dockerhub

Dockerfile.github_action_dockerhub

@@ -1 +1 @@
-FROM codiumai/pr-agent:github_action
+FROM codiumai/pr-agent:0.8-github_action

INSTALL.md

@@ -89,10 +89,10 @@ chmod 600 pr_agent/settings/.secrets.toml
 
 ```
 export PYTHONPATH=[$PYTHONPATH:]<PATH to pr_agent folder>
-python3 -m pr_agent.cli --pr_url <pr_url> review
+python pr_agent/cli.py --pr_url <pr_url> /review
-python3 -m pr_agent.cli --pr_url <pr_url> ask <your question>
+python pr_agent/cli.py --pr_url <pr_url> /ask <your question>
-python3 -m pr_agent.cli --pr_url <pr_url> describe
+python pr_agent/cli.py --pr_url <pr_url> /describe
-python3 -m pr_agent.cli --pr_url <pr_url> improve
+python pr_agent/cli.py --pr_url <pr_url> /improve
 ```
 
 ---

PR_COMPRESSION.md

@@ -1,4 +1,4 @@
-# PR Compression Strategy
+# Git Patch Logic
 There are two scenarios:
 1. The PR is small enough to fit in a single prompt (including system and user prompt)
 2. The PR is too large to fit in a single prompt (including system and user prompt)
@@ -16,7 +16,7 @@ We prioritize the languages of the repo based on the following criteria:
 ## Small PR
 In this case, we can fit the entire PR in a single prompt:
 1. Exclude binary files and non code files (e.g. images, pdfs, etc)
-2. We Expand the surrounding context of each patch to 3 lines above and below the patch
+2. We Expand the surrounding context of each patch to 6 lines above and below the patch
 ## Large PR
 
 ### Motivation
@@ -25,7 +25,7 @@ We want to be able to pack as much information as possible in a single LMM promp
 
 
 
-#### Compression strategy
+#### PR compression strategy
 We prioritize additions over deletions:
  - Combine all deleted files into a single list (`deleted files`)
  - File patches are a list of hunks, remove all hunks of type deletion-only from the hunks in the file patch

README.md

@@ -9,7 +9,6 @@ Making pull requests less painful with an AI agent
 
 [![GitHub license](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://github.com/Codium-ai/pr-agent/blob/main/LICENSE)
 [![Discord](https://badgen.net/badge/icon/discord?icon=discord&label&color=purple)](https://discord.com/channels/1057273017547378788/1126104260430528613)
-[![Twitter](https://img.shields.io/twitter/follow/codiumai)](https://twitter.com/codiumai)
     <a href="https://github.com/Codium-ai/pr-agent/commits/main">
     <img alt="GitHub" src="https://img.shields.io/github/last-commit/Codium-ai/pr-agent/main?style=for-the-badge" height="20">
     </a>
@@ -18,25 +17,22 @@ Making pull requests less painful with an AI agent
 
 CodiumAI `PR-Agent` is an open-source tool aiming to help developers review pull requests faster and more efficiently. It automatically analyzes the pull request and can provide several types of commands:
 
-‣ **Auto Description ([`/describe`](./docs/DESCRIBE.md))**: Automatically generating PR description - title, type, summary, code walkthrough and labels.
+‣ **Auto Description (`/describe`)**: Automatically generating [PR description](https://github.com/Codium-ai/pr-agent/pull/229#issue-1860711415) - title, type, summary, code walkthrough and labels.
 \
-‣ **Auto Review ([`/review`](./docs/REVIEW.md))**: Adjustable feedback about the PR main theme, type, relevant tests, security issues, score, and various suggestions for the PR content.
+‣ **Auto Review (`/review`)**: [Adjustable feedback](https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695022908) about the PR main theme, type, relevant tests, security issues, score, and various suggestions for the PR content.
 \
-‣ **Question Answering ([`/ask ...`](./docs/ASK.md))**: Answering free-text questions about the PR.
+‣ **Question Answering (`/ask ...`)**: Answering [free-text questions](https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695021332) about the PR.
 \
-‣ **Code Suggestions ([`/improve`](./docs/IMPROVE.md))**: Committable code suggestions for improving the PR.
+‣ **Code Suggestions (`/improve`)**: [Committable code suggestions](https://github.com/Codium-ai/pr-agent/pull/229#discussion_r1306919276) for improving the PR.
 \
-‣ **Update Changelog ([`/update_changelog`](./docs/UPDATE_CHANGELOG.md))**: Automatically updating the CHANGELOG.md file with the PR changes.
+‣ **Update Changelog (`/update_changelog`)**: Automatically updating the CHANGELOG.md file with the [PR changes](https://github.com/Codium-ai/pr-agent/pull/168#discussion_r1282077645).
 \
-‣ **Find similar issue ([`/similar_issue`](./docs/SIMILAR_ISSUE.md))**: Automatically retrieves and presents similar issues
+‣ **Find similar issue (`/similar_issue`)**: Automatically retrieves and presents [similar issues](https://github.com/Alibaba-MIIL/ASL/issues/107).
-\
-‣ **Add Documentation ([`/add_docs`](./docs/ADD_DOCUMENTATION.md))**: Automatically adds documentation to un-documented functions/classes in the PR.
 
-See the [Usage Guide](./Usage.md) for instructions how to run the different tools from _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.
+See the [usage guide](./Usage.md) for instructions how to run the different tools from [CLI](./Usage.md#working-from-a-local-repo-cli), or by [online usage](./Usage.md#online-usage), as well as additional details on optional commands and configurations.
 
-See the [Release notes](./RELEASE_NOTES.md) for updates on the latest changes.
+[Release notes](./RELEASE_NOTES.md)
 
 <h3>Example results:</h3>
 </div>
@@ -106,15 +102,13 @@ See the [Release notes](./RELEASE_NOTES.md) for updates on the latest changes.
 |       |                                             | 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:    |          |       |
+|       | Update CHANGELOG.md                         |   :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:    |
 |       |                                             |        |        |      |      |      |
 | 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:    |           |          |          |
@@ -128,7 +122,7 @@ See the [Release notes](./RELEASE_NOTES.md) for updates on the latest changes.
 |       | 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.
+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
 
@@ -171,7 +165,7 @@ There are several ways to use PR-Agent:
 
 The following diagram illustrates PR-Agent tools and their flow:
 
-![PR-Agent Tools](https://www.codium.ai/wp-content/uploads/2023/10/codiumai-diagram-v5.png)
+![PR-Agent Tools](https://www.codium.ai/wp-content/uploads/2023/07/codiumai-diagram-v4.jpg)
 
 Check out the [PR Compression strategy](./PR_COMPRESSION.md) page for more details on how we convert a code diff to a manageable LLM prompt
 
@@ -201,7 +195,7 @@ Here are some advantages of PR-Agent:
   - [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)
+  - [ ] Documentation (is the PR properly documented)
   - [ ] ...
 
