ["\n".join(patches_extended)]
+
    patches = []
    final_diff_list = []
    total_tokens = token_handler.prompt_tokens
--- a/pr_agent/algo/utils.py
+++ b/pr_agent/algo/utils.py
@ -49,7 +49,7 @@ def convert_to_markdown(output_data: dict, gfm_supported: bool=True) -> str:
    }

    for key, value in output_data.items():
-        if value is None or value == '' or value == {}:
+        if value is None or value == '' or value == {} or value == []:
            continue
        if isinstance(value, dict):
            markdown_text += f"## {key}\n\n"
@ -58,10 +58,10 @@ def convert_to_markdown(output_data: dict, gfm_supported: bool=True) -> str:
            emoji = emojis.get(key, "")
            if key.lower() == 'code feedback':
                if gfm_supported:
-                    markdown_text += f"\n\n- "
-                    markdown_text += f"<details><summary> { emoji } Code feedback:</summary>"
+                    markdown_text += f"\n\n"
+                    markdown_text += f"<details><summary> <strong>{ emoji } Code feedback:</strong></summary>"
                else:
-                    markdown_text += f"\n\n- **{emoji} Code feedback:**\n\n"
+                    markdown_text += f"\n\n**{emoji} Code feedback:**\n\n"
            else:
                markdown_text += f"- {emoji} **{key}:**\n\n"
            for i, item in enumerate(value):
@ -76,6 +76,12 @@ def convert_to_markdown(output_data: dict, gfm_supported: bool=True) -> str:
                    markdown_text += "\n\n"
        elif value != 'n/a':
            emoji = emojis.get(key, "")
+            if key.lower() == 'general suggestions':
+                if gfm_supported:
+                    markdown_text += f"\n\n<strong>{emoji} General suggestions:</strong> {value}\n"
+                else:
+                    markdown_text += f"{emoji} **General suggestions:** {value}\n"
+            else:
                markdown_text += f"- {emoji} **{key}:** {value}\n"
    return markdown_text

@ -102,14 +108,15 @@ def parse_code_suggestion(code_suggestions: dict, i: int = 0, gfm_supported: boo
                    markdown_text += f"<tr><td>{sub_key}</td><td>{relevant_file}</td></tr>"
                    # continue
                elif sub_key.lower() == 'suggestion':
-                    markdown_text += f"<tr><td>{sub_key} &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</td><td><strong>{sub_value}</strong></td></tr>"
+                    markdown_text += (f"<tr><td>{sub_key} &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</td>"
+                                      f"<td><br>\n\n**{sub_value.strip()}**\n<br></td></tr>")
                elif sub_key.lower() == 'relevant line':
                    markdown_text += f"<tr><td>relevant line</td>"
                    sub_value_list = sub_value.split('](')
                    relevant_line = sub_value_list[0].lstrip('`').lstrip('[')
                    if len(sub_value_list) > 1:
                        link = sub_value_list[1].rstrip(')').strip('`')
-                        markdown_text += f"<td><a href={link}>{relevant_line}</a></td>"
+                        markdown_text += f"<td><a href='{link}'>{relevant_line}</a></td>"
                    else:
                        markdown_text += f"<td>{relevant_line}</td>"
                    markdown_text += "</tr>"
@ -316,19 +323,21 @@ def _fix_key_value(key: str, value: str):
    return key, value


-def load_yaml(response_text: str) -> dict:
+def load_yaml(response_text: str, keys_fix_yaml: List[str] = []) -> dict:
    response_text = response_text.removeprefix('```yaml').rstrip('`')
    try:
        data = yaml.safe_load(response_text)
    except Exception as e:
        get_logger().error(f"Failed to parse AI prediction: {e}")
-        data = try_fix_yaml(response_text)
+        data = try_fix_yaml(response_text, keys_fix_yaml=keys_fix_yaml)
    return data

-def try_fix_yaml(response_text: str) -> dict:
+
+def try_fix_yaml(response_text: str, keys_fix_yaml: List[str] = []) -> dict:
    response_text_lines = response_text.split('\n')

-    keys = ['relevant line:', 'suggestion content:', 'relevant file:']
+    keys = ['relevant line:', 'suggestion content:', 'relevant file:', 'existing code:', 'improved code:']
+    keys = keys + keys_fix_yaml
    # first fallback - try to convert 'relevant line: ...' to relevant line: |-\n        ...'
    response_text_lines_copy = response_text_lines.copy()
    for i in range(0, len(response_text_lines_copy)):
@ -343,22 +352,34 @@ def try_fix_yaml(response_text: str) -> dict:
    except:
        get_logger().info(f"Failed to parse AI prediction after adding |-\n")

-    # second fallback - try to remove last lines
+    # second fallback - try to extract only range from first ```yaml to ````
+    snippet_pattern = r'```(yaml)?[\s\S]*?```'
+    snippet = re.search(snippet_pattern, '\n'.join(response_text_lines_copy))
+    if snippet:
+        snippet_text = snippet.group()
+        try:
+            data = yaml.safe_load(snippet_text.removeprefix('```yaml').rstrip('`'))
+            get_logger().info(f"Successfully parsed AI prediction after extracting yaml snippet")
+            return data
+        except:
+            pass
+
+     # third fallback - try to remove leading and trailing curly brackets
+    response_text_copy = response_text.strip().rstrip().removeprefix('{').removesuffix('}')
+    try:
+        data = yaml.safe_load(response_text_copy,)
+        get_logger().info(f"Successfully parsed AI prediction after removing curly brackets")
+        return data
+    except:
+        pass
+
+    # fourth fallback - try to remove last lines
    data = {}
    for i in range(1, len(response_text_lines)):
        response_text_lines_tmp = '\n'.join(response_text_lines[:-i])
        try:
            data = yaml.safe_load(response_text_lines_tmp,)
            get_logger().info(f"Successfully parsed AI prediction after removing {i} lines")
-            break
-        except:
-            pass
-    
-    # thrid fallback - try to remove leading and trailing curly brackets
-    response_text_copy = response_text.strip().rstrip().removeprefix('{').removesuffix('}')
-    try:
-        data = yaml.safe_load(response_text_copy,)
-        get_logger().info(f"Successfully parsed AI prediction after removing curly brackets")
            return data
        except:
            pass
@ -379,9 +400,15 @@ def set_custom_labels(variables, git_provider=None):

    # Set custom labels
    variables["custom_labels_class"] = "class Label(str, Enum):"
+    counter = 0
+    labels_minimal_to_labels_dict = {}
    for k, v in labels.items():
-        description = v['description'].strip('\n').replace('\n', '\\n')
-        variables["custom_labels_class"] += f"\n    {k.lower().replace(' ', '_')} = '{k}' # {description}"
+        description = "'" + v['description'].strip('\n').replace('\n', '\\n') + "'"
+        # variables["custom_labels_class"] += f"\n    {k.lower().replace(' ', '_')} = '{k}' # {description}"
+        variables["custom_labels_class"] += f"\n    {k.lower().replace(' ', '_')} = {description}"
+        labels_minimal_to_labels_dict[k.lower().replace(' ', '_')] = k
+        counter += 1
+    variables["labels_minimal_to_labels_dict"] = labels_minimal_to_labels_dict

 def get_user_labels(current_labels: List[str] = None):
    """
@ -448,3 +475,12 @@ def clip_tokens(text: str, max_tokens: int, add_three_dots=True) -> str:
    except Exception as e:
        get_logger().warning(f"Failed to clip tokens: {e}")
        return text
+
+def replace_code_tags(text):
+    """
+    Replace odd instances of ` with <code> and even instances of ` with </code>
+    """
+    parts = text.split('`')
+    for i in range(1, len(parts), 2):
+        parts[i] = '<code>' + parts[i] + '</code>'
+    return ''.join(parts)
--- a/pr_agent/git_providers/azuredevops_provider.py
+++ b/pr_agent/git_providers/azuredevops_provider.py
@ -1,29 +1,40 @@
-import json
+import os
 from typing import Optional, Tuple
 from urllib.parse import urlparse

-import os
-
 from ..log import get_logger
+from ..algo.language_handler import is_valid_file
+from ..algo.utils import clip_tokens, load_large_diff
+from ..config_loader import get_settings
+from .git_provider import EDIT_TYPE, FilePatchInfo, GitProvider

 AZURE_DEVOPS_AVAILABLE = True
+
 try:
+    # noinspection PyUnresolvedReferences
    from msrest.authentication import BasicAuthentication
+    # noinspection PyUnresolvedReferences
    from azure.devops.connection import Connection
-    from azure.devops.v7_1.git.models import Comment, CommentThread, GitVersionDescriptor, GitPullRequest
+    # noinspection PyUnresolvedReferences
+    from azure.devops.v7_1.git.models import (
+        Comment,
+        CommentThread,
+        GitVersionDescriptor,
+        GitPullRequest,
+    )
 except ImportError:
    AZURE_DEVOPS_AVAILABLE = False

-from ..config_loader import get_settings
-from ..algo.utils import load_large_diff, clip_tokens
-from ..algo.language_handler import is_valid_file
-from .git_provider import EDIT_TYPE, FilePatchInfo

+class AzureDevopsProvider(GitProvider):

-class AzureDevopsProvider:
-    def __init__(self, pr_url: Optional[str] = None, incremental: Optional[bool] = False):
+    def __init__(
+            self, pr_url: Optional[str] = None, incremental: Optional[bool] = False
+    ):
        if not AZURE_DEVOPS_AVAILABLE:
-            raise ImportError("Azure DevOps provider is not available. Please install the required dependencies.")
+            raise ImportError(
+                "Azure DevOps provider is not available. Please install the required dependencies."
+            )

        self.azure_devops_client = self._get_azure_devops_client()

@ -37,9 +48,123 @@ class AzureDevopsProvider:
        if pr_url:
            self.set_pr(pr_url)

+    def publish_code_suggestions(self, code_suggestions: list) -> bool:
+        """
+        Publishes code suggestions as comments on the PR.
+        """
+        post_parameters_list = []
+        for suggestion in code_suggestions:
+            body = suggestion['body']
+            relevant_file = suggestion['relevant_file']
+            relevant_lines_start = suggestion['relevant_lines_start']
+            relevant_lines_end = suggestion['relevant_lines_end']
+
+            if not relevant_lines_start or relevant_lines_start == -1:
+                if get_settings().config.verbosity_level >= 2:
+                    get_logger().exception(
+                        f"Failed to publish code suggestion, relevant_lines_start is {relevant_lines_start}")
+                continue
+
+            if relevant_lines_end < relevant_lines_start:
+                if get_settings().config.verbosity_level >= 2:
+                    get_logger().exception(f"Failed to publish code suggestion, "
+                                           f"relevant_lines_end is {relevant_lines_end} and "
+                                           f"relevant_lines_start is {relevant_lines_start}")
+                continue
+
+            if relevant_lines_end > relevant_lines_start:
+                post_parameters = {
+                    "body": body,
+                    "path": relevant_file,
+                    "line": relevant_lines_end,
+                    "start_line": relevant_lines_start,
+                    "start_side": "RIGHT",
+                }
+            else:  # API is different for single line comments
+                post_parameters = {
+                    "body": body,
+                    "path": relevant_file,
+                    "line": relevant_lines_start,
+                    "side": "RIGHT",
+                }
+            post_parameters_list.append(post_parameters)
+
+        try:
+            for post_parameters in post_parameters_list:
+                comment = Comment(content=post_parameters["body"], comment_type=1)
+                thread = CommentThread(comments=[comment],
+                                       thread_context={
+                                           "filePath": post_parameters["path"],
+                                           "rightFileStart": {
+                                               "line": post_parameters["start_line"],
+                                               "offset": 1,
+                                           },
+                                           "rightFileEnd": {
+                                               "line": post_parameters["line"],
+                                               "offset": 1,
+                                           },
+                                       })
+                self.azure_devops_client.create_thread(
+                    comment_thread=thread,
+                    project=self.workspace_slug,
+                    repository_id=self.repo_slug,
+                    pull_request_id=self.pr_num
+                )
+                if get_settings().config.verbosity_level >= 2:
+                    get_logger().info(
+                        f"Published code suggestion on {self.pr_num} at {post_parameters['path']}"
+                    )
+            return True
+        except Exception as e:
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().error(f"Failed to publish code suggestion, error: {e}")
+            return False
+
+    def get_pr_description_full(self) -> str:
+        return self.pr.description
+
+    def remove_comment(self, comment):
+        try:
+            self.azure_devops_client.delete_comment(
+                repository_id=self.repo_slug,
+                pull_request_id=self.pr_num,
+                thread_id=comment["thread_id"],
+                comment_id=comment["comment_id"],
+                project=self.workspace_slug,
+            )
+        except Exception as e:
+            get_logger().exception(f"Failed to remove comment, error: {e}")
+
+    def publish_labels(self, pr_types):
+        try:
+            for pr_type in pr_types:
+                self.azure_devops_client.create_pull_request_label(
+                    label={"name": pr_type},
+                    project=self.workspace_slug,
+                    repository_id=self.repo_slug,
+                    pull_request_id=self.pr_num,
+                )
+        except Exception as e:
+            get_logger().exception(f"Failed to publish labels, error: {e}")
+
+    def get_pr_labels(self):
+        try:
+            labels = self.azure_devops_client.get_pull_request_labels(
+                project=self.workspace_slug,
+                repository_id=self.repo_slug,
+                pull_request_id=self.pr_num,
+            )
+            return [label.name for label in labels]
+        except Exception as e:
+            get_logger().exception(f"Failed to get labels, error: {e}")
+            return []
+
    def is_supported(self, capability: str) -> bool:
-        if capability in ['get_issue_comments', 'create_inline_comment', 'publish_inline_comments', 'get_labels',
-                          'remove_initial_comment', 'gfm_markdown']:
+        if capability in [
+            "get_issue_comments",
+            "create_inline_comment",
+            "publish_inline_comments",
+        ]:
            return False
        return True

@ -49,26 +174,35 @@ class AzureDevopsProvider:

    def get_repo_settings(self):
        try:
-            contents = self.azure_devops_client.get_item_content(repository_id=self.repo_slug,
-                                                                 project=self.workspace_slug, download=False,
-                                                                 include_content_metadata=False, include_content=True,
-                                                                 path=".pr_agent.toml")
+            contents = self.azure_devops_client.get_item_content(
+                repository_id=self.repo_slug,
+                project=self.workspace_slug,
+                download=False,
+                include_content_metadata=False,
+                include_content=True,
+                path=".pr_agent.toml",
+            )
            return contents
        except Exception as e:
-            get_logger().exception("get repo settings error")
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().error(f"Failed to get repo settings, error: {e}")
            return ""

    def get_files(self):
        files = []
-        for i in self.azure_devops_client.get_pull_request_commits(project=self.workspace_slug,
+        for i in self.azure_devops_client.get_pull_request_commits(
+                project=self.workspace_slug,
                repository_id=self.repo_slug,
-                                                                   pull_request_id=self.pr_num):
-
-            changes_obj = self.azure_devops_client.get_changes(project=self.workspace_slug,
-                                                               repository_id=self.repo_slug, commit_id=i.commit_id)
+                pull_request_id=self.pr_num,
+        ):
+            changes_obj = self.azure_devops_client.get_changes(
+                project=self.workspace_slug,
+                repository_id=self.repo_slug,
+                commit_id=i.commit_id,
+            )

            for c in changes_obj.changes:
-                files.append(c['item']['path'])
+                files.append(c["item"]["path"])
        return list(set(files))

    def get_diff_files(self) -> list[FilePatchInfo]:
@ -76,22 +210,27 @@ class AzureDevopsProvider:
            base_sha = self.pr.last_merge_target_commit
            head_sha = self.pr.last_merge_source_commit

-            commits = self.azure_devops_client.get_pull_request_commits(project=self.workspace_slug,
+            commits = self.azure_devops_client.get_pull_request_commits(
+                project=self.workspace_slug,
                repository_id=self.repo_slug,
-                                                                        pull_request_id=self.pr_num)
+                pull_request_id=self.pr_num,
+            )

            diff_files = []
            diffs = []
            diff_types = {}

            for c in commits:
-                changes_obj = self.azure_devops_client.get_changes(project=self.workspace_slug,
-                                                                   repository_id=self.repo_slug, commit_id=c.commit_id)
+                changes_obj = self.azure_devops_client.get_changes(
+                    project=self.workspace_slug,
+                    repository_id=self.repo_slug,
+                    commit_id=c.commit_id,
+                )
                for i in changes_obj.changes:
-                    if(i['item']['gitObjectType'] == 'tree'):
+                    if i["item"]["gitObjectType"] == "tree":
                        continue
-                    diffs.append(i['item']['path'])
-                    diff_types[i['item']['path']] = i['changeType']
+                    diffs.append(i["item"]["path"])
+                    diff_types[i["item"]["path"]] = i["changeType"]

            diffs = list(set(diffs))

@ -99,49 +238,73 @@ class AzureDevopsProvider:
                if not is_valid_file(file):
                    continue

-                version = GitVersionDescriptor(version=head_sha.commit_id, version_type='commit')
+                version = GitVersionDescriptor(
+                    version=head_sha.commit_id, version_type="commit"
+                )
                try:
-                    new_file_content_str = self.azure_devops_client.get_item(repository_id=self.repo_slug,
+                    new_file_content_str = self.azure_devops_client.get_item(
+                        repository_id=self.repo_slug,
                        path=file,
                        project=self.workspace_slug,
                        version_descriptor=version,
                        download=False,
-                                                                            include_content=True)
+                        include_content=True,
+                    )

                    new_file_content_str = new_file_content_str.content
                except Exception as error:
-                    get_logger().error("Failed to retrieve new file content of %s at version %s. Error: %s", file, version, str(error))
+                    get_logger().error(
+                        "Failed to retrieve new file content of %s at version %s. Error: %s",
+                        file,
+                        version,
+                        str(error),
+                    )
                    new_file_content_str = ""

                edit_type = EDIT_TYPE.MODIFIED
-                if diff_types[file] == 'add':
+                if diff_types[file] == "add":
                    edit_type = EDIT_TYPE.ADDED
-                elif diff_types[file] == 'delete':
+                elif diff_types[file] == "delete":
                    edit_type = EDIT_TYPE.DELETED
-                elif diff_types[file] == 'rename':
+                elif diff_types[file] == "rename":
                    edit_type = EDIT_TYPE.RENAMED