 ## Similar Projects

RELEASE_NOTES.md

@@ -36,3 +36,6 @@
 ### Fixed
 - Protection against no code suggestions generated.
 - Resilience to repositories where the languages cannot be automatically detected.
+
+
+

Usage.md

@@ -1,4 +1,4 @@
-## Usage Guide
+## Usage guide
 
 ### Table of Contents
 - [Introduction](#introduction)
@@ -6,19 +6,19 @@
 - [Online usage](#online-usage)
 - [Working with GitHub App](#working-with-github-app)
 - [Working with GitHub Action](#working-with-github-action)
-- [Changing a model](#changing-a-model)
-- [Working with large PRs](#working-with-large-prs)
 - [Appendix - additional configurations walkthrough](#appendix---additional-configurations-walkthrough)
 
 ### Introduction
 
-See the **[installation guide](/INSTALL.md)** for instructions on how to setup PR-Agent. After installation, there are three basic ways to invoke CodiumAI PR-Agent:
+There are 3 basic ways to invoke CodiumAI PR-Agent:
 1. Locally running a CLI command
 2. Online usage - by [commenting](https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695021901) on a PR
 3. Enabling PR-Agent tools to run automatically when a new PR is opened
 
+See the [installation guide](/INSTALL.md) for instructions on how to setup your own PR-Agent.
 
 Specifically, CLI commands can be issued by invoking a pre-built [docker image](/INSTALL.md#running-from-source), or by invoking a [locally cloned repo](INSTALL.md#method-2-run-from-source).
+
 For online usage, you will need to setup either a [GitHub App](INSTALL.md#method-5-run-as-a-github-app), or a [GitHub Action](INSTALL.md#method-3-run-as-a-github-action).
 GitHub App and GitHub Action also enable to run PR-Agent specific tool automatically when a new PR is opened.
 
@@ -27,22 +27,10 @@ GitHub App and GitHub Action also enable to run PR-Agent specific tool automatic
 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.
+**git provider:**
-
-#### 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.
-
-To ignore files or directories, edit the **[ignore.toml](/pr_agent/settings/ignore.toml)** configuration file. This setting is also exposed the following environment variables:
-
- - `IGNORE.GLOB`
- - `IGNORE.REGEX`
-
-See [dynaconf envvars documentation](https://www.dynaconf.com/envvars/).
-
-#### git provider
 The [git_provider](pr_agent/settings/configuration.toml#L4) field in the configuration file determines the GIT provider that will be used by PR-Agent. Currently, the following providers are supported:
 `
-"github", "gitlab", "azure", "codecommit", "local", "gerrit"
+"github", "gitlab", "azure", "codecommit", "local"
 `
 
 [//]: # (** online usage:**)
@@ -59,14 +47,15 @@ The [git_provider](pr_agent/settings/configuration.toml#L4) field in the configu
 
 ### Working from a local repo (CLI)
 When running from your local repo (CLI), your local configuration file will be used.
+
 Examples for invoking the different tools via the CLI:
 
-- **Review**:       `python -m pr_agent.cli --pr_url=<pr_url>  review`
+- **Review**:       `python cli.py --pr_url=<pr_url>  review`
-- **Describe**:     `python -m pr_agent.cli --pr_url=<pr_url>  describe`
+- **Describe**:     `python cli.py --pr_url=<pr_url>  describe`
-- **Improve**:      `python -m pr_agent.cli --pr_url=<pr_url>  improve`
+- **Improve**:      `python cli.py --pr_url=<pr_url>  improve`
-- **Ask**:          `python -m pr_agent.cli --pr_url=<pr_url>  ask "Write me a poem about this PR"`
+- **Ask**:          `python cli.py --pr_url=<pr_url>  ask "Write me a poem about this PR"`
-- **Reflect**:      `python -m pr_agent.cli --pr_url=<pr_url>  reflect`
+- **Reflect**:      `python cli.py --pr_url=<pr_url>  reflect`
-- **Update Changelog**:      `python -m pr_agent.cli --pr_url=<pr_url>  update_changelog`
+- **Update Changelog**:      `python cli.py --pr_url=<pr_url>  update_changelog`
 
 `<pr_url>` is the url of the relevant PR (for example: https://github.com/Codium-ai/pr-agent/pull/50).
 
@@ -74,7 +63,7 @@ Examples for invoking the different tools via the CLI:
 
 (1) in addition to editing your local configuration file, you can also change any configuration value by adding it to the command line:
 ```
-python -m pr_agent.cli --pr_url=<pr_url>  /review --pr_reviewer.extra_instructions="focus on the file: ..."
+python cli.py --pr_url=<pr_url>  /review --pr_reviewer.extra_instructions="focus on the file: ..."
 ```
 
 (2) You can print results locally, without publishing them, by setting in `configuration.toml`:
@@ -104,15 +93,15 @@ For example if you want to edit the `review` tool configurations, you can run:
 ```
 /review --pr_reviewer.extra_instructions="..." --pr_reviewer.require_score_review=false
 ```
-Any configuration value in [configuration file](pr_agent/settings/configuration.toml) file can be similarly edited. comment `/config` to see the list of available configurations.
+Any configuration value in [configuration file](pr_agent/settings/configuration.toml) file can be similarly edited.
 
 
 ### Working with GitHub App
-When running PR-Agent from [GitHub App](INSTALL.md#method-5-run-as-a-github-app), the default configurations from a pre-built docker will be initially loaded.
+When running PR-Agent from [GitHub App](INSTALL.md#method-5-run-as-a-github-app), the default configurations from a pre-built repo will be initially loaded.
 