-                version = GitVersionDescriptor(version=base_sha.commit_id, version_type='commit')
+                version = GitVersionDescriptor(
+                    version=base_sha.commit_id, version_type="commit"
+                )
                try:
-                    original_file_content_str = self.azure_devops_client.get_item(repository_id=self.repo_slug,
+                    original_file_content_str = self.azure_devops_client.get_item(
+                        repository_id=self.repo_slug,
                        path=file,
                        project=self.workspace_slug,
                        version_descriptor=version,
                        download=False,
-                                                                              include_content=True)
+                        include_content=True,
+                    )
                    original_file_content_str = original_file_content_str.content
                except Exception as error:
-                    get_logger().error("Failed to retrieve original file content of %s at version %s. Error: %s", file, version, str(error))
+                    get_logger().error(
+                        "Failed to retrieve original file content of %s at version %s. Error: %s",
+                        file,
+                        version,
+                        str(error),
+                    )
                    original_file_content_str = ""

-                patch = load_large_diff(file, new_file_content_str, original_file_content_str)
+                patch = load_large_diff(
+                    file, new_file_content_str, original_file_content_str
+                )

-                diff_files.append(FilePatchInfo(original_file_content_str, new_file_content_str,
+                diff_files.append(
+                    FilePatchInfo(
+                        original_file_content_str,
+                        new_file_content_str,
                        patch=patch,
                        filename=file,
-                                                edit_type=edit_type))
+                        edit_type=edit_type,
+                    )
+                )

-            self.diff_files = diff_files
            return diff_files
        except Exception as e:
            print(f"Error: {str(e)}")
@ -150,67 +313,92 @@ class AzureDevopsProvider:
    def publish_comment(self, pr_comment: str, is_temporary: bool = False):
        comment = Comment(content=pr_comment)
        thread = CommentThread(comments=[comment])
-        thread_response = self.azure_devops_client.create_thread(comment_thread=thread, project=self.workspace_slug,
+        thread_response = self.azure_devops_client.create_thread(
+            comment_thread=thread,
+            project=self.workspace_slug,
            repository_id=self.repo_slug,
-                                                                 pull_request_id=self.pr_num)
+            pull_request_id=self.pr_num,
+        )
        if is_temporary:
-            self.temp_comments.append({'thread_id': thread_response.id, 'comment_id': comment.id})
+            self.temp_comments.append(
+                {"thread_id": thread_response.id, "comment_id": thread_response.comments[0].id}
+            )

    def publish_description(self, pr_title: str, pr_body: str):
        try:
            updated_pr = GitPullRequest()
            updated_pr.title = pr_title
            updated_pr.description = pr_body
-            self.azure_devops_client.update_pull_request(project=self.workspace_slug,
+            self.azure_devops_client.update_pull_request(
+                project=self.workspace_slug,
                repository_id=self.repo_slug,
                pull_request_id=self.pr_num,
-                                                         git_pull_request_to_update=updated_pr)
+                git_pull_request_to_update=updated_pr,
+            )
        except Exception as e:
-            get_logger().exception(f"Could not update pull request {self.pr_num} description: {e}")
+            get_logger().exception(
+                f"Could not update pull request {self.pr_num} description: {e}"
+            )

    def remove_initial_comment(self):
-        return ""  # not implemented yet
+        try:
+            for comment in self.temp_comments:
+                self.remove_comment(comment)
+        except Exception as e:
+            get_logger().exception(f"Failed to remove temp comments, error: {e}")

-    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
-        raise NotImplementedError("Azure DevOps provider does not support publishing inline comment yet")
-
-    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
-        raise NotImplementedError("Azure DevOps provider does not support creating inline comments yet")
+    def publish_inline_comment(
+            self, body: str, relevant_file: str, relevant_line_in_file: str
+    ):
+        raise NotImplementedError(
+            "Azure DevOps provider does not support publishing inline comment yet"
+        )

    def publish_inline_comments(self, comments: list[dict]):
-        raise NotImplementedError("Azure DevOps provider does not support publishing inline comments yet")
+        raise NotImplementedError(
+            "Azure DevOps provider does not support publishing inline comments yet"
+        )

    def get_title(self):
        return self.pr.title

    def get_languages(self):
        languages = []
-        files = self.azure_devops_client.get_items(project=self.workspace_slug, repository_id=self.repo_slug,
-                                                   recursion_level="Full", include_content_metadata=True,
-                                                   include_links=False, download=False)
+        files = self.azure_devops_client.get_items(
+            project=self.workspace_slug,
+            repository_id=self.repo_slug,
+            recursion_level="Full",
+            include_content_metadata=True,
+            include_links=False,
+            download=False,
+        )
        for f in files:
-            if f.git_object_type == 'blob':
+            if f.git_object_type == "blob":
                file_name, file_extension = os.path.splitext(f.path)
                languages.append(file_extension[1:])

        extension_counts = {}
        for ext in languages:
-            if ext != '':
+            if ext != "":
                extension_counts[ext] = extension_counts.get(ext, 0) + 1

        total_extensions = sum(extension_counts.values())

-        extension_percentages = {ext: (count / total_extensions) * 100 for ext, count in extension_counts.items()}
+        extension_percentages = {
+            ext: (count / total_extensions) * 100
+            for ext, count in extension_counts.items()
+        }

        return extension_percentages

    def get_pr_branch(self):
-        pr_info = self.azure_devops_client.get_pull_request_by_id(project=self.workspace_slug,
-                                                                  pull_request_id=self.pr_num)
-        source_branch = pr_info.source_ref_name.split('/')[-1]
+        pr_info = self.azure_devops_client.get_pull_request_by_id(
+            project=self.workspace_slug, pull_request_id=self.pr_num
+        )
+        source_branch = pr_info.source_ref_name.split("/")[-1]
        return source_branch

-    def get_pr_description(self):
+    def get_pr_description(self, *, full: bool = True) -> str:
        max_tokens = get_settings().get("CONFIG.MAX_DESCRIPTION_TOKENS", None)
        if max_tokens:
            return clip_tokens(self.pr.description, max_tokens)
@ -220,7 +408,9 @@ class AzureDevopsProvider:
        return 0

    def get_issue_comments(self):
-        raise NotImplementedError("Azure DevOps provider does not support issue comments yet")
+        raise NotImplementedError(
+            "Azure DevOps provider does not support issue comments yet"
+        )

    def add_eyes_reaction(self, issue_comment_id: int) -> Optional[int]:
        return True
@ -228,17 +418,16 @@ class AzureDevopsProvider:
    def remove_reaction(self, issue_comment_id: int, reaction_id: int) -> bool:
        return True

-    def get_issue_comments(self):
-        raise NotImplementedError("Azure DevOps provider does not support issue comments yet")
-
    @staticmethod
-    def _parse_pr_url(pr_url: str) -> Tuple[str, int]:
+    def _parse_pr_url(pr_url: str) -> Tuple[str, str, int]:
        parsed_url = urlparse(pr_url)

-        path_parts = parsed_url.path.strip('/').split('/')
+        path_parts = parsed_url.path.strip("/").split("/")

-        if len(path_parts) < 6 or path_parts[4] != 'pullrequest':
-            raise ValueError("The provided URL does not appear to be a Azure DevOps PR URL")
+        if len(path_parts) < 6 or path_parts[4] != "pullrequest":
+            raise ValueError(
+                "The provided URL does not appear to be a Azure DevOps PR URL"
+            )

        workspace_slug = path_parts[1]
        repo_slug = path_parts[3]
@ -249,15 +438,15 @@ class AzureDevopsProvider:

        return workspace_slug, repo_slug, pr_number

-    def _get_azure_devops_client(self):
+    @staticmethod
+    def _get_azure_devops_client():
        try:
            pat = get_settings().azure_devops.pat
            org = get_settings().azure_devops.org
        except AttributeError as e:
-            raise ValueError(
-                "Azure DevOps PAT token is required ") from e
+            raise ValueError("Azure DevOps PAT token is required ") from e

-        credentials = BasicAuthentication('', pat)
+        credentials = BasicAuthentication("", pat)
        azure_devops_connection = Connection(base_url=org, creds=credentials)
        azure_devops_client = azure_devops_connection.clients.get_git_client()

@ -265,13 +454,25 @@ class AzureDevopsProvider:

    def _get_repo(self):
        if self.repo is None:
-            self.repo = self.azure_devops_client.get_repository(project=self.workspace_slug,
-                                                                repository_id=self.repo_slug)
+            self.repo = self.azure_devops_client.get_repository(
+                project=self.workspace_slug, repository_id=self.repo_slug
+            )
        return self.repo

    def _get_pr(self):
-        self.pr = self.azure_devops_client.get_pull_request_by_id(pull_request_id=self.pr_num, project=self.workspace_slug)
+        self.pr = self.azure_devops_client.get_pull_request_by_id(
+            pull_request_id=self.pr_num, project=self.workspace_slug
+        )
        return self.pr

    def get_commit_messages(self):
        return ""  # not implemented yet
+
+    def get_pr_id(self):
+        try:
+            pr_id = f"{self.workspace_slug}/{self.repo_slug}/{self.pr_num}"
+            return pr_id
+        except Exception as e:
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().error(f"Failed to get pr id, error: {e}")
+            return ""
--- a/pr_agent/git_providers/bitbucket_provider.py
+++ b/pr_agent/git_providers/bitbucket_provider.py
@ -201,8 +201,10 @@ class BitbucketProvider(GitProvider):
            get_logger().exception(f"Failed to remove comment, error: {e}")

    # funtion to create_inline_comment
-    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
-        position, absolute_position = find_line_number_of_relevant_line_in_file(self.get_diff_files(), relevant_file.strip('`'), relevant_line_in_file)
+    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str, absolute_position: int = None):
+        position, absolute_position = find_line_number_of_relevant_line_in_file(self.get_diff_files(),
+                                                                            relevant_file.strip('`'),
+                                                                            relevant_line_in_file, absolute_position)
        if position == -1:
            if get_settings().config.verbosity_level >= 2:
                get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
--- a/pr_agent/git_providers/bitbucket_server_provider.py
+++ b/pr_agent/git_providers/bitbucket_server_provider.py
@ -210,11 +210,14 @@ class BitbucketServerProvider(GitProvider):
        pass

    # funtion to create_inline_comment
-    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
+    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str,
+                              absolute_position: int = None):
+
        position, absolute_position = find_line_number_of_relevant_line_in_file(
            self.get_diff_files(),
            relevant_file.strip('`'),
-            relevant_line_in_file
+            relevant_line_in_file,
+            absolute_position
        )
        if position == -1:
            if get_settings().config.verbosity_level >= 2:
--- a/pr_agent/git_providers/codecommit_provider.py
+++ b/pr_agent/git_providers/codecommit_provider.py
@ -229,9 +229,6 @@ class CodeCommitProvider(GitProvider):
        # https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/post_comment_for_compared_commit.html
        raise NotImplementedError("CodeCommit provider does not support publishing inline comments yet")

-    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
-        raise NotImplementedError("CodeCommit provider does not support creating inline comments yet")
-
    def publish_inline_comments(self, comments: list[dict]):
        raise NotImplementedError("CodeCommit provider does not support publishing inline comments yet")

--- a/pr_agent/git_providers/gerrit_provider.py
+++ b/pr_agent/git_providers/gerrit_provider.py
@ -380,11 +380,6 @@ class GerritProvider(GitProvider):
            'Publishing inline comments is not implemented for the gerrit '
            'provider')

-    def create_inline_comment(self, body: str, relevant_file: str,
-                              relevant_line_in_file: str):
-        raise NotImplementedError(
-            'Creating inline comments is not implemented for the gerrit '
-            'provider')

    def publish_labels(self, labels):
        # Not applicable to the local git provider,
--- a/pr_agent/git_providers/git_provider.py
+++ b/pr_agent/git_providers/git_provider.py
@ -74,15 +74,51 @@ class GitProvider(ABC):

    def get_user_description(self) -> str:
        description = (self.get_pr_description_full() or "").strip()
+        description_lowercase = description.lower()
+        get_logger().info(f"Existing description:\n{description_lowercase}")
+
        # if the existing description wasn't generated by the pr-agent, just return it as-is
-        if not any(description.startswith(header) for header in ("## PR Type", "## PR Description")):
+        if not self._is_generated_by_pr_agent(description_lowercase):
+            get_logger().info(f"Existing description was not generated by the pr-agent")
            return description
-        # if the existing description was generated by the pr-agent, but it doesn't contain the user description,
+
+        # if the existing description was generated by the pr-agent, but it doesn't contain a user description,
        # return nothing (empty string) because it means there is no user description
-        if "## User Description:" not in description:
+        user_description_header = "## **user description**"
+        if user_description_header not in description_lowercase:
+            get_logger().info(f"Existing description was generated by the pr-agent, but it doesn't contain a user description")
            return ""
+
        # otherwise, extract the original user description from the existing pr-agent description and return it
-        return description.split("## User Description:", 1)[1].strip()
+        # user_description_start_position = description_lowercase.find(user_description_header) + len(user_description_header)
+        # return description[user_description_start_position:].split("\n", 1)[-1].strip()
+
+        # the 'user description' is in the beginning. extract and return it
+        possible_headers = self._possible_headers()
+        start_position = description_lowercase.find(user_description_header) + len(user_description_header)
+        end_position = len(description)
+        for header in possible_headers: # try to clip at the next header
+            if header != user_description_header and header in description_lowercase:
+                end_position = min(end_position, description_lowercase.find(header))
+        if end_position != len(description) and end_position > start_position:
+            original_user_description = description[start_position:end_position].strip()
+            if original_user_description.endswith("___"):
+                original_user_description = original_user_description[:-3].strip()
+        else:
+            original_user_description = description.split("___")[0].strip()
+            if original_user_description.lower().startswith(user_description_header):
+                original_user_description = original_user_description[len(user_description_header):].strip()
+
+        get_logger().info(f"Extracted user description from existing description:\n{original_user_description}")
+        return original_user_description
+
+    def _possible_headers(self):
+        return ("## **user description**", "## **pr type**", "## **pr description**", "## **pr labels**", "## **type**", "## **description**",
+                "## **labels**", "### 🤖 generated by pr agent")
+
+    def _is_generated_by_pr_agent(self, description_lowercase: str) -> bool:
+        possible_headers = self._possible_headers()
+        return any(description_lowercase.startswith(header) for header in possible_headers)

    @abstractmethod
    def get_repo_settings(self):
@ -106,9 +142,9 @@ class GitProvider(ABC):
    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
        pass

-    @abstractmethod
-    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
-        pass
+    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str,
+                              absolute_position: int = None):
+        raise NotImplementedError("This git provider does not support creating inline comments yet")

    @abstractmethod
    def publish_inline_comments(self, comments: list[dict]):
--- a/pr_agent/git_providers/github_provider.py
+++ b/pr_agent/git_providers/github_provider.py
@ -1,3 +1,4 @@
+import time
 import hashlib
 from datetime import datetime
 from typing import Optional, Tuple
@ -206,8 +207,12 @@ class GithubProvider(GitProvider):
        self.publish_inline_comments([self.create_inline_comment(body, relevant_file, relevant_line_in_file)])


-    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
-        position, absolute_position = find_line_number_of_relevant_line_in_file(self.diff_files, relevant_file.strip('`'), relevant_line_in_file)
+    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str,
+                              absolute_position: int = None):
+        position, absolute_position = find_line_number_of_relevant_line_in_file(self.diff_files,
+                                                                                relevant_file.strip('`'),
+                                                                                relevant_line_in_file,
+                                                                                absolute_position)
        if position == -1:
            if get_settings().config.verbosity_level >= 2:
                get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
@ -217,8 +222,114 @@ class GithubProvider(GitProvider):
        path = relevant_file.strip()
        return dict(body=body, path=path, position=position) if subject_type == "LINE" else {}

-    def publish_inline_comments(self, comments: list[dict]):
+    def publish_inline_comments(self, comments: list[dict], disable_fallback: bool = False):
+        try:
+            # publish all comments in a single message
            self.pr.create_review(commit=self.last_commit_id, comments=comments)
+        except Exception as e:
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().error(f"Failed to publish inline comments")
+
+            if (getattr(e, "status", None) == 422
+                    and get_settings().github.publish_inline_comments_fallback_with_verification and not disable_fallback):
+                pass  # continue to try _publish_inline_comments_fallback_with_verification
+            else:
+                raise e # will end up with publishing the comments one by one
+
+            try:
+                self._publish_inline_comments_fallback_with_verification(comments)
+            except Exception as e:
+                if get_settings().config.verbosity_level >= 2:
+                    get_logger().error(f"Failed to publish inline code comments fallback, error: {e}")
+                raise e
+
+    def _publish_inline_comments_fallback_with_verification(self, comments: list[dict]):
+        """
+        Check each inline comment separately against the GitHub API and discard of invalid comments,
+        then publish all the remaining valid comments in a single review.
+        For invalid comments, also try removing the suggestion part and posting the comment just on the first line.
+        """
+        verified_comments, invalid_comments = self._verify_code_comments(comments)
+
+        # publish as a group the verified comments
+        if verified_comments:
+            try:
+                self.pr.create_review(commit=self.last_commit_id, comments=verified_comments)
+            except:
+                pass
+
+        # try to publish one by one the invalid comments as a one-line code comment
+        if invalid_comments and get_settings().github.try_fix_invalid_inline_comments:
+            fixed_comments_as_one_liner = self._try_fix_invalid_inline_comments(
+                [comment for comment, _ in invalid_comments])
+            for comment in fixed_comments_as_one_liner:
+                try:
+                    self.publish_inline_comments([comment], disable_fallback=True)
+                    if get_settings().config.verbosity_level >= 2:
+                        get_logger().info(f"Published invalid comment as a single line comment: {comment}")
+                except:
+                    if get_settings().config.verbosity_level >= 2:
+                        get_logger().error(f"Failed to publish invalid comment as a single line comment: {comment}")
+
+    def _verify_code_comment(self, comment: dict):
+        is_verified = False
+        e = None
+        try:
+            # event ="" # By leaving this blank, you set the review action state to PENDING
+            input = dict(commit_id=self.last_commit_id.sha, comments=[comment])
+            headers, data = self.pr._requester.requestJsonAndCheck(
+                "POST", f"{self.pr.url}/reviews", input=input)
+            pending_review_id = data["id"]
+            is_verified = True
+        except Exception as err:
+            is_verified = False
+            pending_review_id = None
+            e = err
+        if pending_review_id is not None:
+            try:
+                self.pr._requester.requestJsonAndCheck("DELETE", f"{self.pr.url}/reviews/{pending_review_id}")
+            except Exception:
+                pass
+        return is_verified, e
+
+    def _verify_code_comments(self, comments: list[dict]) -> tuple[list[dict], list[tuple[dict, Exception]]]:
+        """Very each comment against the GitHub API and return 2 lists: 1 of verified and 1 of invalid comments"""
+        verified_comments = []
+        invalid_comments = []
+        for comment in comments:
+            time.sleep(1)  # for avoiding secondary rate limit
+            is_verified, e = self._verify_code_comment(comment)
+            if is_verified:
+                verified_comments.append(comment)
+            else:
+                invalid_comments.append((comment, e))
+        return verified_comments, invalid_comments
+
+    def _try_fix_invalid_inline_comments(self, invalid_comments: list[dict]) -> list[dict]:
+        """
+        Try fixing invalid comments by removing the suggestion part and setting the comment just on the first line.
+        Return only comments that have been modified in some way.
+        This is a best-effort attempt to fix invalid comments, and should be verified accordingly.
+        """
+        import copy
+        fixed_comments = []
+        for comment in invalid_comments:
+            try:
+                fixed_comment = copy.deepcopy(comment)  # avoid modifying the original comment dict for later logging
+                if "```suggestion" in comment["body"]:
+                    fixed_comment["body"] = comment["body"].split("```suggestion")[0]
+                if "start_line" in comment:
+                    fixed_comment["line"] = comment["start_line"]
+                    del fixed_comment["start_line"]
+                if "start_side" in comment:
+                    fixed_comment["side"] = comment["start_side"]
+                    del fixed_comment["start_side"]
+                if fixed_comment != comment:
+                    fixed_comments.append(fixed_comment)
+            except Exception as e:
+                if get_settings().config.verbosity_level >= 2:
+                    get_logger().error(f"Failed to fix inline comment, error: {e}")
+        return fixed_comments

    def publish_code_suggestions(self, code_suggestions: list) -> bool:
        """
@ -262,7 +373,7 @@ class GithubProvider(GitProvider):
            post_parameters_list.append(post_parameters)

        try:
-            self.pr.create_review(commit=self.last_commit_id, comments=post_parameters_list)
+            self.publish_inline_comments(post_parameters_list)
            return True
        except Exception as e:
            if get_settings().config.verbosity_level >= 2:
--- a/pr_agent/git_providers/gitlab_provider.py
+++ b/pr_agent/git_providers/gitlab_provider.py
@ -183,7 +183,7 @@ class GitLabProvider(GitProvider):
        self.send_inline_comment(body, edit_type, found, relevant_file, relevant_line_in_file, source_line_no,
                                 target_file, target_line_no)

-    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
+    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str, absolute_position: int = None):
        raise NotImplementedError("Gitlab provider does not support creating inline comments yet")

    def create_inline_comments(self, comments: list[dict]):
@ -411,6 +411,9 @@ class GitLabProvider(GitProvider):
    def get_pr_labels(self):
        return self.mr.labels

+    def get_repo_labels(self):
+        return self.gl.projects.get(self.id_project).labels.list()
+
    def get_commit_messages(self):
        """
        Retrieves the commit messages of a pull request.
@ -437,11 +440,11 @@ class GitLabProvider(GitProvider):

    def get_line_link(self, relevant_file: str, relevant_line_start: int, relevant_line_end: int = None) -> str:
        if relevant_line_start == -1:
-            link = f"https://gitlab.com/codiumai/pr-agent/-/blob/{self.mr.source_branch}/{relevant_file}?ref_type=heads"
+            link = f"{self.gl.url}/{self.id_project}/-/blob/{self.mr.source_branch}/{relevant_file}?ref_type=heads"
        elif relevant_line_end:
-            link = f"https://gitlab.com/codiumai/pr-agent/-/blob/{self.mr.source_branch}/{relevant_file}?ref_type=heads#L{relevant_line_start}-L{relevant_line_end}"
+            link = f"{self.gl.url}/{self.id_project}/-/blob/{self.mr.source_branch}/{relevant_file}?ref_type=heads#L{relevant_line_start}-L{relevant_line_end}"
        else:
-            link = f"https://gitlab.com/codiumai/pr-agent/-/blob/{self.mr.source_branch}/{relevant_file}?ref_type=heads#L{relevant_line_start}"
+            link = f"{self.gl.url}/{self.id_project}/-/blob/{self.mr.source_branch}/{relevant_file}?ref_type=heads#L{relevant_line_start}"
        return link


@ -457,7 +460,7 @@ class GitLabProvider(GitProvider):

            if absolute_position != -1:
                # link to right file only
-                link = f"https://gitlab.com/codiumai/pr-agent/-/blob/{self.mr.source_branch}/{relevant_file}?ref_type=heads#L{absolute_position}"
+                link = f"{self.gl.url}/{self.id_project}/-/blob/{self.mr.source_branch}/{relevant_file}?ref_type=heads#L{absolute_position}"

                # # link to diff
                # sha_file = hashlib.sha1(relevant_file.encode('utf-8')).hexdigest()
--- a/pr_agent/git_providers/local_git_provider.py
+++ b/pr_agent/git_providers/local_git_provider.py
@ -121,9 +121,6 @@ class LocalGitProvider(GitProvider):
    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
        raise NotImplementedError('Publishing inline comments is not implemented for the local git provider')

-    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
-        raise NotImplementedError('Creating inline comments is not implemented for the local git provider')
-
    def publish_inline_comments(self, comments: list[dict]):
        raise NotImplementedError('Publishing inline comments is not implemented for the local git provider')

--- a/pr_agent/servers/bitbucket_server_webhook.py
+++ b/pr_agent/servers/bitbucket_server_webhook.py
@ -1,4 +1,5 @@
 import json
+import os

 import uvicorn
 from fastapi import APIRouter, FastAPI
@ -13,35 +14,55 @@ from starlette_context.middleware import RawContextMiddleware
 from pr_agent.agent.pr_agent import PRAgent
 from pr_agent.config_loader import get_settings
 from pr_agent.log import get_logger
+from pr_agent.servers.utils import verify_signature

 router = APIRouter()


-def handle_request(background_tasks: BackgroundTasks, url: str, body: str, log_context: dict):
+def handle_request(
+    background_tasks: BackgroundTasks, url: str, body: str, log_context: dict
+):
    log_context["action"] = body
-    log_context["event"] = "pull_request" if body == "review" else "comment"
    log_context["api_url"] = url
    with get_logger().contextualize(**log_context):
        background_tasks.add_task(PRAgent().handle_request, url, body)


-@router.post("/webhook")
+@router.post("/")
 async def handle_webhook(background_tasks: BackgroundTasks, request: Request):
    log_context = {"server_type": "bitbucket_server"}
    data = await request.json()
    get_logger().info(json.dumps(data))

-    pr_id = data['pullRequest']['id']
-    repository_name = data['pullRequest']['toRef']['repository']['slug']
-    project_name = data['pullRequest']['toRef']['repository']['project']['key']
+    webhook_secret = get_settings().get("BITBUCKET_SERVER.WEBHOOK_SECRET", None)
+    if webhook_secret:
+        body_bytes = await request.body()
+        signature_header = request.headers.get("x-hub-signature", None)
+        verify_signature(body_bytes, webhook_secret, signature_header)
+
+    pr_id = data["pullRequest"]["id"]
+    repository_name = data["pullRequest"]["toRef"]["repository"]["slug"]
+    project_name = data["pullRequest"]["toRef"]["repository"]["project"]["key"]
    bitbucket_server = get_settings().get("BITBUCKET_SERVER.URL")
    pr_url = f"{bitbucket_server}/projects/{project_name}/repos/{repository_name}/pull-requests/{pr_id}"

    log_context["api_url"] = pr_url
    log_context["event"] = "pull_request"

-    handle_request(background_tasks, pr_url, "review", log_context)
-    return JSONResponse(status_code=status.HTTP_200_OK, content=jsonable_encoder({"message": "success"}))
+    if data["eventKey"] == "pr:opened":
+        body = "review"
+    elif data["eventKey"] == "pr:comment:added":
+        body = data["comment"]["text"]
+    else:
+        return JSONResponse(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            content=json.dumps({"message": "Unsupported event"}),
+        )
+
+    handle_request(background_tasks, pr_url, body, log_context)
+    return JSONResponse(
+        status_code=status.HTTP_200_OK, content=jsonable_encoder({"message": "success"})
+    )


@router.get("/")
@ -50,15 +71,10 @@ async def root():


 def start():
-    bitbucket_server_url = get_settings().get("BITBUCKET_SERVER.URL", None)
-    if not bitbucket_server_url:
-        raise ValueError("BITBUCKET_SERVER.URL is not set")
-    get_settings().config.git_provider = "bitbucket_server"
-    middleware = [Middleware(RawContextMiddleware)]
-    app = FastAPI(middleware=middleware)
+    app = FastAPI(middleware=[Middleware(RawContextMiddleware)])
    app.include_router(router)
-    uvicorn.run(app, host="0.0.0.0", port=3000)
+    uvicorn.run(app, host="0.0.0.0", port=int(os.environ.get("PORT", "3000")))


-if __name__ == '__main__':
+if __name__ == "__main__":
    start()
--- a/pr_agent/servers/github_action_runner.py
+++ b/pr_agent/servers/github_action_runner.py
@ -82,14 +82,23 @@ async def run_action():
        if action in ["opened", "reopened"]:
            pr_url = event_payload.get("pull_request", {}).get("url")
            if pr_url:
+                # legacy - supporting both GITHUB_ACTION and GITHUB_ACTION_CONFIG
                auto_review = get_setting_or_env("GITHUB_ACTION.AUTO_REVIEW", None)
+                if auto_review is None:
+                    auto_review = get_setting_or_env("GITHUB_ACTION_CONFIG.AUTO_REVIEW", None)
+                auto_describe = get_setting_or_env("GITHUB_ACTION.AUTO_DESCRIBE", None)
+                if auto_describe is None:
+                    auto_describe = get_setting_or_env("GITHUB_ACTION_CONFIG.AUTO_DESCRIBE", None)
+                auto_improve = get_setting_or_env("GITHUB_ACTION.AUTO_IMPROVE", None)
+                if auto_improve is None:
+                    auto_improve = get_setting_or_env("GITHUB_ACTION_CONFIG.AUTO_IMPROVE", None)
+
+                # invoke by default all three tools
+                if auto_describe is None or is_true(auto_describe):
+                    await PRDescription(pr_url).run()
                if auto_review is None or is_true(auto_review):
                    await PRReviewer(pr_url).run()
-                auto_describe = get_setting_or_env("GITHUB_ACTION.AUTO_DESCRIBE", None)
-                if is_true(auto_describe):
-                    await PRDescription(pr_url).run()
-                auto_improve = get_setting_or_env("GITHUB_ACTION.AUTO_IMPROVE", None)
-                if is_true(auto_improve):
+                if auto_improve is None or is_true(auto_improve):
                    await PRCodeSuggestions(pr_url).run()

    # Handle issue comment event
--- a/pr_agent/servers/github_polling.py
+++ b/pr_agent/servers/github_polling.py
@ -7,7 +7,6 @@ from pr_agent.agent.pr_agent import PRAgent
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
 from pr_agent.log import LoggingFormat, get_logger, setup_logger
-from pr_agent.servers.help import bot_help_text

 setup_logger(fmt=LoggingFormat.JSON)
 NOTIFICATION_URL = "https://api.github.com/notifications"
@ -104,8 +103,6 @@ async def polling_loop():
                                                                                 notify=lambda: git_provider.add_eyes_reaction(comment_id))  # noqa E501
                                            if not success:
                                                git_provider.set_pr(pr_url)
-                                                git_provider.publish_comment("### How to use PR-Agent\n" +
-                                                                             bot_help_text(user_id))

                    elif response.status != 304:
                        print(f"Failed to fetch notifications. Status code: {response.status}")
--- a/pr_agent/servers/help.py
+++ b/pr_agent/servers/help.py
@ -1,19 +1,328 @@
-commands_text = "> **/review**: Request a review of your Pull Request.   \n" \
-                "> **/describe**: Update the PR title and description based on the contents of the PR.   \n" \
-                "> **/improve [--extended]**: Suggest code improvements. Extended mode provides a higher quality feedback.   \n" \
-                "> **/ask \\<QUESTION\\>**: Ask a question about the PR.   \n" \
-                "> **/update_changelog**: Update the changelog based on the PR's contents.   \n" \
-                "> **/add_docs**: Generate docstring for new components introduced in the PR.   \n" \
-                "> **/generate_labels**: Generate labels for the PR based on the PR's contents.   \n" \
-                "> see the [tools guide](https://github.com/Codium-ai/pr-agent/blob/main/docs/TOOLS_GUIDE.md) for more details.\n\n" \
-                ">To edit any configuration parameter from the [configuration.toml](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml), add --config_path=new_value.  \n" \
-                ">For example: /review --pr_reviewer.extra_instructions=\"focus on the file: ...\"    \n" \
-                ">To list the possible configuration parameters, add a **/config** comment.   \n" \
+class HelpMessage:
+    @staticmethod
+    def get_general_commands_text():
+       commands_text = "> - **/review**: Request a review of your Pull Request.   \n" \
+                "> - **/describe**: Update the PR title and description based on the contents of the PR.   \n" \
+                "> - **/improve [--extended]**: Suggest code improvements. Extended mode provides a higher quality feedback.   \n" \
+                "> - **/ask \\<QUESTION\\>**: Ask a question about the PR.   \n" \
+                "> - **/update_changelog**: Update the changelog based on the PR's contents.   \n" \
+                "> - **/add_docs** 💎: Generate docstring for new components introduced in the PR.   \n" \
+                "> - **/generate_labels** 💎: Generate labels for the PR based on the PR's contents.   \n" \
+                "> - **/analyze** 💎: Automatically analyzes the PR, and presents changes walkthrough for each component.   \n\n" \
+                ">See the [tools guide](https://github.com/Codium-ai/pr-agent/blob/main/docs/TOOLS_GUIDE.md) for more details.\n" \
+                ">To list the possible configuration parameters, add a **/config** comment.   \n"
+       return commands_text


-def bot_help_text(user: str):
-    return f"> Tag me in a comment '@{user}' and add one of the following commands:  \n" + commands_text
+    @staticmethod
+    def get_general_bot_help_text():
+        output = f"> To invoke the PR-Agent, add a comment using one of the following commands:  \n{HelpMessage.get_general_commands_text()} \n"
+        return output
+
+    @staticmethod
+    def get_review_usage_guide():
+        output ="**Overview:**\n"
+        output +="The `review` tool scans the PR code changes, and generates a PR review. The tool can be triggered [automatically](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools) every time a new PR is opened, or can be invoked manually by commenting on any PR.\n"
+        output +="""\
+When commenting, to edit [configurations](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L19) related to the review tool (`pr_reviewer` section), use the following template:
+```
+/review --pr_reviewer.some_config1=... --pr_reviewer.some_config2=...
+```
+With a [configuration file](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#working-with-github-app), use the following template:
+```
+[pr_reviewer]
+some_config1=...
+some_config2=...
+```
+    """
+        output +="\n\n<table>"
+
+        # extra instructions
+        output += "<tr><td><details> <summary><strong> Utilizing extra instructions</strong></summary><hr>\n\n"
+        output += '''\
+The `review` tool can be configured with extra instructions, which can be used to guide the model to a feedback tailored to the needs of your project.
+
+Be specific, clear, and concise in the instructions. With extra instructions, you are the prompter. Specify the relevant sub-tool, and the relevant aspects of the PR that you want to emphasize.
+
+Examples for extra instructions:
+```
+[pr_reviewer] # /review #
+extra_instructions="""
+In the 'general suggestions' section, emphasize the following:
+- 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.
+        '''
+        output += "\n\n</details></td></tr>\n\n"
+
+        # automation
+        output += "<tr><td><details> <summary><strong> How to enable\\disable automation</strong></summary><hr>\n\n"
+        output += """\
+- When you first install PR-Agent app, the [default mode](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools) for the `review` tool is:
+```
+pr_commands = ["/review", ...]
+```
+meaning the `review` tool will run automatically on every PR, with the default configuration.
+Edit this field to enable/disable the tool, or to change the used configurations
+        """
+        output += "\n\n</details></td></tr>\n\n"
+
+#         # code feedback
+#         output += "<tr><td><details> <summary><strong> About the 'Code feedback' section</strong></summary><hr>\n\n"
+#         output+="""\
+# The `review` tool provides several type of feedbacks, one of them is code suggestions.
+# If you are interested **only** in the code suggestions, it is recommended to use the [`improve`](https://github.com/Codium-ai/pr-agent/blob/main/docs/IMPROVE.md) feature instead, since it dedicated only to code suggestions, and usually gives better results.
+# Use the `review` tool if you want to get a more comprehensive feedback, which includes code suggestions as well.
+# """
+#         output += "\n\n</details></td></tr>\n\n"
+
+        # auto-labels
+        output += "<tr><td><details> <summary><strong> Auto-labels</strong></summary><hr>\n\n"
+        output+="""\
+The `review` tool can auto-generate two specific types of labels for a PR:
+- a `possible security issue` label, that detects possible [security issues](https://github.com/Codium-ai/pr-agent/blob/tr/user_description/pr_agent/settings/pr_reviewer_prompts.toml#L136) (`enable_review_labels_security` flag)
+- a `Review effort [1-5]: x` label, where x is the estimated effort to review the PR (`enable_review_labels_effort` flag)
+"""
+        output += "\n\n</details></td></tr>\n\n"
+
+        # extra sub-tools
+        output += "<tr><td><details> <summary><strong> Extra sub-tools</strong></summary><hr>\n\n"
+        output += """\
+The `review` tool provides a collection of possible feedbacks about a PR.
+It is recommended to review the [possible options](https://github.com/Codium-ai/pr-agent/blob/main/docs/REVIEW.md#enabledisable-features), and choose the ones relevant for your use case.
+Some of the feature that are disabled by default are quite useful, and should be considered for enabling. For example: 
+`require_score_review`, `require_soc2_ticket`, and more.
+"""
+        output += "\n\n</details></td></tr>\n\n"
+
+        # general
+        output += "\n\n<tr><td><details> <summary><strong> More PR-Agent commands</strong></summary><hr> \n\n"
+        output += HelpMessage.get_general_bot_help_text()
+        output += "\n\n</details></td></tr>\n\n"
+
+        output += "</table>"
+
+        output += f"\n\nSee the [review usage](https://github.com/Codium-ai/pr-agent/blob/main/docs/REVIEW.md) page for a comprehensive guide on using this tool.\n\n"
+
+        return output