 #### GitHub app automatic tools
 The [github_app](pr_agent/settings/configuration.toml#L56) section defines GitHub app specific configurations. 
-An important parameter is `pr_commands`, which is a list of tools that will be **run automatically** when a new PR is opened:
+An important parameter is `pr_commands`, which is a list of tools that will be **run automatically when a new PR is opened**:
 ```
 [github_app]
 pr_commands = [
@@ -123,7 +112,7 @@ pr_commands = [
 This means that when a new PR is opened, 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.
 
-You can override the default tool parameters by uploading a local configuration file called `.pr_agent.toml` to the root of your repo.
+However, 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:
 ```
 [pr_description]
@@ -132,17 +121,11 @@ keep_original_user_title = false
 ```
 When a new PR is opened, PR-Agent will run the `describe` tool with the above parameters.
 
-To cancel the automatic run of all the tools, set:
-```
-[github_app]
-pr_commands = ""
-```
-
-
 Note that a local `.pr_agent.toml` file enables you to edit and customize the default parameters of any tool, not just the ones that are run automatically.
 
 #### Editing the prompts
 The prompts for the various PR-Agent tools are defined in the `pr_agent/settings` folder.
+
 In practice, the prompts are loaded and stored as a standard setting object. 
 Hence, editing them is similar to editing any other configuration value - just place the relevant key in `.pr_agent.toml`file, and override the default value.
 
@@ -172,23 +155,24 @@ You can configure settings in GitHub action by adding environment variables unde
 ```
 specifically, `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.
+if not set, the default option is that only the `review` tool will run automatically when a new PR is opened.
 
-### Changing a model
 
+### Appendix - additional configurations walkthrough
+
+#### 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
-To use Azure, set in your .secrets.toml:
+To use Azure, set: 
 ```
 api_key = "" # your azure api key
 api_type = "azure"
 api_version = '2023-05-15'  # Check Azure documentation for the current API version
 api_base = ""  # The base URL for your Azure OpenAI resource. e.g. "https://<your resource name>.openai.azure.com"
-openai.deployment_id = ""  # The deployment name you chose when you deployed the engine
+deployment_id = ""  # The deployment name you chose when you deployed the engine
 ```
+in your .secrets.toml
 