-actions_help_text = "> To invoke the PR-Agent, add a comment using one of the following commands:  \n" + \
-                    commands_text
+
+    @staticmethod
+    def get_describe_usage_guide():
+        output = "**Overview:**\n"
+        output += "The `describe` tool scans the PR code changes, and generates a description for the PR - title, type, summary, walkthrough and labels. "
+        output += "The tool can be triggered [automatically](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools) every time a new PR is opened, or can be invoked manually by commenting on a PR.\n"
+        output += """\
+
+When commenting, to edit [configurations](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L46) related to the describe tool (`pr_description` section), use the following template:
+```
+/describe --pr_description.some_config1=... --pr_description.some_config2=...
+```
+With a [configuration file](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#working-with-github-app), use the following template:
+```
+[pr_description]
+some_config1=...
+some_config2=...
+```
+"""
+        output += "\n\n<table>"
+
+        # automation
+        output += "<tr><td><details> <summary><strong> Enabling\\disabling automation </strong></summary><hr>\n\n"
+        output += """\
+- When you first install the app, the [default mode](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools) for the describe tool is:
+```
+pr_commands = ["/describe --pr_description.add_original_user_description=true" 
+                         "--pr_description.keep_original_user_title=true", ...]
+```
+meaning the `describe` tool will run automatically on every PR, will keep the original title, and will add the original user description above the generated description. 
+
+- Markers are an alternative way to control the generated description, to give maximal control to the user. If you set:
+```
+pr_commands = ["/describe --pr_description.use_description_markers=true", ...]
+```
+the tool will replace every marker of the form `pr_agent:marker_name` in the PR description with the relevant content, where `marker_name` is one of the following:
+  - `type`: the PR type.
+  - `summary`: the PR summary.
+  - `walkthrough`: the PR walkthrough.
+
+Note that when markers are enabled, if the original PR description does not contain any markers, the tool will not alter the description at all.
+        
+"""
+        output += "\n\n</details></td></tr>\n\n"
+
+        # custom labels
+        output += "<tr><td><details> <summary><strong> Custom labels </strong></summary><hr>\n\n"
+        output += """\
+The default labels of the `describe` tool are quite generic: [`Bug fix`, `Tests`, `Enhancement`, `Documentation`, `Other`].
+
+If you specify [custom labels](https://github.com/Codium-ai/pr-agent/blob/main/docs/DESCRIBE.md#handle-custom-labels-from-the-repos-labels-page-gem) in the repo's labels page or via configuration file, you can get tailored labels for your use cases.
+Examples for custom labels:
+- `Main topic:performance` - pr_agent:The main topic of this PR is performance
+- `New endpoint` - pr_agent:A new endpoint was added in this PR
+- `SQL query` - pr_agent:A new SQL query was added in this PR
+- `Dockerfile changes` - pr_agent:The PR contains changes in the Dockerfile
+- ...
+
+The list above is eclectic, and aims to give an idea of different possibilities. Define custom labels that are relevant for your repo and use cases.
+Note that Labels are not mutually exclusive, so you can add multiple label categories.
+Make sure to provide proper title, and a detailed and well-phrased description for each label, so the tool will know when to suggest it.        
+"""
+        output += "\n\n</details></td></tr>\n\n"
+
+        # Inline File Walkthrough
+        output += "<tr><td><details> <summary><strong> Inline File Walkthrough 💎</strong></summary><hr>\n\n"
+        output += """\
+For enhanced user experience, the `describe` tool can add file summaries directly to the "Files changed" tab in the PR page.
+This will enable you to quickly understand the changes in each file, while reviewing the code changes (diffs).
+
+To enable inline file summary, set `pr_description.inline_file_summary` in the configuration file, possible values are:
+- `'table'`: File changes walkthrough table will be displayed on the top of the "Files changed" tab, in addition to the "Conversation" tab.
+- `true`: A collapsable file comment with changes title and a changes summary for each file in the PR.
+- `false` (default): File changes walkthrough will be added only to the "Conversation" tab.
+"""
+        # extra instructions
+        output += "<tr><td><details> <summary><strong> Utilizing extra instructions</strong></summary><hr>\n\n"
+        output += '''\
+The `describe` tool can be configured with extra instructions, to guide the model to a feedback tailored to the needs of your project.
+
+Be specific, clear, and concise in the instructions. With extra instructions, you are the prompter. Notice that the general structure of the description is fixed, and cannot be changed. Extra instructions can change the content or style of each sub-section of the PR description.
+
+Examples for extra instructions:
+```
+[pr_description] 
+extra_instructions="""
+- The PR title should be in the format: '<PR type>: <title>'
+- The title should be short and concise (up to 10 words)
+- ...
+"""
+```
+Use triple quotes to write multi-line instructions. Use bullet points to make the instructions more readable.
+'''
+        output += "\n\n</details></td></tr>\n\n"
+
+
+        # general
+        output += "\n\n<tr><td><details> <summary><strong> More PR-Agent commands</strong></summary><hr> \n\n"
+        output += HelpMessage.get_general_bot_help_text()
+        output += "\n\n</details></td></tr>\n\n"
+
+        output += "</table>"
+
+        output += f"\n\nSee the [describe usage](https://github.com/Codium-ai/pr-agent/blob/main/docs/DESCRIBE.md) page for a comprehensive guide on using this tool.\n\n"
+
+        return output
+
+    @staticmethod
+    def get_ask_usage_guide():
+        output = "**Overview:**\n"
+        output += """\
+The `ask` tool answers questions about the PR, based on the PR code changes.
+It can be invoked manually by commenting on any PR:
+```
+/ask "..."
+```
+
+Note that the tool does not have "memory" of previous questions, and answers each question independently.        
+        """
+        output += "\n\n<table>"
+
+        # general
+        output += "\n\n<tr><td><details> <summary><strong> More PR-Agent commands</strong></summary><hr> \n\n"
+        output += HelpMessage.get_general_bot_help_text()
+        output += "\n\n</details></td></tr>\n\n"
+
+        output += "</table>"
+
+        output += f"\n\nSee the [ask usage](https://github.com/Codium-ai/pr-agent/blob/main/docs/ASK.md) page for a comprehensive guide on using this tool.\n\n"
+
+        return output
+
+
+    @staticmethod
+    def get_improve_usage_guide():
+        output = "**Overview:**\n"
+        output += "The `improve` tool scans the PR code changes, and automatically generates suggestions for improving the PR code. "
+        output += "The tool can be triggered [automatically](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools) every time a new PR is opened, or can be invoked manually by commenting on a PR.\n"
+        output += """\
+When commenting, to edit [configurations](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L69) related to the improve tool (`pr_code_suggestions` section), use the following template:
+
+```
+/improve --pr_code_suggestions.some_config1=... --pr_code_suggestions.some_config2=...
+```
+
+With a [configuration file](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#working-with-github-app), use the following template:
+
+```
+[pr_code_suggestions]
+some_config1=...
+some_config2=...
+```
+    
+"""
+        output += "\n\n<table>"
+
+        # automation
+        output += "<tr><td><details> <summary><strong> Enabling\\disabling automation </strong></summary><hr>\n\n"
+        output += """\
+When you first install the app, the [default mode](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools) for the improve tool is:
+
+```
+pr_commands = ["/improve --pr_code_suggestions.summarize=true", ...]
+```
+
+meaning the `improve` tool will run automatically on every PR, with summarization enabled. Delete this line to disable the tool from running automatically.
+"""
+        output += "\n\n</details></td></tr>\n\n"
+
+        # extra instructions
+        output += "<tr><td><details> <summary><strong> Utilizing extra instructions</strong></summary><hr>\n\n"
+        output += '''\
+Extra instructions are very important for the `improve` tool, since they enable 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.
+    '''
+        output += "\n\n</details></td></tr>\n\n"
+
+        # suggestions quality
+        output += "\n\n<tr><td><details> <summary><strong> A note on code suggestions quality</strong></summary><hr> \n\n"
+        output += """\
+- 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. 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 'extra_instructions' field to guide the model to suggestions that are more relevant to the specific needs of the project, or use the [custom suggestions :gem:](https://github.com/Codium-ai/pr-agent/blob/main/docs/CUSTOM_SUGGESTIONS.md) tool
+- With large PRs, best quality will be obtained by using 'improve --extended' mode.
+
+
+"""
+        output += "\n\n</details></td></tr>\n\n"\
+
+        # general
+        output += "\n\n<tr><td><details> <summary><strong> More PR-Agent commands</strong></summary><hr> \n\n"
+        output += HelpMessage.get_general_bot_help_text()
+        output += "\n\n</details></td></tr>\n\n"
+
+        output += "</table>"
+
+        output += f"\n\nSee the [improve usage](https://github.com/Codium-ai/pr-agent/blob/main/docs/IMPROVE.md) page for a more comprehensive guide on using this tool.\n\n"
+
+        return output
--- a/pr_agent/settings/.secrets_template.toml
+++ b/pr_agent/settings/.secrets_template.toml
@ -65,6 +65,11 @@ personal_access_token = ""
 # For Bitbucket personal/repository bearer token
 bearer_token = ""

+[bitbucket_server]
+# For Bitbucket Server bearer token
+auth_token = ""
+webhook_secret = ""
+
 # For Bitbucket app
 app_key = ""
 base_url = ""
--- a/pr_agent/settings/configuration.toml
+++ b/pr_agent/settings/configuration.toml
@ -1,5 +1,5 @@
 [config]
-model="gpt-4" # "gpt-4-1106-preview"
+model="gpt-4" # "gpt-4-0125-preview"
 fallback_models=["gpt-3.5-turbo-16k"]
 git_provider="github"
 publish_output=true
@ -7,6 +7,7 @@ publish_output_progress=true
 verbosity_level=0 # 0,1,2
 use_extra_bad_extensions=false
 use_repo_settings_file=true
+use_global_settings_file=true
 ai_timeout=180
 max_description_tokens = 500
 max_commits_tokens = 500
@ -22,35 +23,40 @@ require_score_review=false
 require_tests_review=true
 require_security_review=true
 require_estimate_effort_to_review=true
+# soc2
+require_soc2_ticket=false
+soc2_ticket_prompt="Does the PR description include a link to ticket in a project management system (e.g., Jira, Asana, Trello, etc.) ?"
 # general options
 num_code_suggestions=4
 inline_code_comments = false
 ask_and_reflect=false
-automatic_review=true
+#automatic_review=true
 remove_previous_review_comment=false
 persistent_comment=true
 extra_instructions = ""
 # review labels
 enable_review_labels_security=true
-enable_review_labels_effort=false
+enable_review_labels_effort=true
 # specific configurations for incremental review (/review -i)
 require_all_thresholds_for_incremental_review=false
 minimal_commits_for_incremental_review=0
 minimal_minutes_for_incremental_review=0
+enable_help_text=true # Determines whether to include help text in the PR review. Enabled by default.

 [pr_description] # /describe #
 publish_labels=true
 publish_description_as_comment=false
-add_original_user_description=false
-keep_original_user_title=false
+add_original_user_description=true
+keep_original_user_title=true
 use_bullet_points=true
 extra_instructions = ""
 enable_pr_type=true
-enable_file_walkthrough=false
-enable_semantic_files_types=true
 final_update_message = true
-
-
+enable_help_text=true
+## changes walkthrough section
+enable_semantic_files_types=true
+collapsible_file_list='adaptive' # true, false, 'adaptive'
+inline_file_summary=false # false, true, 'table'
 # markers
 use_description_markers=false
 include_generated_by_header=true
@ -58,13 +64,17 @@ include_generated_by_header=true
 #custom_labels = ['Bug fix', 'Tests', 'Bug fix with tests', 'Enhancement', 'Documentation', 'Other']

 [pr_questions] # /ask #
+enable_help_text=true
+

 [pr_code_suggestions] # /improve #
 num_code_suggestions=4
-summarize = false
+summarize = true
 extra_instructions = ""
 rank_suggestions = false
+enable_help_text=true
 # params for '/improve --extended' mode
+auto_extended_mode=false
 num_code_suggestions_per_chunk=8
 rank_extended_suggestions = true
 max_number_of_calls = 5
@ -78,6 +88,17 @@ docs_style = "Sphinx Style" # "Google Style with Args, Returns, Attributes...etc
 push_changelog_changes=false
 extra_instructions = ""

+[pr_analyze] # /analyze #
+
+[pr_test] # /test #
+extra_instructions = ""
+testing_framework = "" # specify the testing framework you want to use
+num_tests=3            # number of tests to generate. max 5.
+avoid_mocks=true       # if true, the generated tests will prefer to use real objects instead of mocks
+file = ""              # in case there are several components with the same name, you can specify the relevant file
+class_name = ""        # in case there are several methods with the same name in the same file, you can specify the relevant class name
+enable_help_text=true
+
 [pr_config] # /config #

 [github]
@ -85,8 +106,10 @@ extra_instructions = ""
 deployment_type = "user"
 ratelimit_retries = 5
 base_url = "https://api.github.com"
+publish_inline_comments_fallback_with_verification = true
+try_fix_invalid_inline_comments = true

-[github_action]
+[github_action_config]
 # auto_review = true    # set as env var in .github/workflows/pr-agent.yaml
 # auto_describe = true  # set as env var in .github/workflows/pr-agent.yaml
 # auto_improve = true   # set as env var in .github/workflows/pr-agent.yaml
@ -103,7 +126,8 @@ duplicate_requests_cache_ttl = 60  # in seconds
 handle_pr_actions = ['opened', 'reopened', 'ready_for_review', 'review_requested']
 pr_commands = [
    "/describe --pr_description.add_original_user_description=true --pr_description.keep_original_user_title=true",
-    "/auto_review",
+    "/review --pr_reviewer.num_code_suggestions=0",
+    "/improve --pr_code_suggestions.summarize=true",
 ]
 # settings for "pull_request" event with "synchronize" action - used to detect and handle push triggers for new commits
 handle_push_trigger = false
@ -164,6 +188,11 @@ polling_interval_seconds = 30
 # token to authenticate in the patch server
 # patch_server_token = ""

+[bitbucket_server]
+# URL to the BitBucket Server instance
+# url = "https://git.bitbucket.com"
+url = ""
+
 [litellm]
 #use_client = false

@ -171,9 +200,12 @@ polling_interval_seconds = 30
 skip_comments = false
 force_update_dataset = false
 max_issues_to_scan = 500
+vectordb = "pinecone"

 [pinecone]
 # fill and place in .secrets.toml
 #api_key = ...
 # environment = "gcp-starter"

+[lancedb]
+uri = "./lancedb"
--- a/pr_agent/settings/pr_add_docs.toml
+++ b/pr_agent/settings/pr_add_docs.toml
@ -5,7 +5,7 @@ Your task is to generate {{ docs_for_language }} for code components in the PR D

 Example for the PR Diff format:
 ======
-## src/file1.py
+## file: 'src/file1.py'

@@ -12,3 +12,4 @@ def func1():
 __new hunk__
@ -18,7 +18,6 @@ __old hunk__
 -code line that was removed in the PR
 code line2 that remained unchanged in the PR

-
@@ ... @@ def func2():
 __new hunk__
 ...
@ -26,7 +25,7 @@ __old hunk__
 ...


-## src/file2.py
+## file: 'src/file2.py'
 ...
 ======

@ -35,7 +34,7 @@ Specific instructions:
 - Try to identify edited/added code components (classes/functions/methods...) that are undocumented, and generate {{ docs_for_language }} for each one.
 - If there are documented (any type of {{ language }} documentation) code components in the PR, Don't generate {{ docs_for_language }} for them.
 - Ignore code components that don't appear fully in the '__new hunk__' section. For example, you must see the component header and body.
- Make sure the {{ docs_for_language }} starts and ends with standart {{ language }} {{ docs_for_language }} signs.
+- Make sure the {{ docs_for_language }} starts and ends with standard {{ language }} {{ docs_for_language }} signs.
 - The {{ docs_for_language }} should be in standard format.
 - Provide the exact line number (inclusive) where the {{ docs_for_language }} should be added.

@ -69,6 +68,7 @@ Code Documentation:
        - after
      description: |-
        The {{ docs_for_language }} placement relative to the relevant line (code component).
+        For example, in Python the docs are placed after the function signature, but in Java they are placed before.
    documentation:
      type: string
      description: |-
--- a/pr_agent/settings/pr_code_suggestions_prompts.toml
+++ b/pr_agent/settings/pr_code_suggestions_prompts.toml
@ -4,19 +4,17 @@ Your task is to provide meaningful and actionable code suggestions, to improve t

 Example for the PR Diff format:
 ======
-## src/file1.py
+## file: 'src/file1.py'

-@@ -12,3 +12,4 @@ def func1():
+@@ ... @@ def func1():
 __new hunk__
 12  code line1 that remained unchanged in the PR
-14 +new code line1 added in the PR
-15 +new code line2 added in the PR
-16  code line2 that remained unchanged in the PR
+13 +new code line2 added in the PR
+14  code line3 that remained unchanged in the PR
 __old hunk__
 code line1 that remained unchanged in the PR
-code line that was removed in the PR
- code line2 that remained unchanged in the PR
-
+-old code line2 that was removed in the PR
+ code line3 that remained unchanged in the PR

@@ ... @@ def func2():
 __new hunk__
@ -25,20 +23,19 @@ __old hunk__
 ...


-## src/file2.py
+## file: 'src/file2.py'
 ...
 ======


 Specific instructions:
- Provide up to {{ num_code_suggestions }} code suggestions. Try to provide diverse and insightful suggestions.
- Prioritize suggestions that address major problems, issues and bugs in the code. As a second priority, suggestions should focus on best practices, code readability, maintainability, enhancments, performance, and other aspects.
- Don't suggest to add docstring, type hints, or comments.
- Suggestions should refer only to code from the '__new hunk__' sections, and focus on new lines of code (lines starting with '+').
+- Provide up to {{ num_code_suggestions }} code suggestions. The suggestions should be diverse and insightful.
+- The suggestions should refer only to code from the '__new hunk__' sections, and focus on new lines of code (lines starting with '+').
+- Prioritize suggestions that address major problems, issues and bugs in the PR code. As a second priority, suggestions should focus on enhancement, best practice, performance, maintainability, and other aspects.
+- Don't suggest to add docstring, type hints, or comments, or to remove unused imports.
 - Avoid making suggestions that have already been implemented in the PR code. For example, if you want to add logs, or change a variable to const, or anything else, make sure it isn't already in the '__new hunk__' code.
- For each suggestion, make sure to take into consideration also the context, meaning the lines before and after the relevant code.
 - Provide the exact line numbers range (inclusive) for each suggestion.
- Assume there is additional relevant code, that is not included in the diff.
+- When quoting variables or names from the code, use backticks (`) instead of single quote (').


 {%- if extra_instructions %}
@ -49,86 +46,67 @@ Extra instructions from the user:
 ======
 {%- endif %}

+The output must be a YAML object equivalent to type $PRCodeSuggestions, according to the following Pydantic definitions:
+=====
+class CodeSuggestion(BaseModel):
+    relevant_file: str = Field(description="the relevant file full path")
+    language: str = Field(description="the code language of the relevant file")
+    suggestion_content: str = Field(description="an actionable suggestion for meaningfully improving the new code introduced in the PR")
+{%- if summarize_mode %}
+    existing_code: str = Field(description="a short code snippet from a '__new hunk__' section to illustrate the relevant existing code. Don't show the line numbers.")
+    improved_code: str = Field(description="a short code snippet to illustrate the improved code, after applying the suggestion.")
+    one_sentence_summary:str = Field(description="a short summary of the suggestion action, in a single sentence. Focus on the 'what'. Be general, and avoid method or variable names.")
+{%- else %}
+    existing_code: str = Field(description="a code snippet, demonstrating the relevant code lines from a '__new hunk__' section. It must be contiguous, correctly formatted and indented, and without line numbers")
+    improved_code: str = Field(description="a new code snippet, that can be used to replace the relevant lines in '__new hunk__' code. Replacement suggestions should be complete, correctly formatted and indented, and without line numbers")
+{%- endif %}
+    relevant_lines_start: int = Field(description="The relevant line number, from a '__new hunk__' section, where the suggestion starts (inclusive). Should be derived from the hunk line numbers, and correspond to the 'existing code' snippet above")
+    relevant_lines_end: int = Field(description="The relevant line number, from a '__new hunk__' section, where the suggestion ends (inclusive). Should be derived from the hunk line numbers, and correspond to the 'existing code' snippet above")
+    label: str = Field(description="a single label for the suggestion, to help the user understand the suggestion type. For example: 'security', 'bug', 'performance', 'enhancement', 'possible issue', 'best practice', 'maintainability', etc. Other labels are also allowed")
+
+class PRCodeSuggestions(BaseModel):
+    code_suggestions: List[CodeSuggestion]
+=====

-You must use the following YAML schema to format your answer:
-```yaml
-Code suggestions:
-  type: array
-  minItems: 1
-  maxItems: {{ num_code_suggestions }}
-  uniqueItems: true
-  items:
-    relevant file:
-      type: string
-      description: the relevant file full path
-    suggestion content:
-      type: string
-      description: |-
-        a concrete suggestion for meaningfully improving the new PR code.
-    existing code:
-      type: string
-      description: |-
-        a code snippet showing the relevant code lines from a '__new hunk__' section.
-        It must be contiguous, correctly formatted and indented, and without line numbers.
-    relevant lines start:
-      type: integer
-      description: |-
-        The relevant line number from a '__new hunk__' section where the suggestion starts (inclusive).
-        Should be derived from the hunk line numbers, and correspond to the 'existing code' snippet above.
-    relevant lines end:
-      type: integer
-      description: |-
-        The relevant line number from a '__new hunk__' section where the suggestion ends (inclusive).
-        Should be derived from the hunk line numbers, and correspond to the 'existing code' snippet above.
-    improved code:
-      type: string
-      description: |-
-        a new code snippet that can be used to replace the relevant lines in '__new hunk__' code.
-        Replacement suggestions should be complete, correctly formatted and indented, and without line numbers.
-```

 Example output:
 ```yaml
-Code suggestions:
- relevant file: |-
+code_suggestions:
+- relevant_file: |-
    src/file1.py
-  suggestion content: |-
+  language: |-
+    python
+  suggestion_content: |-
    Add a docstring to func1()
-  existing code: |-
+{%- if summarize_mode %}
+  existing_code: |-
    def func1():
-  relevant lines start: |-
-    12
-  relevant lines end: |-
-    12
-  improved code: |-
+  improved_code: |-
    ...
+  one_sentence_summary: |-
+    ...
+  relevant_lines_start: 12
+  relevant_lines_end: 12
+{%- else %}
+  existing_code: |-
+    def func1():
+  relevant_lines_start: 12
+  relevant_lines_end: 12
+  improved_code: |-
+    ...
+{%- endif %}
+  label: |-
    ...
 ```


 Each YAML output MUST be after a newline, indented, with block scalar indicator ('|-').
-Don't repeat the prompt in the answer, and avoid outputting the 'type' and 'description' fields.
 """

 user="""PR Info:

 Title: '{{title}}'

-Branch: '{{branch}}'
-
-{%- if description %}
-
-Description:
-======
-{{ description|trim }}
-======
-{%- endif %}
-
-{%- if language %}
-
-Main PR language: '{{ language }}'
-{%- endif %}
-

 The PR Diff:
 ======
--- a/pr_agent/settings/pr_custom_labels.toml
+++ b/pr_agent/settings/pr_custom_labels.toml
@ -30,7 +30,7 @@ class Label(str, Enum):
 {%- endif %}

 class Labels(BaseModel):
-    labels: List[Label] = Field(min_items=0, description="custom labels that describe the PR. Return the label value, not the name.")
+    labels: List[Label] =  Field(min_items=0, description="choose the relevant custom labels that describe the PR content, and return their keys. Use the value field of the Label object to better understand the label meaning.")
 ======


--- a/pr_agent/settings/pr_description_prompts.toml
+++ b/pr_agent/settings/pr_description_prompts.toml
@ -1,10 +1,15 @@
 [pr_description_prompt]
 system="""You are PR-Reviewer, a language model designed to review a Git Pull Request (PR).
-Your task is to provide a full description for the PR content - title, type, description, and main files walkthrough.
+{%- if enable_custom_labels %}
+Your task is to provide a full description for the PR content - files walkthrough, title, type, description and labels.
+{%- else %}
+Your task is to provide a full description for the PR content - files walkthrough, title, type, and description.
+{%- endif %}
 - Focus on the new PR code (lines starting with '+').
 - Keep in mind that the 'Previous title', 'Previous description' and 'Commit messages' sections may be partial, simplistic, non-informative or out of date. Hence, compare them to the PR diff code, and use them only as a reference.
 - The generated title and description should prioritize the most significant changes.
 - If needed, each YAML output should be in block scalar indicator ('|-')
+- When quoting variables or names from the code, use backticks (`) instead of single quote (').

 {%- if extra_instructions %}

@ -30,31 +35,25 @@ class PRType(str, Enum):

 {%- endif %}

-{%- if enable_file_walkthrough %}
-class FileWalkthrough(BaseModel):
-    filename: str = Field(description="the relevant file full path")
-    changes_in_file: str = Field(description="minimal and concise summary of the changes in the relevant file")
-{%- endif %}
-
 {%- if enable_semantic_files_types %}
+
 Class FileDescription(BaseModel):
    filename: str = Field(description="the relevant file full path")
-    changes_summary: str = Field(description="minimal and concise summary of the changes in the relevant file")
+    language: str = Field(description="the relevant file language")
+    changes_summary: str = Field(description="concise summary of the changes in the relevant file, in bullet points (1-4 bullet points).")
+    changes_title: str = Field(description="an informative title for the changes in the files, describing its main theme (5-10 words).")
    label: str = Field(description="a single semantic label that represents a type of code changes that occurred in the File. Possible values (partial list): 'bug fix', 'tests', 'enhancement', 'documentation', 'error handling', 'configuration changes', 'dependencies', 'formatting', 'miscellaneous', ...")
 {%- endif %}

 Class PRDescription(BaseModel):
-    title: str = Field(description="an informative title for the PR, describing its main theme")
-    type: List[PRType] = Field(description="one or more types that describe the PR type. Return the label value, not the name.")
-    description: str = Field(description="an informative and concise description of the PR. {%- if use_bullet_points %} Use bullet points.{% endif %}")
-{%- if enable_custom_labels %}
-    labels: List[Label] = Field(min_items=0, description="custom labels that describe the PR. Return the label value, not the name.")
-{%- endif %}
-{%- if enable_file_walkthrough %}
-    main_files_walkthrough: List[FileWalkthrough] = Field(max_items=10)
-{%- endif %}
+    type: List[PRType] = Field(description="one or more types that describe the PR content. Return the label member value (e.g. 'Bug fix', not 'bug_fix')")
 {%- if enable_semantic_files_types %}
-    pr_files[List[FileDescription]] = Field(max_items=15")
+    pr_files[List[FileDescription]] = Field(max_items=15, description="a list of the files in the PR, and their changes summary.")
+{%- endif %}
+    description: str = Field(description="an informative and concise description of the PR. Use bullet points. Display first the most significant changes.")
+    title: str = Field(description="an informative title for the PR, describing its main theme")
+{%- if enable_custom_labels %}
+    labels: List[Label] =  Field(min_items=0, description="choose the relevant custom labels that describe the PR content, and return their keys. Use the value field of the Label object to better understand the label meaning.")
 {%- endif %}
 =====

@ -62,33 +61,34 @@ Class PRDescription(BaseModel):
 Example output:

 ```yaml
-title: |-
-  ...
 type:
 - ...
 - ...
-{%- if enable_custom_labels %}
-labels:
- ...
- ...
-{%- endif %}
-description: |-
-  ...
-{%- if enable_file_walkthrough %}
-main_files_walkthrough:
- ...
- ...
-{%- endif %}
 {%- if enable_semantic_files_types %}
 pr_files:
 - filename: |
    ...
+  language: |
+    ...
  changes_summary: |
    ...
+  changes_title: |
+    ...
  label: |
    ...
 ...
 {%- endif %}
+description: |-
+  ...
+title: |-
+  ...
+{%- if enable_custom_labels %}
+labels:
+- |
+  ...
+- |
+  ...
+{%- endif %}
 ```

 Answer should be a valid YAML, and nothing else. Each YAML output MUST be after a newline, with proper indent, and block scalar indicator ('|-')
@ -107,10 +107,7 @@ Previous description:
 {%- endif %}

 Branch: '{{branch}}'
-{%- if language %}

-Main PR language: '{{ language }}'
-{%- endif %}
 {%- if commit_messages_str %}

 Commit messages:
--- a/pr_agent/settings/pr_questions_prompts.toml
+++ b/pr_agent/settings/pr_questions_prompts.toml
@ -1,7 +1,7 @@
 [pr_questions_prompt]
-system="""You are PR-Reviewer, a language model designed to review a Git Pull Request (PR).
+system="""You are PR-Reviewer, a language model designed to answer questions about a Git Pull Request (PR).

-Your goal is to answer questions\\tasks about the new PR code (lines starting with '+'), and provide feedback.
+Your goal is to answer questions\\tasks about the new code introduced in the PR (lines starting with '+' in the 'PR Git Diff' section), and provide feedback.
 Be informative, constructive, and give examples. Try to be as specific as possible.
 Don't avoid answering the questions. You must answer the questions, as best as you can, without adding any unrelated content.
 """
--- a/pr_agent/settings/pr_reviewer_prompts.toml
+++ b/pr_agent/settings/pr_reviewer_prompts.toml
@ -5,7 +5,7 @@ The review should focus on new code added in the PR diff (lines starting with '+

 Example PR Diff:
 ======
-## src/file1.py
+## file: 'src/file1.py'

@@ -12,5 +12,5 @@ def func1():
 code line 1 that remained unchanged in the PR
@ -14,12 +14,11 @@ code line 2 that remained unchanged in the PR
 +code line added in the PR
 code line 3 that remained unchanged in the PR

-
@@ ... @@ def func2():
 ...


-## src/file2.py
+## file: 'src/file2.py'
 ...
 ======

@ -32,6 +31,7 @@ Code suggestions guidelines:
 - Avoid making suggestions that have already been implemented in the PR code. For example, if you want to add logs, or change a variable to const, or anything else, make sure it isn't already in the PR code.
 - Don't suggest to add docstring, type hints, or comments.
 - Suggestions should focus on the new code added in the PR diff (lines starting with '+')
+- When quoting variables or names from the code, use backticks (`) instead of single quote (').
 {%- endif %}

 {%- if extra_instructions %}
@ -114,6 +114,9 @@ PR Feedback:
      relevant file:
        type: string
        description: the relevant file full path
+      language:
+        type: string
+        description: the language of the relevant file
      suggestion:
        type: string
        description: |-
@ -165,6 +168,8 @@ PR Feedback:
  Code feedback:
    - relevant file: |-
        directory/xxx.py
+      language: |-
+        python
      suggestion: |-
        xxx [important]
      relevant line: |-
@ -194,10 +199,6 @@ Description:
 ======
 {%- endif %}

-{%- if language %}
-
-Main PR language: '{{ language }}'
-{%- endif %}
 {%- if commit_messages_str %}

 Commit messages:
--- a/pr_agent/tools/pr_add_docs.py
+++ b/pr_agent/tools/pr_add_docs.py
@ -1,10 +1,12 @@
 import copy
 import textwrap
+from functools import partial
 from typing import Dict

 from jinja2 import Environment, StrictUndefined

-from pr_agent.algo.ai_handler import AiHandler
+from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
+from pr_agent.algo.ai_handlers.litellm_ai_handler import LiteLLMAIHandler
 from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
 from pr_agent.algo.token_handler import TokenHandler
 from pr_agent.algo.utils import load_yaml
@ -15,14 +17,15 @@ from pr_agent.log import get_logger


 class PRAddDocs:
-    def __init__(self, pr_url: str, cli_mode=False, args: list = None):
+    def __init__(self, pr_url: str, cli_mode=False, args: list = None,
+                 ai_handler: partial[BaseAiHandler,] = LiteLLMAIHandler):

        self.git_provider = get_git_provider()(pr_url)
        self.main_language = get_main_pr_language(
            self.git_provider.get_languages(), self.git_provider.get_files()
        )

-        self.ai_handler = AiHandler()
+        self.ai_handler = ai_handler()
        self.patches_diff = None
        self.prediction = None
        self.cli_mode = cli_mode
--- a/pr_agent/tools/pr_code_suggestions.py
+++ b/pr_agent/tools/pr_code_suggestions.py
@ -1,20 +1,25 @@
 import copy
 import textwrap
+from functools import partial
 from typing import Dict, List
 from jinja2 import Environment, StrictUndefined

-from pr_agent.algo.ai_handler import AiHandler
+from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
+from pr_agent.algo.ai_handlers.litellm_ai_handler import LiteLLMAIHandler
 from pr_agent.algo.pr_processing import get_pr_diff, get_pr_multi_diffs, retry_with_fallback_models
 from pr_agent.algo.token_handler import TokenHandler
-from pr_agent.algo.utils import load_yaml
+from pr_agent.algo.utils import load_yaml, replace_code_tags
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
 from pr_agent.git_providers.git_provider import get_main_pr_language
 from pr_agent.log import get_logger
-
+from pr_agent.servers.help import HelpMessage
+from pr_agent.tools.pr_description import insert_br_after_x_chars
+import difflib

 class PRCodeSuggestions:
-    def __init__(self, pr_url: str, cli_mode=False, args: list = None):
+    def __init__(self, pr_url: str, cli_mode=False, args: list = None,
+                 ai_handler: partial[BaseAiHandler,] = LiteLLMAIHandler):

        self.git_provider = get_git_provider()(pr_url)
        self.main_language = get_main_pr_language(
@ -23,7 +28,7 @@ class PRCodeSuggestions:

        # extended mode
        try:
-            self.is_extended = any(["extended" in arg for arg in args])
+            self.is_extended = self._get_is_extended(args or [])
        except:
            self.is_extended = False
        if self.is_extended:
@ -31,7 +36,7 @@ class PRCodeSuggestions:
        else:
            num_code_suggestions = get_settings().pr_code_suggestions.num_code_suggestions