 and 
 ```
@@ -258,50 +242,12 @@ key = ...
 
 Also review the [AiHandler](pr_agent/algo/ai_handler.py) file for instruction how to set keys for other models.
 
-### 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.
-```
-@@ -12,5 +12,5 @@ def func1():
- code line that already existed in the file...
- code line that already existed in the file...
- code line that already existed in the file....
--code line that was removed in the PR
-+new code line added in the PR
- code line that already existed in the file...
- code line that already existed in the file...
- code line that already existed in the file...
-```
-
-For the `review`, `describe`, `ask` and `add_docs` tools, if the token budget allows, PR-Agent tries to increase the number of lines of context, via the parameter:
-```
-[config]
-patch_extra_lines=3
-```
-
-Increasing this number provides more context to the model, but will also increase the token budget.
-If the PR is too large (see [PR Compression strategy](./PR_COMPRESSION.md)), PR-Agent automatically sets this number to 0, using the original git patch.
-
-
 #### Azure DevOps provider
 To use Azure DevOps provider use the following settings in configuration.toml:
 ```
@@ -316,3 +262,25 @@ And use the following settings (you have to replace the values) in .secrets.toml
 org = "https://dev.azure.com/YOUR_ORGANIZATION/"
 pat = "YOUR_PAT_TOKEN"
 ```
+
+#### Similar issue tool
+
+[Example usage](https://github.com/Alibaba-MIIL/ASL/issues/107)
+
+<img src=./pics/similar_issue_tool.png width="768">
+
+To enable usage of the '**similar issue**' tool, you need to set the following keys in `.secrets.toml` (or in the relevant environment variables):
+```
+[pinecone]
+api_key = "..."
+environment = "..."
+```
+These parameters can be obtained by registering to [Pinecone](https://app.pinecone.io/?sessionType=signup/).
+
+- To invoke the 'similar issue' tool from **CLI**, run:
+`python3 cli.py --issue_url=... similar_issue`
+
+- To invoke the 'similar' issue tool via online usage, [comment](https://github.com/Codium-ai/pr-agent/issues/178#issuecomment-1716934893) on a PR:
+`/similar_issue`
+
+- You can also enable the 'similar issue' tool to run automatically when a new issue is opened, by adding it to the [pr_commands list in the github_app section](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L66)

docs/ADD_DOCUMENTATION.md

@@ -1,15 +0,0 @@
-# Add Documentation Tool
-The `add_docs` tool scans the PR code changes, and automatically suggests documentation for the undocumented code components (functions, classes, etc.).
-
-It can be invoked manually by commenting on any PR:
-```
-/add_docs
-```
-For example:
-
-<kbd><img src=./../pics/add_docs_comment.png width="768"></kbd>
-<kbd><img src=./../pics/add_docs.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 ...".

docs/ASK.md

@@ -1,11 +0,0 @@
-# ASK Tool
-
-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 "..."
-```
-For example:
-
-<kbd><img src=./../pics/ask_comment.png width="768"></kbd>
-<kbd><img src=./../pics/ask.png width="768"></kbd>

docs/DESCRIBE.md

@@ -1,51 +0,0 @@
-# Describe Tool
-
-The `describe` tool scans the PR code changes, and automatically generates PR description - title, type, summary, code walkthrough and labels.
-It can be invoked manually by commenting on any PR:
-```
-/describe
-```
-For example:
-
-<kbd><img src=./../pics/describe_comment.png width="768"></kbd>
-
-<kbd><img src=./../pics/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)
-
-### Configuration options
-
-Under the section 'pr_description', the [configuration file](./../pr_agent/settings/configuration.toml#L28) contains options to customize the 'describe' tool:
-
-- `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.
-
-- `add_original_user_description`: if set to true, the tool will add the original user description to the generated description. Default is false.
-
-- `keep_original_user_title`: if set to true, the tool will keep the original PR title, and won't change it. Default is false.
-
-- `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".
-
-#### Markers template
-
-markers enable to easily integrate user's content and auto-generated content, with a template-like mechanism.
-
-- `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.
-
-For example, if the PR original description was:
-```
-User content...
-
-## PR Type:
-pr_agent:pr_type
-
-## PR Description:
-pr_agent:summary
-
-## PR Walkthrough:
-pr_agent:walkthrough
-```
-The marker `pr_agent:pr_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.
-
-- `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.

docs/IMPROVE.md

@@ -1,34 +0,0 @@
-# Improve Tool
-
-The `improve` tool scans the PR code changes, and automatically generate committable suggestions for improving the PR code.
-It can be invoked manually by commenting on any PR:
-```
-/improve
-```
-For example:
-
-<kbd><img src=./../pics/improve_comment.png width="768"></kbd>
-<kbd><img src=./../pics/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)
-
-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).
-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:
-
-- `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.
-
-#### params for '/improve --extended' mode
-- `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.

docs/REVIEW.md

@@ -1,46 +0,0 @@
-# Review Tool
-
-The `review` tool scans the PR code changes, and automatically generates a PR review.
-It can be invoked manually by commenting on any PR:
-```
-/review
-```
-For example:
-
-<kbd><img src=./../pics/review_comment.png width="768"></kbd>
-<kbd><img src=./../pics/describe.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:
-
-- `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.
-- `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.
-- `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".
-####  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:
-```
-/improve -i
-```
-Note that the incremental mode is only available for GitHub.
-
-<kbd><img src=./../pics/incremental_review.png width="768"></kbd>
-
-#### 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.
-
-<kbd><img src=./../pics/reflection_questions.png width="768"></kbd>
-<kbd><img src=./../pics/reflection_answers.png width="768"></kbd>
-<kbd><img src=./../pics/reflection_insights.png width="768"></kbd>

docs/SIMILAR_ISSUE.md

@@ -1,31 +0,0 @@
-# Similar Issue Tool
-The similar issue tool retrieves the most similar issues to the current issue.
-It can be invoked manually by commenting on any PR:
-```
-/similar_issue
-```
-For example:
-
-<kbd><img src=./../pics/similar_issue_original_issue.png width="768"></kbd>
-<kbd><img src=./../pics/similar_issue_comment.png width="768"></kbd>
-<kbd><img src=./../pics/similar_issue.png width="768"></kbd>
-
-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):
-```
-[pinecone]
-api_key = "..."
-environment = "..."
-```
-These parameters can be obtained by registering to [Pinecone](https://app.pinecone.io/?sessionType=signup/).
-
-
-### How to use:
-- To invoke the 'similar issue' tool from **CLI**, run:
-`python3 cli.py --issue_url=... similar_issue`
-
-- To invoke the 'similar' issue tool via online usage, [comment](https://github.com/Codium-ai/pr-agent/issues/178#issuecomment-1716934893) on a PR:
-`/similar_issue`
-
-- You can also enable the 'similar issue' tool to run automatically when a new issue is opened, by adding it to the [pr_commands list in the github_app section](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L66)

docs/TOOLS_GUIDE.md

@@ -1,10 +0,0 @@
-## Tools Guide
-- [DESCRIBE](./DESCRIBE.md)
-- [REVIEW](./REVIEW.md)
-- [IMPROVE](./IMPROVE.md)
-- [ASK](./ASK.md)
-- [SIMILAR_ISSUE](./SIMILAR_ISSUE.md)
-- [UPDATE CHANGELOG](./UPDATE_CHANGELOG.md)
-- [ADD DOCUMENTATION](./ADD_DOCUMENTATION.md)
-
-See the **[installation guide](/INSTALL.md)** for instructions on how to setup PR-Agent.

docs/UPDATE_CHANGELOG.md

@@ -1,19 +0,0 @@
-# Update Changelog Tool
-
-The `update_changelog` tool automatically updates the CHANGELOG.md file with the PR changes.
-It can be invoked manually by commenting on any PR:
-```
-/update_changelog
-```
-For example:
-
-<kbd><img src=./../pics/update_changelog_comment.png width="768"></kbd>
-<kbd><img src=./../pics/update_changelog.png width="768"></kbd>
-
-
-### Configuration options
-
-Under the section 'pr_update_changelog', the [configuration file](./../pr_agent/settings/configuration.toml#L50) contains options to customize the 'update changelog' tool:
-
-- `push_changelog_changes`: whether to push the changes to CHANGELOG.md, or just print them. Default is false (print only).
-- `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...

pr_agent/agent/pr_agent.py

@@ -6,7 +6,6 @@ import tempfile
 from pr_agent.algo.utils import update_settings_from_args
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
-from pr_agent.tools.pr_add_docs import PRAddDocs
 from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
 from pr_agent.tools.pr_description import PRDescription
 from pr_agent.tools.pr_information_from_user import PRInformationFromUser
@@ -33,7 +32,6 @@ command2class = {
     "config": PRConfig,
     "settings": PRConfig,
     "similar_issue": PRSimilarIssue,
-    "add_docs": PRAddDocs,
 }
 
 commands = list(command2class.keys())
@@ -69,8 +67,8 @@ class PRAgent:
         args = update_settings_from_args(args)
 
         action = action.lstrip("/").lower()
-        if action == "reflect_and_review":
+        if action == "reflect_and_review" and not get_settings().pr_reviewer.ask_and_reflect:
-            get_settings().pr_reviewer.ask_and_reflect = True
+            action = "review"
         if action == "answer":
             if notify:
                 notify()

pr_agent/algo/ai_handler.py

@@ -92,8 +92,6 @@ class AiHandler:
                     f"Generating completion with {model}"
                     f"{(' from deployment ' + deployment_id) if deployment_id else ''}"
                 )
-            if self.azure:
-                model = 'azure/' + model
             response = await acompletion(
                 model=model,
                 deployment_id=deployment_id,
@@ -102,6 +100,7 @@ class AiHandler:
                     {"role": "user", "content": user}
                 ],
                 temperature=temperature,
+                azure=self.azure,
                 force_timeout=get_settings().config.ai_timeout
             )
         except (APIError, Timeout, TryAgain) as e:

pr_agent/algo/file_filter.py

@@ -1,31 +0,0 @@
-import fnmatch
-import re
-
-from pr_agent.config_loader import get_settings
-
-def filter_ignored(files):
-    """
-    Filter out files that match the ignore patterns.
-    """
-
-    try:
-        # load regex patterns, and translate glob patterns to regex
-        patterns = get_settings().ignore.regex
-        patterns += [fnmatch.translate(glob) for glob in get_settings().ignore.glob]
-
-        # compile all valid patterns
-        compiled_patterns = []
-        for r in patterns:
-            try:
-                compiled_patterns.append(re.compile(r))
-            except re.error:
-                pass
-
-        # keep filenames that _don't_ match the ignore regex
-        for r in compiled_patterns:
-            files = [f for f in files if not r.match(f.filename)]
-
-    except Exception as e:
-        print(f"Could not filter file list: {e}")
-
-    return files

pr_agent/algo/pr_processing.py

@@ -11,7 +11,6 @@ from github import RateLimitExceededException
 from pr_agent.algo import MAX_TOKENS
 from pr_agent.algo.git_patch_processing import convert_to_hunks_with_lines_numbers, extend_patch, handle_patch_deletions
 from pr_agent.algo.language_handler import sort_files_by_main_languages
-from pr_agent.algo.file_filter import filter_ignored
 from pr_agent.algo.token_handler import TokenHandler, get_token_encoder
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers.git_provider import FilePatchInfo, GitProvider
@@ -22,6 +21,7 @@ MORE_MODIFIED_FILES_ = "More modified files:\n"
 
 OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD = 1000
 OUTPUT_BUFFER_TOKENS_HARD_THRESHOLD = 600
+PATCH_EXTRA_LINES = 3
 
 def get_pr_diff(git_provider: GitProvider, token_handler: TokenHandler, model: str,
                 add_line_numbers_to_hunks: bool = False, disable_extra_lines: bool = False) -> str:
@@ -44,9 +44,8 @@ def get_pr_diff(git_provider: GitProvider, token_handler: TokenHandler, model: s
     """
 
     if disable_extra_lines:
+        global PATCH_EXTRA_LINES
         PATCH_EXTRA_LINES = 0
-    else:
-        PATCH_EXTRA_LINES = get_settings().config.patch_extra_lines
 
     try:
         diff_files = git_provider.get_diff_files()
@@ -54,14 +53,12 @@ def get_pr_diff(git_provider: GitProvider, token_handler: TokenHandler, model: s
         logging.error(f"Rate limit exceeded for git provider API. original message {e}")
         raise
 
-    diff_files = filter_ignored(diff_files)
-
     # get pr languages
     pr_languages = sort_files_by_main_languages(git_provider.get_languages(), diff_files)
 
     # generate a standard diff string, with patch extension
-    patches_extended, total_tokens, patches_extended_tokens = pr_generate_extended_diff(
+    patches_extended, total_tokens, patches_extended_tokens = pr_generate_extended_diff(pr_languages, token_handler,
-        pr_languages, token_handler, add_line_numbers_to_hunks, patch_extra_lines=PATCH_EXTRA_LINES)
+                                                               add_line_numbers_to_hunks)
 
     # if we are under the limit, return the full diff
     if total_tokens + OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD < MAX_TOKENS[model]:
@@ -83,8 +80,7 @@ def get_pr_diff(git_provider: GitProvider, token_handler: TokenHandler, model: s
 
 def pr_generate_extended_diff(pr_languages: list,
                               token_handler: TokenHandler,
-                              add_line_numbers_to_hunks: bool,
+                              add_line_numbers_to_hunks: bool) -> Tuple[list, int, list]:
-                              patch_extra_lines: int = 0) -> Tuple[list, int, list]:
     """
     Generate a standard diff string with patch extension, while counting the number of tokens used and applying diff
     minimization techniques if needed.
@@ -106,7 +102,7 @@ def pr_generate_extended_diff(pr_languages: list,
                 continue
 
             # extend each patch with extra lines of context
-            extended_patch = extend_patch(original_file_content_str, patch, num_lines=patch_extra_lines)
+            extended_patch = extend_patch(original_file_content_str, patch, num_lines=PATCH_EXTRA_LINES)
             full_extended_patch = f"\n\n## {file.filename}\n\n{extended_patch}\n"
 
             if add_line_numbers_to_hunks:
@@ -370,8 +366,6 @@ def get_pr_multi_diffs(git_provider: GitProvider,
         logging.error(f"Rate limit exceeded for git provider API. original message {e}")
         raise
 
-    diff_files = filter_ignored(diff_files)
-
     # Sort files by main language
     pr_languages = sort_files_by_main_languages(git_provider.get_languages(), diff_files)
 

pr_agent/algo/utils.py

@@ -62,7 +62,7 @@ def convert_to_markdown(output_data: dict, gfm_supported: bool=True) -> str:
                 markdown_text += f"- {emoji} **{key}:**\n\n"
             for item in value:
                 if isinstance(item, dict) and key.lower() == 'code feedback':
-                    markdown_text += parse_code_suggestion(item, gfm_supported)
+                    markdown_text += parse_code_suggestion(item)
                 elif item:
                     markdown_text += f"  - {item}\n"
             if key.lower() == 'code feedback':
@@ -76,7 +76,7 @@ def convert_to_markdown(output_data: dict, gfm_supported: bool=True) -> str:
     return markdown_text
 
 
-def parse_code_suggestion(code_suggestions: dict, gfm_supported: bool=True) -> str:
+def parse_code_suggestion(code_suggestions: dict) -> str:
     """
     Convert a dictionary of data into markdown format.
 
@@ -99,9 +99,6 @@ def parse_code_suggestion(code_suggestions: dict, gfm_supported: bool=True) -> s
                 markdown_text += f"\n  - **{sub_key}:** {sub_value}\n"
             else:
                 markdown_text += f"   **{sub_key}:** {sub_value}\n"
-            if not gfm_supported:
-                if "relevant line" not in sub_key.lower(): # nicer presentation
-                        markdown_text = markdown_text.rstrip('\n') + "\\\n"
 
     markdown_text += "\n"
     return markdown_text

pr_agent/config_loader.py

@@ -14,7 +14,6 @@ global_settings = Dynaconf(
     settings_files=[join(current_dir, f) for f in [
         "settings/.secrets.toml",
         "settings/configuration.toml",
-        "settings/ignore.toml",
         "settings/language_extensions.toml",
         "settings/pr_reviewer_prompts.toml",
         "settings/pr_questions_prompts.toml",
@@ -23,7 +22,6 @@ global_settings = Dynaconf(
         "settings/pr_sort_code_suggestions_prompts.toml",
         "settings/pr_information_from_user_prompts.toml",
         "settings/pr_update_changelog_prompts.toml",
-        "settings/pr_add_docs.toml",
         "settings_prod/.secrets.toml"
     ]]
 )

pr_agent/git_providers/azuredevops_provider.py

@@ -88,8 +88,6 @@ class AzureDevopsProvider:
                 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'):
-                        continue
                     diffs.append(i['item']['path'])
                     diff_types[i['item']['path']] = i['changeType']
 
@@ -100,7 +98,6 @@ class AzureDevopsProvider:
                     continue
 
                 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,
                                                                          path=file,
                                                                          project=self.workspace_slug,
@@ -109,9 +106,6 @@ class AzureDevopsProvider:
                                                                          include_content=True)
 
                 new_file_content_str = new_file_content_str.content
-                except Exception as error:
-                    logging.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':
@@ -122,7 +116,6 @@ class AzureDevopsProvider:
                     edit_type = EDIT_TYPE.RENAMED
 
                 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,
                                                                               path=file,
                                                                               project=self.workspace_slug,
@@ -130,9 +123,6 @@ class AzureDevopsProvider:
                                                                               download=False,
                                                                               include_content=True)
                 original_file_content_str = original_file_content_str.content
-                except Exception as error:
-                    logging.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)
 

pr_agent/git_providers/gitlab_provider.py

@@ -1,4 +1,3 @@
-import hashlib
 import logging
 import re
 from typing import Optional, Tuple
@@ -8,7 +7,7 @@ import gitlab
 from gitlab import GitlabGetError
 
 from ..algo.language_handler import is_valid_file
-from ..algo.pr_processing import clip_tokens, find_line_number_of_relevant_line_in_file
+from ..algo.pr_processing import clip_tokens
 from ..algo.utils import load_large_diff
 from ..config_loader import get_settings
 from .git_provider import EDIT_TYPE, FilePatchInfo, GitProvider
@@ -176,7 +175,8 @@ class GitLabProvider(GitProvider):
                 pos_obj['new_line'] = target_line_no - 1
                 pos_obj['old_line'] = source_line_no - 1
             logging.debug(f"Creating comment in {self.id_mr} with body {body} and position {pos_obj}")
-            self.mr.discussions.create({'body': body, 'position': pos_obj})
+            self.mr.discussions.create({'body': body,
+                                        'position': pos_obj})
 
     def get_relevant_diff(self, relevant_file: str, relevant_line_in_file: int) -> Optional[dict]:
         changes = self.mr.changes()  # Retrieve the changes for the merge request once
@@ -228,9 +228,6 @@ class GitLabProvider(GitProvider):
             except Exception as e:
                 logging.exception(f"Could not publish code suggestion:\nsuggestion: {suggestion}\nerror: {e}")
 
-        # note that we publish suggestions one-by-one. so, if one fails, the rest will still be published
-        return True
-
     def search_line(self, relevant_file, relevant_line_in_file):
         target_file = None
 
@@ -389,27 +386,3 @@ class GitLabProvider(GitProvider):
             return pr_id
         except:
             return ""
-
-    def generate_link_to_relevant_line_number(self, suggestion) -> str:
-        try:
-            relevant_file = suggestion['relevant file'].strip('`').strip("'")
-            relevant_line_str = suggestion['relevant line']
-            if not relevant_line_str:
-                return ""
-