-        self.ai_handler = AiHandler()
+        self.ai_handler = ai_handler()
        self.patches_diff = None
        self.prediction = None
        self.cli_mode = cli_mode
@ -42,6 +47,7 @@ class PRCodeSuggestions:
            "language": self.main_language,
            "diff": "",  # empty diff for initial calculation
            "num_code_suggestions": num_code_suggestions,
+            "summarize_mode": get_settings().pr_code_suggestions.summarize,
            "extra_instructions": get_settings().pr_code_suggestions.extra_instructions,
            "commit_messages_str": self.git_provider.get_commit_messages(),
        }
@ -62,21 +68,33 @@ class PRCodeSuggestions:
                data = self._prepare_pr_code_suggestions()
            else:
                data = await retry_with_fallback_models(self._prepare_prediction_extended)
-            if (not data) or (not 'Code suggestions' in data):
+
+
+            if (not data) or (not 'code_suggestions' in data):
                get_logger().info('No code suggestions found for PR.')
                return

            if (not self.is_extended and get_settings().pr_code_suggestions.rank_suggestions) or \
                    (self.is_extended and get_settings().pr_code_suggestions.rank_extended_suggestions):
                get_logger().info('Ranking Suggestions...')
-                data['Code suggestions'] = await self.rank_suggestions(data['Code suggestions'])
+                data['code_suggestions'] = await self.rank_suggestions(data['code_suggestions'])

            if get_settings().config.publish_output:
                get_logger().info('Pushing PR code suggestions...')
                self.git_provider.remove_initial_comment()
-                if get_settings().pr_code_suggestions.summarize:
+                if get_settings().pr_code_suggestions.summarize and self.git_provider.is_supported("gfm_markdown"):
                    get_logger().info('Pushing summarize code suggestions...')
-                    self.publish_summarizes_suggestions(data)
+
+                    # generate summarized suggestions
+                    pr_body = self.generate_summarized_suggestions(data)
+
+                    # add usage guide
+                    if get_settings().pr_code_suggestions.enable_help_text:
+                        pr_body += "<hr>\n\n<details> <summary><strong>✨ Usage guide:</strong></summary><hr> \n\n"
+                        pr_body += HelpMessage.get_improve_usage_guide()
+                        pr_body += "\n</details>\n"
+
+                    self.git_provider.publish_comment(pr_body)
                else:
                    get_logger().info('Pushing inline code suggestions...')
                    self.push_inline_code_suggestions(data)
@ -106,36 +124,52 @@ class PRCodeSuggestions:
        response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
                                                                        system=system_prompt, user=user_prompt)

+        if get_settings().config.verbosity_level >= 2:
+            get_logger().info(f"\nAI response:\n{response}")
+
        return response

    def _prepare_pr_code_suggestions(self) -> Dict:
        review = self.prediction.strip()
-        data = load_yaml(review)
+        data = load_yaml(review,
+                         keys_fix_yaml=["relevant_file", "suggestion_content", "existing_code", "improved_code"])
        if isinstance(data, list):
-            data = {'Code suggestions': data}
+            data = {'code_suggestions': data}
+
+        # remove invalid suggestions
+        suggestion_list = []
+        for i, suggestion in enumerate(data['code_suggestions']):
+            if suggestion['existing_code'] != suggestion['improved_code']:
+                suggestion_list.append(suggestion)
+            else:
+                get_logger().debug(
+                    f"Skipping suggestion {i + 1}, because existing code is equal to improved code {suggestion['existing_code']}")
+        data['code_suggestions'] = suggestion_list
+
        return data

    def push_inline_code_suggestions(self, data):
        code_suggestions = []

-        if not data['Code suggestions']:
+        if not data['code_suggestions']:
            get_logger().info('No suggestions found to improve this PR.')
            return self.git_provider.publish_comment('No suggestions found to improve this PR.')

-        for d in data['Code suggestions']:
+        for d in data['code_suggestions']:
            try:
                if get_settings().config.verbosity_level >= 2:
                    get_logger().info(f"suggestion: {d}")
-                relevant_file = d['relevant file'].strip()
-                relevant_lines_start = int(d['relevant lines start'])  # absolute position
-                relevant_lines_end = int(d['relevant lines end'])
-                content = d['suggestion content']
-                new_code_snippet = d['improved code']
+                relevant_file = d['relevant_file'].strip()
+                relevant_lines_start = int(d['relevant_lines_start'])  # absolute position
+                relevant_lines_end = int(d['relevant_lines_end'])
+                content = d['suggestion_content'].rstrip()
+                new_code_snippet = d['improved_code'].rstrip()
+                label = d['label'].strip()

                if new_code_snippet:
                    new_code_snippet = self.dedent_code(relevant_file, relevant_lines_start, new_code_snippet)

-                body = f"**Suggestion:** {content}\n```suggestion\n" + new_code_snippet + "\n```"
+                body = f"**Suggestion:** {content} [{label}]\n```suggestion\n" + new_code_snippet + "\n```"
                code_suggestions.append({'body': body, 'relevant_file': relevant_file,
                                             'relevant_lines_start': relevant_lines_start,
                                             'relevant_lines_end': relevant_lines_end})
@ -156,6 +190,7 @@ class PRCodeSuggestions:
            original_initial_line = None
            for file in self.diff_files:
                if file.filename.strip() == relevant_file:
+                    if file.head_file:  # in bitbucket, head_file is empty. toDo: fix this
                        original_initial_line = file.head_file.splitlines()[relevant_lines_start - 1]
                    break
            if original_initial_line:
@ -171,6 +206,16 @@ class PRCodeSuggestions:

        return new_code_snippet

+    def _get_is_extended(self, args: list[str]) -> bool:
+        """Check if extended mode should be enabled by the `--extended` flag or automatically according to the configuration"""
+        if any(["extended" in arg for arg in args]):
+            get_logger().info("Extended mode is enabled by the `--extended` flag")
+            return True
+        if get_settings().pr_code_suggestions.auto_extended_mode:
+            get_logger().info("Extended mode is enabled automatically based on the configuration toggle")
+            return True
+        return False
+
    async def _prepare_prediction_extended(self, model: str) -> dict:
        get_logger().info('Getting PR diff...')
        patches_diff_list = get_pr_multi_diffs(self.git_provider, self.token_handler, model,
@ -181,7 +226,7 @@ class PRCodeSuggestions:
        for i, patches_diff in enumerate(patches_diff_list):
            get_logger().info(f"Processing chunk {i + 1} of {len(patches_diff_list)}")
            self.patches_diff = patches_diff
-            prediction = await self._get_prediction(model)
+            prediction = await self._get_prediction(model) # toDo: parallelize
            prediction_list.append(prediction)
        self.prediction_list = prediction_list

@ -189,8 +234,8 @@ class PRCodeSuggestions:
        for prediction in prediction_list:
            self.prediction = prediction
            data_per_chunk = self._prepare_pr_code_suggestions()
-            if "Code suggestions" in data:
-                data["Code suggestions"].extend(data_per_chunk["Code suggestions"])
+            if "code_suggestions" in data:
+                data["code_suggestions"].extend(data_per_chunk["code_suggestions"])
            else:
                data.update(data_per_chunk)
        self.data = data
@ -208,13 +253,15 @@ class PRCodeSuggestions:
        """

        suggestion_list = []
-        # remove invalid suggestions
-        for i, suggestion in enumerate(data):
-            if suggestion['existing code'] != suggestion['improved code']:
+        if not data:
+            return suggestion_list
+        for suggestion in data:
            suggestion_list.append(suggestion)
-
        data_sorted = [[]] * len(suggestion_list)

+        if len(suggestion_list ) == 1:
+            return suggestion_list
+
        try:
            suggestion_str = ""
            for i, suggestion in enumerate(suggestion_list):
@ -239,7 +286,13 @@ class PRCodeSuggestions:
                data_sorted[importance_order - 1] = suggestion_list[suggestion_number - 1]

            if get_settings().pr_code_suggestions.final_clip_factor != 1:
-                new_len = int(0.5 + len(data_sorted) * get_settings().pr_code_suggestions.final_clip_factor)
+                max_len = max(
+                    len(data_sorted),
+                    get_settings().pr_code_suggestions.num_code_suggestions,
+                    get_settings().pr_code_suggestions.num_code_suggestions_per_chunk,
+                )
+                new_len = int(0.5 + max_len * get_settings().pr_code_suggestions.final_clip_factor)
+                if new_len < len(data_sorted):
                    data_sorted = data_sorted[:new_len]
        except Exception as e:
            if get_settings().config.verbosity_level >= 1:
@ -248,9 +301,13 @@ class PRCodeSuggestions:

        return data_sorted

-    def publish_summarizes_suggestions(self, data: Dict):
+    def generate_summarized_suggestions(self, data: Dict) -> str:
        try:
-            data_markdown = "## PR Code Suggestions\n\n"
+            pr_body = "## PR Code Suggestions\n\n"
+
+            if len(data.get('code_suggestions', [])) == 0:
+                pr_body += "No suggestions found to improve this PR."
+                return pr_body

            language_extension_map_org = get_settings().language_extension_map_org
            extension_to_language = {}
@ -258,31 +315,78 @@ class PRCodeSuggestions:
                for ext in extensions:
                    extension_to_language[ext] = language

-            for s in data['Code suggestions']:
-                try:
-                    extension_s = s['relevant file'].rsplit('.')[-1]
-                    code_snippet_link = self.git_provider.get_line_link(s['relevant file'], s['relevant lines start'],
-                                                                        s['relevant lines end'])
-                    data_markdown += f"\n💡 Suggestion:\n\n**{s['suggestion content']}**\n\n"
-                    if code_snippet_link:
-                        data_markdown += f" File: [{s['relevant file']} ({s['relevant lines start']}-{s['relevant lines end']})]({code_snippet_link})\n\n"
+            pr_body += "<table>"
+            header = f"Suggestions"
+            delta = 77
+            header += "&nbsp; " * delta
+            pr_body += f"""<thead><tr><th></th><th>{header}</th></tr></thead>"""
+            pr_body += """<tbody>"""
+            suggestions_labels = dict()
+            # add all suggestions related to each label
+            for suggestion in data['code_suggestions']:
+                label = suggestion['label'].strip().strip("'").strip('"')
+                if label not in suggestions_labels:
+                    suggestions_labels[label] = []
+                suggestions_labels[label].append(suggestion)
+
+            for label, suggestions in suggestions_labels.items():
+                pr_body += f"""<tr><td><strong>{label}</strong></td>"""
+                pr_body += f"""<td>"""
+                # pr_body += f"""<details><summary>{len(suggestions)} suggestions</summary>"""
+                pr_body += f"""<table>"""
+                for suggestion in suggestions:
+
+                    relevant_file = suggestion['relevant_file'].strip()
+                    relevant_lines_start = int(suggestion['relevant_lines_start'])
+                    relevant_lines_end = int(suggestion['relevant_lines_end'])
+                    range_str = ""
+                    if relevant_lines_start == relevant_lines_end:
+                        range_str = f"[{relevant_lines_start}]"
                    else:
-                        data_markdown += f"File: {s['relevant file']} ({s['relevant lines start']}-{s['relevant lines end']})\n\n"
-                    if self.git_provider.is_supported("gfm_markdown"):
-                        data_markdown += "<details> <summary> Example code:</summary>\n\n"
-                        data_markdown += f"___\n\n"
-                    language_name = "python"
-                    if extension_s and (extension_s in extension_to_language):
-                        language_name = extension_to_language[extension_s]
-                    data_markdown += f"Existing code:\n```{language_name}\n{s['existing code']}\n```\n"
-                    data_markdown += f"Improved code:\n```{language_name}\n{s['improved code']}\n```\n"
-                    if self.git_provider.is_supported("gfm_markdown"):
-                        data_markdown += "</details>\n"
-                    data_markdown += "\n___\n\n"
-                except Exception as e:
-                    get_logger().error(f"Could not parse suggestion: {s}, error: {e}")
-            self.git_provider.publish_comment(data_markdown)
+                        range_str = f"[{relevant_lines_start}-{relevant_lines_end}]"
+                    code_snippet_link = self.git_provider.get_line_link(relevant_file, relevant_lines_start,
+                                                                        relevant_lines_end)
+                    # add html table for each suggestion
+
+                    suggestion_content = suggestion['suggestion_content'].rstrip().rstrip()
+
+                    suggestion_content = insert_br_after_x_chars(suggestion_content, 90)
+                    # pr_body += f"<tr><td><details><summary>{suggestion_content}</summary>"
+                    existing_code = suggestion['existing_code'].rstrip()+"\n"
+                    improved_code = suggestion['improved_code'].rstrip()+"\n"
+
+                    diff = difflib.unified_diff(existing_code.split('\n'),
+                                                improved_code.split('\n'), n=999)
+                    patch_orig = "\n".join(diff)
+                    patch = "\n".join(patch_orig.splitlines()[5:]).strip('\n')
+
+                    example_code = ""
+                    example_code += f"```diff\n{patch}\n```\n"
+
+                    pr_body += f"""<tr><td>"""
+                    suggestion_summary = suggestion['one_sentence_summary'].strip()
+                    if '`' in suggestion_summary:
+                        suggestion_summary = replace_code_tags(suggestion_summary)
+                    suggestion_summary = suggestion_summary + max((77-len(suggestion_summary)), 0)*"&nbsp;"
+                    pr_body += f"""\n\n<details><summary>{suggestion_summary}</summary>\n\n___\n\n"""
+
+                    pr_body += f"""
+  
+  
+**{suggestion_content}**
+    
+[{relevant_file} {range_str}]({code_snippet_link})
+
+{example_code}                   
+"""
+                    pr_body += f"</details>"
+                    pr_body += f"</td></tr>"
+
+                pr_body += """</table>"""
+                # pr_body += "</details>"
+                pr_body += """</td></tr>"""
+            pr_body += """</tr></tbody></table>"""
+            return pr_body
        except Exception as e:
            get_logger().info(f"Failed to publish summarized code suggestions, error: {e}")
-
-
+            return ""
--- a/pr_agent/tools/pr_config.py
+++ b/pr_agent/tools/pr_config.py
@ -7,7 +7,7 @@ class PRConfig:
    """
    The PRConfig class is responsible for listing all configuration options available for the user.
    """
-    def __init__(self, pr_url: str, args=None):
+    def __init__(self, pr_url: str, args=None, ai_handler=None):
        """
        Initialize the PRConfig object with the necessary attributes and objects to comment on a pull request.

--- a/pr_agent/tools/pr_description.py
+++ b/pr_agent/tools/pr_description.py
@ -1,10 +1,12 @@
 import copy
 import re
+from functools import partial
 from typing import List, Tuple

 from jinja2 import Environment, StrictUndefined

-from pr_agent.algo.ai_handler import AiHandler
+from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
+from pr_agent.algo.ai_handlers.litellm_ai_handler import LiteLLMAIHandler
 from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
 from pr_agent.algo.token_handler import TokenHandler
 from pr_agent.algo.utils import load_yaml, set_custom_labels, get_user_labels
@ -12,10 +14,12 @@ from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
 from pr_agent.git_providers.git_provider import get_main_pr_language
 from pr_agent.log import get_logger
+from pr_agent.servers.help import HelpMessage


 class PRDescription:
-    def __init__(self, pr_url: str, args: list = None):
+    def __init__(self, pr_url: str, args: list = None,
+                 ai_handler: partial[BaseAiHandler,] = LiteLLMAIHandler):
        """
        Initialize the PRDescription object with the necessary attributes and objects for generating a PR description
        using an AI model.
@ -36,7 +40,7 @@ class PRDescription:
            get_settings().pr_description.enable_semantic_files_types = False

        # Initialize the AI handler
-        self.ai_handler = AiHandler()
+        self.ai_handler = ai_handler()
    
        # Initialize the variables dictionary
        self.vars = {
@ -45,12 +49,10 @@ class PRDescription:
            "description": self.git_provider.get_pr_description(full=False),
            "language": self.main_pr_language,
            "diff": "",  # empty diff for initial calculation
-            "use_bullet_points": get_settings().pr_description.use_bullet_points,
            "extra_instructions": get_settings().pr_description.extra_instructions,
            "commit_messages_str": self.git_provider.get_commit_messages(),
            "enable_custom_labels": get_settings().config.enable_custom_labels,
            "custom_labels_class": "",  # will be filled if necessary in 'set_custom_labels' function
-            "enable_file_walkthrough": get_settings().pr_description.enable_file_walkthrough,
            "enable_semantic_files_types": get_settings().pr_description.enable_semantic_files_types,
        }

@ -84,6 +86,7 @@ class PRDescription:
            if self.prediction:
                self._prepare_data()
            else:
+                self.git_provider.remove_initial_comment()
                return None

            if get_settings().pr_description.enable_semantic_files_types:
@ -97,20 +100,34 @@ class PRDescription:
                pr_title, pr_body = self._prepare_pr_answer_with_markers()
            else:
                pr_title, pr_body,  = self._prepare_pr_answer()
+
+            # Add help text if gfm_markdown is supported
+            if self.git_provider.is_supported("gfm_markdown") and get_settings().pr_description.enable_help_text:
+                pr_body += "<hr>\n\n<details> <summary><strong>✨ Usage guide:</strong></summary><hr> \n\n"
+                pr_body += HelpMessage.get_describe_usage_guide()
+                pr_body += "\n</details>\n"
+
+            # final markdown description
            full_markdown_description = f"## Title\n\n{pr_title}\n\n___\n{pr_body}"
+            get_logger().debug(f"full_markdown_description:\n{full_markdown_description}")

            if get_settings().config.publish_output:
                get_logger().info(f"Pushing answer {self.pr_id}")
-                if get_settings().pr_description.publish_description_as_comment:
-                    get_logger().info(f"Publishing answer as comment")
-                    self.git_provider.publish_comment(full_markdown_description)
-                else:
-                    self.git_provider.publish_description(pr_title, pr_body)
+
+                # publish labels
                if get_settings().pr_description.publish_labels and self.git_provider.is_supported("get_labels"):
                    current_labels = self.git_provider.get_pr_labels()
                    user_labels = get_user_labels(current_labels)
                    self.git_provider.publish_labels(pr_labels + user_labels)

+                # publish description
+                if get_settings().pr_description.publish_description_as_comment:
+                    get_logger().info(f"Publishing answer as comment")
+                    self.git_provider.publish_comment(full_markdown_description)
+                else:
+                    self.git_provider.publish_description(pr_title, pr_body)
+
+                    # publish final update message
                    if (get_settings().pr_description.final_update_message and
                            hasattr(self.git_provider, 'pr_url') and self.git_provider.pr_url):
                        latest_commit_url = self.git_provider.get_latest_commit_url()
@ -124,26 +141,17 @@ class PRDescription:
        return ""

    async def _prepare_prediction(self, model: str) -> None:
-        """
-        Prepare the AI prediction for the PR description based on the provided model.
-
-        Args:
-            model (str): The name of the model to be used for generating the prediction.
-
-        Returns:
-            None
-
-        Raises:
-            Any exceptions raised by the 'get_pr_diff' and '_get_prediction' functions.
-
-        """
        if get_settings().pr_description.use_description_markers and 'pr_agent:' not in self.user_description:
            return None

        get_logger().info(f"Getting PR diff {self.pr_id}")
        self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
+        if self.patches_diff:
            get_logger().info(f"Getting AI prediction {self.pr_id}")
            self.prediction = await self._get_prediction(model)
+        else:
+            get_logger().error(f"Error getting PR diff {self.pr_id}")
+            self.prediction = None

    async def _get_prediction(self, model: str) -> str:
        """
@ -160,6 +168,7 @@ class PRDescription:

        environment = Environment(undefined=StrictUndefined)
        set_custom_labels(variables, self.git_provider)
+        self.variables = variables
        system_prompt = environment.from_string(get_settings().pr_description_prompt.system).render(variables)
        user_prompt = environment.from_string(get_settings().pr_description_prompt.user).render(variables)

@ -186,6 +195,22 @@ class PRDescription:
        if get_settings().pr_description.add_original_user_description and self.user_description:
            self.data["User Description"] = self.user_description

+        # re-order keys
+        if 'User Description' in self.data:
+            self.data['User Description'] = self.data.pop('User Description')
+        if 'title' in self.data:
+            self.data['title'] = self.data.pop('title')
+        if 'type' in self.data:
+            self.data['type'] = self.data.pop('type')
+        if 'labels' in self.data:
+            self.data['labels'] = self.data.pop('labels')
+        if 'description' in self.data:
+            self.data['description'] = self.data.pop('description')
+        if 'pr_files' in self.data:
+            self.data['pr_files'] = self.data.pop('pr_files')
+
+
+

    def _prepare_labels(self) -> List[str]:
        pr_types = []
@ -201,6 +226,16 @@ class PRDescription:
                pr_types = self.data['type']
            elif type(self.data['type']) == str:
                pr_types = self.data['type'].split(',')
+
+        # convert lowercase labels to original case
+        try:
+            if "labels_minimal_to_labels_dict" in self.variables:
+                d: dict = self.variables["labels_minimal_to_labels_dict"]
+                for i, label_i in enumerate(pr_types):
+                    if label_i in d:
+                        pr_types[i] = d[label_i]
+        except Exception as e:
+            get_logger().error(f"Error converting labels to original case {self.pr_id}: {e}")
        return pr_types

    def _prepare_pr_answer_with_markers(self) -> Tuple[str, str]:
@ -222,16 +257,15 @@ class PRDescription:
            summary = f"{ai_header}{ai_summary}"
            body = body.replace('pr_agent:summary', summary)

-        if not re.search(r'<!--\s*pr_agent:walkthrough\s*-->', body):
-            ai_walkthrough = self.data.get('PR Main Files Walkthrough')
-            if ai_walkthrough:
-                walkthrough = str(ai_header)
-                for file in ai_walkthrough:
-                    filename = file['filename'].replace("'", "`")
-                    description = file['changes in file'].replace("'", "`")
-                    walkthrough += f'- `{filename}`: {description}\n'
-
-                body = body.replace('pr_agent:walkthrough', walkthrough)
+        ai_walkthrough = self.data.get('pr_files')
+        if ai_walkthrough and not re.search(r'<!--\s*pr_agent:walkthrough\s*-->', body):
+            try:
+                walkthrough_gfm = ""
+                walkthrough_gfm = self.process_pr_files_prediction(walkthrough_gfm, self.file_label_dict)
+                body = body.replace('pr_agent:walkthrough', walkthrough_gfm)
+            except Exception as e:
+                get_logger().error(f"Failing to process walkthrough {self.pr_id}: {e}")
+                body = body.replace('pr_agent:walkthrough', "")

        return title, body

@ -252,7 +286,7 @@ class PRDescription:
        if not get_settings().pr_description.enable_pr_type:
            self.data.pop('type')
        for key, value in self.data.items():
-            markdown_text += f"## {key}\n\n"
+            markdown_text += f"## **{key}**\n\n"
            markdown_text += f"{value}\n\n"

        # Remove the 'PR Title' key from the dictionary
@ -270,10 +304,10 @@ class PRDescription:
        for idx, (key, value) in enumerate(self.data.items()):
            if key == 'pr_files':
                value = self.file_label_dict
-                key_publish = "PR changes walkthrough"
+                key_publish = "Changes walkthrough"
            else:
                key_publish = key.rstrip(':').replace("_", " ").capitalize()
-            pr_body += f"## {key_publish}\n"
+            pr_body += f"## **{key_publish}**\n"
            if 'walkthrough' in key.lower():
                if self.git_provider.is_supported("gfm_markdown"):
                    pr_body += "<details> <summary>files:</summary>\n\n"
@ -304,43 +338,62 @@ class PRDescription:
            try:
                filename = file['filename'].replace("'", "`").replace('"', '`')
                changes_summary = file['changes_summary']
-                label = file['label']
+                changes_title = file['changes_title'].strip()
+                label = file.get('label')
                if label not in self.file_label_dict:
                    self.file_label_dict[label] = []
-                self.file_label_dict[label].append((filename, changes_summary))
+                self.file_label_dict[label].append((filename, changes_title, changes_summary))
            except Exception as e:
                get_logger().error(f"Error preparing file label dict {self.pr_id}: {e}")
                pass

    def process_pr_files_prediction(self, pr_body, value):
+        # logic for using collapsible file list
+        use_collapsible_file_list = get_settings().pr_description.collapsible_file_list
+        num_files = 0
+        if value:
+            for semantic_label in value.keys():
+                num_files += len(value[semantic_label])
+        if use_collapsible_file_list == "adaptive":
+            use_collapsible_file_list = num_files > 8
+
        if not self.git_provider.is_supported("gfm_markdown"):
            get_logger().info(f"Disabling semantic files types for {self.pr_id} since gfm_markdown is not supported")
            return pr_body
        try:
            pr_body += "<table>"
            header = f"Relevant files"
-            delta = 65
-            header += "&nbsp; " * delta
-            pr_body += f"""<thead><tr><th></th><th>{header}</th></tr></thead>"""
+            delta = 77
+            # header += "&nbsp; " * delta
+            pr_body += f"""<thead><tr><th></th><th align="left">{header}</th></tr></thead>"""
            pr_body += """<tbody>"""
            for semantic_label in value.keys():
                s_label = semantic_label.strip("'").strip('"')
                pr_body += f"""<tr><td><strong>{s_label.capitalize()}</strong></td>"""
                list_tuples = value[semantic_label]
+
+                if use_collapsible_file_list:
                    pr_body += f"""<td><details><summary>{len(list_tuples)} files</summary><table>"""
-                for filename, file_change_description in list_tuples:
+                else:
+                    pr_body += f"""<td><table>"""
+                for filename, file_changes_title, file_change_description in list_tuples:
                    filename = filename.replace("'", "`")
                    filename_publish = filename.split("/")[-1]
-                    filename_publish = f"{filename_publish}"
-                    if len(filename_publish) < (delta - 5):
-                        filename_publish += "&nbsp; " * ((delta - 5) - len(filename_publish))
+                    file_changes_title_br = insert_br_after_x_chars(file_changes_title, x=(delta - 5),
+                                                                    new_line_char="\n\n")
+                    file_changes_title_extended = file_changes_title_br.strip() + "</code>"
+                    if len(file_changes_title_extended) < (delta - 5):
+                        file_changes_title_extended += "&nbsp; " * ((delta - 5) - len(file_changes_title_extended))
+                    filename_publish = f"<strong>{filename_publish}</strong><dd><code>{file_changes_title_extended}</dd>"
                    diff_plus_minus = ""
+                    delta_nbsp = ""
                    diff_files = self.git_provider.diff_files
                    for f in diff_files:
                        if f.filename.lower() == filename.lower():
                            num_plus_lines = f.num_plus_lines
                            num_minus_lines = f.num_minus_lines
                            diff_plus_minus += f"+{num_plus_lines}/-{num_minus_lines}"
+                            delta_nbsp = "&nbsp; " * max(0, (8 - len(diff_plus_minus)))
                            break

                    # try to add line numbers link to code suggestions
@ -349,23 +402,25 @@ class PRDescription:
                        filename = filename.strip()
                        link = self.git_provider.get_line_link(filename, relevant_line_start=-1)

-                    file_change_description = self._insert_br_after_x_chars(file_change_description, x=(delta - 5))
+                    file_change_description_br = insert_br_after_x_chars(file_change_description, x=(delta - 5))
                    pr_body += f"""
 <tr>
  <td>
    <details>
-      <summary><strong>{filename_publish}</strong></summary>
-      <ul>
-        {filename}<br><br>
-        <strong>{file_change_description}</strong>
-      </ul>
+      <summary>{filename_publish}</summary>
+<hr>
+
+{filename}
+{file_change_description_br}
    </details>
  </td>
-  <td><a href="{link}"> {diff_plus_minus}</a></td>
-
+  <td><a href="{link}">{diff_plus_minus}</a>{delta_nbsp}</td>
 </tr>                    
 """
+                if use_collapsible_file_list:
                    pr_body += """</table></details></td></tr>"""
+                else:
+                    pr_body += """</table></td></tr>"""
            pr_body += """</tr></tbody></table>"""

        except Exception as e:
@ -373,25 +428,48 @@ class PRDescription:
            pass
        return pr_body

-    def _insert_br_after_x_chars(self, text, x=70):
+def insert_br_after_x_chars(text, x=70, new_line_char="<br> "):
    """
    Insert <br> into a string after a word that increases its length above x characters.
    """
    if len(text) < x:
        return text

-        words = text.split(' ')
+    lines = text.splitlines()
+    words = []
+    for i,line in enumerate(lines):
+        words += line.split(' ')
+        if i<len(lines)-1:
+            words[-1] += "\n"
+
+
+    # words = text.split(' ')
+
    new_text = ""
    current_length = 0
-
+    is_inside_code = False
    for word in words:
        # Check if adding this word exceeds x characters
        if current_length + len(word) > x:
-                new_text += "<br>"  # Insert line break
+            if not is_inside_code:
+                new_text += f"{new_line_char} "  # Insert line break
                current_length = 0  # Reset counter
+            else:
+                new_text += f"`{new_line_char} `"
+        # check if inside <code> tag
+        if word.startswith("`") and not is_inside_code and not word.endswith("`"):
+            is_inside_code = True
+        if word.endswith("`"):
+            is_inside_code = False

        # Add the word to the new text
+        if word.endswith("\n"):
+            new_text += word
+        else:
            new_text += word + " "
        current_length += len(word) + 1  # Add 1 for the space

+
+        if word.endswith("\n"):
+            current_length = 0
    return new_text.strip()  # Remove trailing space
--- a/pr_agent/tools/pr_generate_labels.py
+++ b/pr_agent/tools/pr_generate_labels.py
@ -1,10 +1,12 @@
 import copy
 import re
+from functools import partial
 from typing import List, Tuple

 from jinja2 import Environment, StrictUndefined

-from pr_agent.algo.ai_handler import AiHandler
+from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
+from pr_agent.algo.ai_handlers.litellm_ai_handler import LiteLLMAIHandler
 from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
 from pr_agent.algo.token_handler import TokenHandler
 from pr_agent.algo.utils import load_yaml, set_custom_labels, get_user_labels
@ -15,7 +17,8 @@ from pr_agent.log import get_logger


 class PRGenerateLabels:
-    def __init__(self, pr_url: str, args: list = None):
+    def __init__(self, pr_url: str, args: list = None,
+                 ai_handler: partial[BaseAiHandler,] = LiteLLMAIHandler):
        """
        Initialize the PRGenerateLabels object with the necessary attributes and objects for generating labels
        corresponding to the PR using an AI model.
@ -31,7 +34,7 @@ class PRGenerateLabels:
        self.pr_id = self.git_provider.get_pr_id()

        # Initialize the AI handler
-        self.ai_handler = AiHandler()
+        self.ai_handler = ai_handler()
    
        # Initialize the variables dictionary
        self.vars = {
@ -40,7 +43,6 @@ class PRGenerateLabels:
            "description": self.git_provider.get_pr_description(full=False),
            "language": self.main_pr_language,
            "diff": "",  # empty diff for initial calculation
-            "use_bullet_points": get_settings().pr_description.use_bullet_points,
            "extra_instructions": get_settings().pr_description.extra_instructions,
            "commit_messages_str": self.git_provider.get_commit_messages(),
            "enable_custom_labels": get_settings().config.enable_custom_labels,
@ -133,6 +135,7 @@ class PRGenerateLabels:

        environment = Environment(undefined=StrictUndefined)
        set_custom_labels(variables, self.git_provider)
+        self.variables = variables
        system_prompt = environment.from_string(get_settings().pr_custom_labels_prompt.system).render(variables)
        user_prompt = environment.from_string(get_settings().pr_custom_labels_prompt.user).render(variables)

@ -168,4 +171,14 @@ class PRGenerateLabels:
            elif type(self.data['labels']) == str:
                pr_types = self.data['labels'].split(',')

+        # convert lowercase labels to original case
+        try:
+            if "labels_minimal_to_labels_dict" in self.variables:
+                d: dict = self.variables["labels_minimal_to_labels_dict"]
+                for i, label_i in enumerate(pr_types):
+                    if label_i in d:
+                        pr_types[i] = d[label_i]
+        except Exception as e:
+            get_logger().error(f"Error converting labels to original case {self.pr_id}: {e}")
+
        return pr_types
--- a/pr_agent/tools/pr_information_from_user.py
+++ b/pr_agent/tools/pr_information_from_user.py
@ -1,8 +1,10 @@
 import copy
+from functools import partial

 from jinja2 import Environment, StrictUndefined

-from pr_agent.algo.ai_handler import AiHandler
+from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
+from pr_agent.algo.ai_handlers.litellm_ai_handler import LiteLLMAIHandler
 from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
 from pr_agent.algo.token_handler import TokenHandler
 from pr_agent.config_loader import get_settings
@ -12,12 +14,13 @@ from pr_agent.log import get_logger


 class PRInformationFromUser:
-    def __init__(self, pr_url: str, args: list = None):
+    def __init__(self, pr_url: str, args: list = None,
+                 ai_handler: partial[BaseAiHandler,] = LiteLLMAIHandler):
        self.git_provider = get_git_provider()(pr_url)
        self.main_pr_language = get_main_pr_language(
            self.git_provider.get_languages(), self.git_provider.get_files()
        )
-        self.ai_handler = AiHandler()
+        self.ai_handler = ai_handler()
        self.vars = {
            "title": self.git_provider.pr.title,
            "branch": self.git_provider.get_pr_branch(),
--- a/pr_agent/tools/pr_questions.py
+++ b/pr_agent/tools/pr_questions.py
@ -1,24 +1,27 @@
 import copy
+from functools import partial

 from jinja2 import Environment, StrictUndefined

-from pr_agent.algo.ai_handler import AiHandler
+from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
+from pr_agent.algo.ai_handlers.litellm_ai_handler import LiteLLMAIHandler
 from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
 from pr_agent.algo.token_handler import TokenHandler
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
 from pr_agent.git_providers.git_provider import get_main_pr_language
 from pr_agent.log import get_logger
+from pr_agent.servers.help import HelpMessage


 class PRQuestions:
-    def __init__(self, pr_url: str, args=None):
+    def __init__(self, pr_url: str, args=None, ai_handler: partial[BaseAiHandler,] = LiteLLMAIHandler):
        question_str = self.parse_args(args)
        self.git_provider = get_git_provider()(pr_url)
        self.main_pr_language = get_main_pr_language(
            self.git_provider.get_languages(), self.git_provider.get_files()
        )
-        self.ai_handler = AiHandler()
+        self.ai_handler = ai_handler()
        self.question_str = question_str
        self.vars = {
            "title": self.git_provider.pr.title,
@ -50,6 +53,11 @@ class PRQuestions:
        await retry_with_fallback_models(self._prepare_prediction)
        get_logger().info('Preparing answer...')
        pr_comment = self._prepare_pr_answer()
+        if self.git_provider.is_supported("gfm_markdown") and get_settings().pr_questions.enable_help_text:
+            pr_comment += "<hr>\n\n<details> <summary><strong>✨ Usage guide:</strong></summary><hr> \n\n"
+            pr_comment += HelpMessage.get_ask_usage_guide()
+            pr_comment += "\n</details>\n"
+
        if get_settings().config.publish_output:
            get_logger().info('Pushing answer...')
            self.git_provider.publish_comment(pr_comment)
--- a/pr_agent/tools/pr_reviewer.py
+++ b/pr_agent/tools/pr_reviewer.py
@ -1,13 +1,15 @@
 import copy
 import datetime
 from collections import OrderedDict
+from functools import partial
 from typing import List, Tuple

 import yaml
 from jinja2 import Environment, StrictUndefined
 from yaml import SafeLoader

-from pr_agent.algo.ai_handler import AiHandler
+from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
+from pr_agent.algo.ai_handlers.litellm_ai_handler import LiteLLMAIHandler
 from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
 from pr_agent.algo.token_handler import TokenHandler
 from pr_agent.algo.utils import convert_to_markdown, load_yaml, try_fix_yaml, set_custom_labels, get_user_labels
@ -15,20 +17,23 @@ from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
 from pr_agent.git_providers.git_provider import IncrementalPR, get_main_pr_language
 from pr_agent.log import get_logger
-from pr_agent.servers.help import actions_help_text, bot_help_text
+from pr_agent.servers.help import HelpMessage


 class PRReviewer:
    """
    The PRReviewer class is responsible for reviewing a pull request and generating feedback using an AI model.
    """
-    def __init__(self, pr_url: str, is_answer: bool = False, is_auto: bool = False, args: list = None):
+    def __init__(self, pr_url: str, is_answer: bool = False, is_auto: bool = False, args: list = None,
+                 ai_handler: partial[BaseAiHandler,] = LiteLLMAIHandler):
        """
        Initialize the PRReviewer object with the necessary attributes and objects to review a pull request.