-            position, absolute_position = find_line_number_of_relevant_line_in_file \
-                (self.diff_files, relevant_file, relevant_line_str)
-
-            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 to diff
-                # sha_file = hashlib.sha1(relevant_file.encode('utf-8')).hexdigest()
-                # link = f"{self.pr.web_url}/diffs#{sha_file}_{absolute_position}_{absolute_position}"
-                return link
-        except Exception as e:
-            if get_settings().config.verbosity_level >= 2:
-                logging.info(f"Failed adding line link, error: {e}")
-
-        return ""

pr_agent/settings/configuration.toml

@@ -10,7 +10,6 @@ use_repo_settings_file=true
 ai_timeout=180
 max_description_tokens = 500
 max_commits_tokens = 500
-patch_extra_lines = 3
 secret_provider="google_cloud_storage"
 cli_mode=false
 
@@ -48,10 +47,6 @@ rank_extended_suggestions = true
 max_number_of_calls = 5
 final_clip_factor = 0.9
 
-[pr_add_docs] # /add_docs #
-extra_instructions = ""
-docs_style = "Sphinx Style" # "Google Style with Args, Returns, Attributes...etc", "Numpy Style", "Sphinx Style", "PEP257", "reStructuredText"
-
 [pr_update_changelog] # /update_changelog #
 push_changelog_changes=false
 extra_instructions = ""

pr_agent/settings/ignore.toml

@@ -1,11 +0,0 @@
-[ignore]
-
-glob = [
-    # Ignore files and directories matching these glob patterns.
-    # See https://docs.python.org/3/library/glob.html
-    'vendor/**',
-]
-regex = [
-    # Ignore files and directories matching these regex patterns.
-    # See https://learnbyexample.github.io/python-regex-cheatsheet/
-]

pr_agent/settings/language_extensions.toml

@@ -53,8 +53,7 @@ default = [
     'xz',
     'zip',
     'zst',
-    'snap',
+    'snap'
-    'lockb'
 ]
 extra = [
     'md',

pr_agent/settings/pr_add_docs.toml

@@ -1,117 +0,0 @@
-[pr_add_docs_prompt]
-system="""You are a language model called PR-Code-Documentation Agent, that specializes in generating documentation for code.
-Your task is to generate meaningfull {{ docs_for_language }} to a PR (the '+' lines).
-
-Example for a PR Diff input:
-'
-## src/file1.py
-
-@@ -12,3 +12,5 @@ def func1():
-__new hunk__
-12  code line that already existed in the file...
-13  code line that already existed in the file....
-14 +new code line1 added in the PR
-15 +new code line2 added in the PR
-16  code line that already existed in the file...
-__old hunk__
- code line that already existed in the file...
--code line that was removed in the PR
- code line that already existed in the file...
-
-
-@@ ... @@ def func2():
-__new hunk__
-...
-__old hunk__
-...
-
-
-## src/file2.py
-...
-'
-
-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.
-- The {{ docs_for_language }} should be in standard format.
-- Provide the exact line number (inclusive) where the {{ docs_for_language }} should be added.
-
-
-{%- if extra_instructions %}
-
-Extra instructions from the user:
-'
-{{ extra_instructions }}
-'
-{%- endif %}
-
-You must use the following YAML schema to format your answer:
-```yaml
-Code Documentation:
-  type: array
-  uniqueItems: true
-  items:
-    relevant file:
-      type: string
-      description: the relevant file full path
-    relevant line:
-      type: integer
-      description: |-
-        The relevant line number from a '__new hunk__' section where the {{ docs_for_language }} should be added.
-    doc placement:
-      type: string
-      enum:
-        - before
-        - after
-      description: |-
-        The {{ docs_for_language }} placement relative to the relevant line (code component).
-    documentation:
-      type: string
-      description: |-
-        The {{ docs_for_language }} content. It should be complete, correctly formatted and indented, and without line numbers.
-```
-
-Example output:
-```yaml
-Code Documentation:
--   relevant file: |-
-        src/file1.py
-    relevant lines: 12
-    doc placement: after
-    documentation: |-
-        \"\"\"
-        This is a python docstring for func1.
-        \"\"\"
-- ...
-...
-```
-
-
-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 }}'
-
-Description: '{{description}}'
-
-{%- if language %}
-
-Main language: {{language}}
-{%- endif %}
-
-
-The PR Diff:
-```
-{{- diff|trim }}
-```
-
-Response (should be a valid YAML, and nothing else):
-```yaml
-"""

pr_agent/settings/pr_code_suggestions_prompts.toml

@@ -1,6 +1,6 @@
 [pr_code_suggestions_prompt]
 system="""You are a language model called PR-Code-Reviewer, that specializes in suggesting code improvements for Pull Request (PR).
-Your task is to provide meaningful and actionable code suggestions, to improve the new code presented in a PR (the '+' lines in the diff).
+Your task is to provide meaningful and actionable code suggestions, to improve the new code presented in a PR.
 
 Example for a PR Diff input:
 '
@@ -31,13 +31,14 @@ __old hunk__
 '
 
 Specific instructions:
-- Provide up to {{ num_code_suggestions }} code suggestions. Try to provide diverse and insightful suggestions.
+- Provide up to {{ num_code_suggestions }} code 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.
+  Don't suggest to add docstring, type hints, or comments.
+  Try to provide diverse and insightful suggestions.
 - Suggestions should refer only to code from the '__new hunk__' sections, and focus on new lines of code (lines starting with '+').
-- 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.
+  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.
+  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 issue.
 - Assume there is additional relevant code, that is not included in the diff.
 
@@ -45,9 +46,7 @@ Specific instructions:
 {%- if extra_instructions %}
 
 Extra instructions from the user:
-'
 {{ extra_instructions }}
-'
 {%- endif %}
 
 You must use the following YAML schema to format your answer:

pr_agent/settings/pr_description_prompts.toml

@@ -7,9 +7,7 @@ Your task is to provide full description of the PR content.
 {%- if extra_instructions %}
 
 Extra instructions from the user:
-'
 {{ extra_instructions }}
-'
 {% endif %}
 
 You must use the following YAML schema to format your answer:

pr_agent/settings/pr_reviewer_prompts.toml

@@ -35,9 +35,7 @@ The review should focus on new code added in the PR (lines starting with '+'), a
 {%- if extra_instructions %}
 
 Extra instructions from the user:
-'
 {{ extra_instructions }}
-'
 {% endif %}
 
 You must use the following YAML schema to format your answer:
@@ -131,7 +129,8 @@ PR Feedback:
   Security concerns:
     type: string
     description: >-
-      yes\\no question: does this PR code introduce possible vulnerabilities such as exposure of sensitive information (e.g., API keys, secrets, passwords), or security concerns like SQL injection, XSS, CSRF, and others ? If answered 'yes', explain your answer briefly.
+      yes\\no question: does this PR code introduce possible security concerns or
+      issues, like SQL injection, XSS, CSRF, and others ? If answered 'yes',explain your answer shortly
 {%- endif %}
 ```
 