        Args:
            pr_url (str): The URL of the pull request to be reviewed.
            is_answer (bool, optional): Indicates whether the review is being done in answer mode. Defaults to False.
+            is_auto (bool, optional): Indicates whether the review is being done in automatic mode. Defaults to False.
+            ai_handler (BaseAiHandler): The AI handler to be used for the review. Defaults to None.
            args (list, optional): List of arguments passed to the PRReviewer class. Defaults to None.
        """
        self.parse_args(args) # -i command
@ -43,7 +48,7 @@ class PRReviewer:

        if self.is_answer and not self.git_provider.is_supported("get_issue_comments"):
            raise Exception(f"Answer mode is not supported for {get_settings().config.git_provider} for now")
-        self.ai_handler = AiHandler()
+        self.ai_handler = ai_handler()
        self.patches_diff = None
        self.prediction = None

@ -93,14 +98,7 @@ class PRReviewer:
        self.incremental = IncrementalPR(is_incremental)

    async def run(self) -> None:
-        """
-        Review the pull request and generate feedback.
-        """
-
        try:
-            if self.is_auto and not get_settings().pr_reviewer.automatic_review:
-                get_logger().info(f'Automatic review is disabled {self.pr_url}')
-                return None
            if self.incremental.is_incremental and not self._can_run_incremental_review():
                return None

@ -110,6 +108,9 @@ class PRReviewer:
                self.git_provider.publish_comment("Preparing review...", is_temporary=True)

            await retry_with_fallback_models(self._prepare_prediction)
+            if not self.prediction:
+                self.git_provider.remove_initial_comment()
+                return None

            get_logger().info('Preparing PR review...')
            pr_comment = self._prepare_pr_review()
@ -136,19 +137,14 @@ class PRReviewer:
            get_logger().error(f"Failed to review PR: {e}")

    async def _prepare_prediction(self, model: str) -> None:
-        """
-        Prepare the AI prediction for the pull request review.
-
-        Args:
-            model: A string representing the AI model to be used for the prediction.
-
-        Returns:
-            None
-        """
        get_logger().info('Getting PR diff...')
        self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
+        if self.patches_diff:
            get_logger().info('Getting AI prediction...')
            self.prediction = await self._get_prediction(model)
+        else:
+            get_logger().error(f"Error getting PR diff")
+            self.prediction = None

    async def _get_prediction(self, model: str) -> str:
        """
@ -244,19 +240,11 @@ class PRReviewer:
            data.move_to_end('Incremental PR Review', last=False)

        markdown_text = convert_to_markdown(data, self.git_provider.is_supported("gfm_markdown"))
-        user = self.git_provider.get_user_id()

-        # Add help text if not in CLI mode
-        if not get_settings().get("CONFIG.CLI_MODE", False):
-            markdown_text += "\n### How to use\n"
-            if self.git_provider.is_supported("gfm_markdown"):
-                markdown_text += "\n <details> <summary> Instructions</summary>\n\n"
-            bot_user = "[bot]" if get_settings().github_app.override_deployment_type else get_settings().github_app.bot_user
-            if user and bot_user not in user:
-                markdown_text += bot_help_text(user)
-            else:
-                markdown_text += actions_help_text
-            if self.git_provider.is_supported("gfm_markdown"):
+        # Add help text if gfm_markdown is supported
+        if self.git_provider.is_supported("gfm_markdown") and get_settings().pr_reviewer.enable_help_text:
+            markdown_text += "<hr>\n\n<details> <summary><strong>✨ Usage guide:</strong></summary><hr> \n\n"
+            markdown_text += HelpMessage.get_review_usage_guide()
            markdown_text += "\n</details>\n"

        # Add custom labels from the review prediction (effort, security)
@ -393,9 +381,12 @@ class PRReviewer:
                        review_labels.append('Possible security concern')

                current_labels = self.git_provider.get_pr_labels()
+                if current_labels:
                    current_labels_filtered = [label for label in current_labels if
                                               not label.lower().startswith('review effort [1-5]:') and not label.lower().startswith(
                                                   'possible security concern')]
+                else:
+                    current_labels_filtered = []
                if current_labels or review_labels:
                    get_logger().info(f"Setting review labels: {review_labels + current_labels_filtered}")
                    self.git_provider.publish_labels(review_labels + current_labels_filtered)
--- a/pr_agent/tools/pr_similar_issue.py
+++ b/pr_agent/tools/pr_similar_issue.py
@ -19,7 +19,7 @@ MODEL = "text-embedding-ada-002"


 class PRSimilarIssue:
-    def __init__(self, issue_url: str, args: list = None):
+    def __init__(self, issue_url: str, ai_handler, args: list = None):
        if get_settings().config.git_provider != "github":
            raise Exception("Only github is supported for similar issue tool")

@ -35,6 +35,7 @@ class PRSimilarIssue:
        repo_name_for_index = self.repo_name_for_index = repo_obj.full_name.lower().replace('/', '-').replace('_/', '-')
        index_name = self.index_name = "codium-ai-pr-agent-issues"

+        if get_settings().pr_similar_issue.vectordb == "pinecone":
            # assuming pinecone api key and environment are set in secrets file
            try:
                api_key = get_settings().pinecone.api_key
@ -105,6 +106,69 @@ class PRSimilarIssue:
                else:
                    get_logger().info('No new issues to update')
        
+        elif get_settings().pr_similar_issue.vectordb == "lancedb":
+            import lancedb # import lancedb only if needed
+            self.db = lancedb.connect(get_settings().lancedb.uri)
+            self.table = None
+
+            run_from_scratch = False
+            if run_from_scratch:  # for debugging
+                if index_name in self.db.table_names():
+                    get_logger().info('Removing Table...')
+                    self.db.drop_table(index_name)
+                    get_logger().info('Done')
+
+            ingest = True
+            if index_name not in self.db.table_names():
+                run_from_scratch = True
+                ingest = False
+            else:
+                if get_settings().pr_similar_issue.force_update_dataset:
+                    ingest = True
+                else:
+                    self.table = self.db[index_name]
+                    res = self.table.search().limit(len(self.table)).where(f"id='example_issue_{repo_name_for_index}'").to_list()
+                    get_logger().info("result: ", res)
+                    if res[0].get("vector"):
+                        ingest = False
+
+            if run_from_scratch or ingest:  # indexing the entire repo
+                get_logger().info('Indexing the entire repo...')
+
+                get_logger().info('Getting issues...')
+                issues = list(repo_obj.get_issues(state='all'))
+                get_logger().info('Done')
+
+                self._update_table_with_issues(issues, repo_name_for_index, ingest=ingest)
+            else:  # update table if needed
+                issues_to_update = []
+                issues_paginated_list = repo_obj.get_issues(state='all')
+                counter = 1
+                for issue in issues_paginated_list:
+                    if issue.pull_request:
+                        continue
+                    issue_str, comments, number = self._process_issue(issue)
+                    issue_key = f"issue_{number}"
+                    issue_id = issue_key + "." + "issue"
+                    res = self.table.search().limit(len(self.table)).where(f"id='{issue_id}'").to_list()
+                    is_new_issue = True
+                    for r in res:
+                        if r['metadata']['repo'] == repo_name_for_index:
+                            is_new_issue = False
+                            break
+                    if is_new_issue:
+                        counter += 1
+                        issues_to_update.append(issue)
+                    else:
+                        break
+
+                if issues_to_update:
+                    get_logger().info(f'Updating index with {counter} new issues...')
+                    self._update_table_with_issues(issues_to_update, repo_name_for_index, ingest=True)
+                else:
+                    get_logger().info('No new issues to update')
+        
+
    async def run(self):
        get_logger().info('Getting issue...')
        repo_name, original_issue_number = self.git_provider._parse_issue_url(self.issue_url.split('=')[-1])
@ -116,14 +180,18 @@ class PRSimilarIssue:
        get_logger().info('Querying...')
        res = openai.Embedding.create(input=[issue_str], engine=MODEL)
        embeds = [record['embedding'] for record in res['data']]
+
+        relevant_issues_number_list = []
+        relevant_comment_number_list = []
+        score_list = []
+        
+        if get_settings().pr_similar_issue.vectordb == "pinecone":
            pinecone_index = pinecone.Index(index_name=self.index_name)
            res = pinecone_index.query(embeds[0],
                                    top_k=5,
                                    filter={"repo": self.repo_name_for_index},
                                    include_metadata=True).to_dict()
-        relevant_issues_number_list = []
-        relevant_comment_number_list = []
-        score_list = []
+        
            for r in res['matches']:
                # skip example issue
                if 'example_issue_' in r["id"]:
@ -146,8 +214,35 @@ class PRSimilarIssue:
                score_list.append(str("{:.2f}".format(r['score'])))
            get_logger().info('Done')

+        elif get_settings().pr_similar_issue.vectordb == "lancedb":
+            res = self.table.search(embeds[0]).where(f"metadata.repo='{self.repo_name_for_index}'", prefilter=True).to_list()
+            
+            for r in res:
+                # skip example issue
+                if 'example_issue_' in r["id"]:
+                    continue
+                
+                try:
+                    issue_number = int(r["id"].split('.')[0].split('_')[-1])
+                except:
+                    get_logger().debug(f"Failed to parse issue number from {r['id']}")
+                    continue
+
+                if original_issue_number == issue_number:
+                    continue
+                if issue_number not in relevant_issues_number_list:
+                    relevant_issues_number_list.append(issue_number)
+                
+                if 'comment' in r["id"]:
+                    relevant_comment_number_list.append(int(r["id"].split('.')[1].split('_')[-1]))
+                else:
+                    relevant_comment_number_list.append(-1)
+                score_list.append(str("{:.2f}".format(1-r['_distance'])))
+            get_logger().info('Done')
+        
        get_logger().info('Publishing response...')
        similar_issues_str = "### Similar Issues\n___\n\n"
+
        for i, issue_number_similar in enumerate(relevant_issues_number_list):
            issue = self.git_provider.repo_obj.get_issue(issue_number_similar)
            title = issue.title
@ -266,6 +361,96 @@ class PRSimilarIssue:
            time.sleep(5)  # wait for pinecone to finalize upserting before querying
        get_logger().info('Done')

+    def _update_table_with_issues(self, issues_list, repo_name_for_index, ingest=False):
+        get_logger().info('Processing issues...')
+
+        corpus = Corpus()
+        example_issue_record = Record(
+            id=f"example_issue_{repo_name_for_index}",
+            text="example_issue",
+            metadata=Metadata(repo=repo_name_for_index)
+        )
+        corpus.append(example_issue_record)
+
+        counter = 0
+        for issue in issues_list:
+            if issue.pull_request:
+                continue
+
+            counter += 1
+            if counter % 100 == 0:
+                get_logger().info(f"Scanned {counter} issues")
+            if counter >= self.max_issues_to_scan:
+                get_logger().info(f"Scanned {self.max_issues_to_scan} issues, stopping")
+                break
+
+            issue_str, comments, number = self._process_issue(issue)
+            issue_key = f"issue_{number}"
+            username = issue.user.login
+            created_at = str(issue.created_at)
+            if len(issue_str) < 8000 or \
+                    self.token_handler.count_tokens(issue_str) < get_max_tokens(MODEL):  # fast reject first
+                issue_record = Record(
+                    id=issue_key + "." + "issue",
+                    text=issue_str,
+                    metadata=Metadata(repo=repo_name_for_index,
+                                        username=username,
+                                        created_at=created_at,
+                                        level=IssueLevel.ISSUE)
+                )
+                corpus.append(issue_record)
+                if comments:
+                    for j, comment in enumerate(comments):
+                        comment_body = comment.body
+                        num_words_comment = len(comment_body.split())
+                        if num_words_comment < 10 or not isinstance(comment_body, str):
+                            continue
+
+                        if len(comment_body) < 8000 or \
+                                self.token_handler.count_tokens(comment_body) < MAX_TOKENS[MODEL]:
+                            comment_record = Record(
+                                id=issue_key + ".comment_" + str(j + 1),
+                                text=comment_body,
+                                metadata=Metadata(repo=repo_name_for_index,
+                                                    username=username,  # use issue username for all comments
+                                                    created_at=created_at,
+                                                    level=IssueLevel.COMMENT)
+                            )
+                            corpus.append(comment_record)
+        df = pd.DataFrame(corpus.dict()["documents"])
+        get_logger().info('Done')
+
+        get_logger().info('Embedding...')
+        openai.api_key = get_settings().openai.key
+        list_to_encode = list(df["text"].values)
+        try:
+            res = openai.Embedding.create(input=list_to_encode, engine=MODEL)
+            embeds = [record['embedding'] for record in res['data']]
+        except:
+            embeds = []
+            get_logger().error('Failed to embed entire list, embedding one by one...')
+            for i, text in enumerate(list_to_encode):
+                try:
+                    res = openai.Embedding.create(input=[text], engine=MODEL)
+                    embeds.append(res['data'][0]['embedding'])
+                except:
+                    embeds.append([0] * 1536)
+        df["vector"] = embeds
+        get_logger().info('Done')
+
+        if not ingest:
+            get_logger().info('Creating table from scratch...')
+            self.table = self.db.create_table(self.index_name, data=df, mode="overwrite")
+            time.sleep(15)  
+        else:
+            get_logger().info('Ingesting in Table...')
+            if self.index_name not in self.db.table_names():
+                self.table.add(df)
+            else:
+                get_logger().info(f"Table {self.index_name} doesn't exists!")
+            time.sleep(5)  
+        get_logger().info('Done')
+

 class IssueLevel(str, Enum):
    ISSUE = "issue"
--- a/pr_agent/tools/pr_update_changelog.py
+++ b/pr_agent/tools/pr_update_changelog.py
@ -1,11 +1,13 @@
 import copy
 from datetime import date
+from functools import partial
 from time import sleep
 from typing import Tuple

 from jinja2 import Environment, StrictUndefined

-from pr_agent.algo.ai_handler import AiHandler
+from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
+from pr_agent.algo.ai_handlers.litellm_ai_handler import LiteLLMAIHandler
 from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
 from pr_agent.algo.token_handler import TokenHandler
 from pr_agent.config_loader import get_settings
@ -17,7 +19,7 @@ CHANGELOG_LINES = 50


 class PRUpdateChangelog:
-    def __init__(self, pr_url: str, cli_mode=False, args=None):
+    def __init__(self, pr_url: str, cli_mode=False, args=None, ai_handler: partial[BaseAiHandler,] = LiteLLMAIHandler):

        self.git_provider = get_git_provider()(pr_url)
        self.main_language = get_main_pr_language(
@ -25,7 +27,7 @@ class PRUpdateChangelog:
        )
        self.commit_changelog = get_settings().pr_update_changelog.push_changelog_changes
        self._get_changlog_file()  # self.changelog_file_str
-        self.ai_handler = AiHandler()
+        self.ai_handler = ai_handler()
        self.patches_diff = None
        self.prediction = None
        self.cli_mode = cli_mode
--- a/pyproject.toml
+++ b/pyproject.toml
@ -17,7 +17,7 @@ maintainers = [
 ]
 description = "CodiumAI PR-Agent is an open-source tool to automatically analyze a pull request and provide several types of feedback"
 readme = "README.md"
-requires-python = ">=3.9"
+requires-python = ">=3.10"
 keywords = ["ai", "tool", "developer", "review", "agent"]
 license = {file = "LICENSE", name = "Apache 2.0 License"}
 classifiers = [
--- a/requirements.txt
+++ b/requirements.txt
@ -1,5 +1,5 @@
 aiohttp==3.9.1
-atlassian-python-api==3.39.0
+atlassian-python-api==3.41.4
 azure-devops==7.1.0b3
 boto3==1.33.6
 dynaconf==3.2.4
@ -14,6 +14,7 @@ msrest==0.7.1
 openai==0.27.8
 pinecone-client
 pinecone-datasets @ git+https://github.com/mrT23/pinecone-datasets.git@main
+lancedb==0.3.4
 pytest==7.4.0
 PyGithub==1.59.*
 PyYAML==6.0.1
@ -23,3 +24,4 @@ starlette-context==0.3.6
 tiktoken==0.5.2
 ujson==5.8.0
 uvicorn==0.22.0
+# langchain==0.0.349 # uncomment this to support language LangChainOpenAIHandler
--- a/tests/unittest/test_convert_to_markdown.py
+++ b/tests/unittest/test_convert_to_markdown.py
@ -71,7 +71,7 @@ class TestConvertToMarkdown:
 - 📌 **Type of PR:** Test type\n\
 - 🧪 **Relevant tests added:** no\n\
 - ✨ **Focused PR:** Yes\n\
-  **General PR suggestions:** general suggestion...\n\n\n- <details><summary> 🤖 Code feedback:</summary>  - **Code example:**\n    - **Before:**\n        ```\n        Code before\n        ```\n    - **After:**\n        ```\n        Code after\n        ```\n\n  - **Code example:**\n    - **Before:**\n        ```\n        Code before 2\n        ```\n    - **After:**\n        ```\n        Code after 2\n        ```\n\n</details>\
+-  **General PR suggestions:** general suggestion...\n\n\n<details><summary> <strong>🤖 Code feedback:</strong></summary>  - **Code example:**\n    - **Before:**\n        ```\n        Code before\n        ```\n    - **After:**\n        ```\n        Code after\n        ```\n\n  - **Code example:**\n    - **Before:**\n        ```\n        Code before 2\n        ```\n    - **After:**\n        ```\n        Code after 2\n        ```\n\n</details>\
 """
        assert convert_to_markdown(input_data).strip() == expected_output.strip()

--- a/tests/unittest/test_try_fix_yaml.py
+++ b/tests/unittest/test_try_fix_yaml.py
@ -19,6 +19,19 @@ class TestTryFixYaml:
        expected_output = {"relevant line": "value: 3"}
        assert try_fix_yaml(review_text) == expected_output

+    # The function extracts YAML snippet
+    def test_extract_snippet(self):
+        review_text = '''\
+Here is the answer in YAML format:
+
+```yaml
+name: John Smith
+age: 35
+```
+'''
+        expected_output = {'name': 'John Smith', 'age': 35}
+        assert try_fix_yaml(review_text) == expected_output
+
    # The function removes the last line(s) of the YAML string and successfully parses the YAML string.
    def test_remove_last_line(self):
        review_text = "key: value\nextra invalid line\n"