@@ -152,9 +151,6 @@ PR Analysis:
 {%- if require_focused %}
   Focused PR: no, because ...
 {%- endif %}
-{%- if require_estimate_effort_to_review %}
-  Estimated effort to review [1-5]: 3, because ...
-{%- endif %}
 PR Feedback:
   General PR suggestions: |-
     ...
@@ -197,9 +193,7 @@ Here are questions to better understand the PR. Use the answers to provide bette
 {{question_str|trim}}
 
 User answers:
-'
 {{answer_str|trim}}
-'
 ######
 {%- endif %}
 

pr_agent/settings/pr_update_changelog_prompts.toml

@@ -8,9 +8,7 @@ Your task is to update the CHANGELOG.md file of the project, to shortly summariz
 {%- if extra_instructions %}
 
 Extra instructions from the user:
-'
 {{ extra_instructions }}
-'
 {%- endif %}
 """
 

pr_agent/tools/pr_add_docs.py

@@ -1,173 +0,0 @@
-import copy
-import logging
-import textwrap
-from typing import List, Dict
-from jinja2 import Environment, StrictUndefined
-
-from pr_agent.algo.ai_handler import AiHandler
-from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models, get_pr_multi_diffs
-from pr_agent.algo.token_handler import TokenHandler
-from pr_agent.algo.utils import load_yaml
-from pr_agent.config_loader import get_settings
-from pr_agent.git_providers import BitbucketProvider, get_git_provider
-from pr_agent.git_providers.git_provider import get_main_pr_language
-
-
-class PRAddDocs:
-    def __init__(self, pr_url: str, cli_mode=False, args: list = None):
-
-        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.patches_diff = None
-        self.prediction = None
-        self.cli_mode = cli_mode
-        self.vars = {
-            "title": self.git_provider.pr.title,
-            "branch": self.git_provider.get_pr_branch(),
-            "description": self.git_provider.get_pr_description(),
-            "language": self.main_language,
-            "diff": "",  # empty diff for initial calculation
-            "extra_instructions": get_settings().pr_add_docs.extra_instructions,
-            "commit_messages_str": self.git_provider.get_commit_messages(),
-            'docs_for_language': get_docs_for_language(self.main_language,
-                                                       get_settings().pr_add_docs.docs_style),
-        }
-        self.token_handler = TokenHandler(self.git_provider.pr,
-                                          self.vars,
-                                          get_settings().pr_add_docs_prompt.system,
-                                          get_settings().pr_add_docs_prompt.user)
-
-    async def run(self):
-        try:
-            logging.info('Generating code Docs for PR...')
-            if get_settings().config.publish_output:
-                self.git_provider.publish_comment("Generating Documentation...", is_temporary=True)
-
-            logging.info('Preparing PR documentation...')
-            await retry_with_fallback_models(self._prepare_prediction)
-            data = self._prepare_pr_code_docs()
-            if (not data) or (not 'Code Documentation' in data):
-                logging.info('No code documentation found for PR.')
-                return
-
-            if get_settings().config.publish_output:
-                logging.info('Pushing PR documentation...')
-                self.git_provider.remove_initial_comment()
-                logging.info('Pushing inline code documentation...')
-                self.push_inline_docs(data)
-        except Exception as e:
-            logging.error(f"Failed to generate code documentation for PR, error: {e}")
-
-    async def _prepare_prediction(self, model: str):
-        logging.info('Getting PR diff...')
-        self.patches_diff = get_pr_diff(self.git_provider,
-                                        self.token_handler,
-                                        model,
-                                        add_line_numbers_to_hunks=True,
-                                        disable_extra_lines=False)
-
-        logging.info('Getting AI prediction...')
-        self.prediction = await self._get_prediction(model)
-
-    async def _get_prediction(self, model: str):
-        variables = copy.deepcopy(self.vars)
-        variables["diff"] = self.patches_diff  # update diff
-        environment = Environment(undefined=StrictUndefined)
-        system_prompt = environment.from_string(get_settings().pr_add_docs_prompt.system).render(variables)
-        user_prompt = environment.from_string(get_settings().pr_add_docs_prompt.user).render(variables)
-        if get_settings().config.verbosity_level >= 2:
-            logging.info(f"\nSystem prompt:\n{system_prompt}")
-            logging.info(f"\nUser prompt:\n{user_prompt}")
-        response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
-                                                                        system=system_prompt, user=user_prompt)
-
-        return response
-
-    def _prepare_pr_code_docs(self) -> Dict:
-        docs = self.prediction.strip()
-        data = load_yaml(docs)
-        if isinstance(data, list):
-            data = {'Code Documentation': data}
-        return data
-
-    def push_inline_docs(self, data):
-        docs = []
-
-        if not data['Code Documentation']:
-            return self.git_provider.publish_comment('No code documentation found to improve this PR.')
-
-        for d in data['Code Documentation']:
-            try:
-                if get_settings().config.verbosity_level >= 2:
-                    logging.info(f"add_docs: {d}")
-                relevant_file = d['relevant file'].strip()
-                relevant_line = int(d['relevant line'])  # absolute position
-                documentation = d['documentation']
-                doc_placement = d['doc placement'].strip()
-                if documentation:
-                    new_code_snippet = self.dedent_code(relevant_file, relevant_line, documentation, doc_placement,
-                                                        add_original_line=True)
-
-                    body = f"**Suggestion:** Proposed documentation\n```suggestion\n" + new_code_snippet + "\n```"
-                    docs.append({'body': body, 'relevant_file': relevant_file,
-                                             'relevant_lines_start': relevant_line,
-                                             'relevant_lines_end': relevant_line})
-            except Exception:
-                if get_settings().config.verbosity_level >= 2:
-                    logging.info(f"Could not parse code docs: {d}")
-
-        is_successful = self.git_provider.publish_code_suggestions(docs)
-        if not is_successful:
-            logging.info("Failed to publish code docs, trying to publish each docs separately")
-            for doc_suggestion in docs:
-                self.git_provider.publish_code_suggestions([doc_suggestion])
-
-    def dedent_code(self, relevant_file, relevant_lines_start, new_code_snippet, doc_placement='after',
-                    add_original_line=False):
-        try:  # dedent code snippet
-            self.diff_files = self.git_provider.diff_files if self.git_provider.diff_files \
-                else self.git_provider.get_diff_files()
-            original_initial_line = None
-            for file in self.diff_files:
-                if file.filename.strip() == relevant_file:
-                    original_initial_line = file.head_file.splitlines()[relevant_lines_start - 1]
-                    break
-            if original_initial_line:
-                if doc_placement == 'after':
-                    line = file.head_file.splitlines()[relevant_lines_start]
-                else:
-                    line = original_initial_line
-                suggested_initial_line = new_code_snippet.splitlines()[0]
-                original_initial_spaces = len(line) - len(line.lstrip())
-                suggested_initial_spaces = len(suggested_initial_line) - len(suggested_initial_line.lstrip())
-                delta_spaces = original_initial_spaces - suggested_initial_spaces
-                if delta_spaces > 0:
-                    new_code_snippet = textwrap.indent(new_code_snippet, delta_spaces * " ").rstrip('\n')
-                if add_original_line:
-                    if doc_placement == 'after':
-                        new_code_snippet = original_initial_line + "\n" + new_code_snippet
-                    else:
-                        new_code_snippet = new_code_snippet.rstrip() + "\n" + original_initial_line
-        except Exception as e:
-            if get_settings().config.verbosity_level >= 2:
-                logging.info(f"Could not dedent code snippet for file {relevant_file}, error: {e}")
-
-        return new_code_snippet
-
-
-def get_docs_for_language(language, style):
-    language = language.lower()
-    if language == 'java':
-        return "Javadocs"
-    elif language in ['python', 'lisp', 'clojure']:
-        return f"Docstring ({style})"
-    elif language in ['javascript', 'typescript']:
-        return "JSdocs"
-    elif language == 'c++':
-        return "Doxygen"
-    else:
-        return "Docs"

pr_agent/tools/pr_reviewer.py

@@ -209,22 +209,6 @@ class PRReviewer:
                         link = self.git_provider.generate_link_to_relevant_line_number(suggestion)
                         if link:
                             suggestion['relevant line'] = f"[{suggestion['relevant line']}]({link})"
-                    else:
-                        pass
-                        # try:
-                        #     relevant_file = suggestion['relevant file'].strip('`').strip("'")
-                        #     relevant_line_str = suggestion['relevant line']
-                        #     if not relevant_line_str:
-                        #         return ""
-                        #
-                        #     position, absolute_position = find_line_number_of_relevant_line_in_file(
-                        #         self.git_provider.diff_files, relevant_file, relevant_line_str)
-                        #     if absolute_position != -1:
-                        #         suggestion[
-                        #             'relevant line'] = f"{suggestion['relevant line']} (line {absolute_position})"
-                        # except:
-                        #     pass
-
 
         # Add incremental review section
         if self.incremental.is_incremental:
@@ -241,8 +225,7 @@ class PRReviewer:
         # Add help text if not in CLI mode
         if not get_settings().get("CONFIG.CLI_MODE", False):
             markdown_text += "\n### How to use\n"
-            bot_user = "[bot]" if get_settings().github_app.override_deployment_type else get_settings().github_app.bot_user
+            if user and '[bot]' not in user:
-            if user and bot_user not in user:
                 markdown_text += bot_help_text(user)
             else:
                 markdown_text += actions_help_text

tests/unittest/test_file_filter.py

@@ -1,80 +0,0 @@
-import pytest
-from pr_agent.algo.file_filter import filter_ignored
-from pr_agent.config_loader import global_settings
-
-class TestIgnoreFilter:
-    def test_no_ignores(self):
-        """
-        Test no files are ignored when no patterns are specified.
-        """
-        files = [
-            type('', (object,), {'filename': 'file1.py'})(),
-            type('', (object,), {'filename': 'file2.java'})(),
-            type('', (object,), {'filename': 'file3.cpp'})(),
-            type('', (object,), {'filename': 'file4.py'})(),
-            type('', (object,), {'filename': 'file5.py'})()
-        ]
-        assert filter_ignored(files) == files, "Expected all files to be returned when no ignore patterns are given."
-
-    def test_glob_ignores(self, monkeypatch):
-        """
-        Test files are ignored when glob patterns are specified.
-        """
-        monkeypatch.setattr(global_settings.ignore, 'glob', ['*.py'])
-
-        files = [
-            type('', (object,), {'filename': 'file1.py'})(),
-            type('', (object,), {'filename': 'file2.java'})(),
-            type('', (object,), {'filename': 'file3.cpp'})(),
-            type('', (object,), {'filename': 'file4.py'})(),
-            type('', (object,), {'filename': 'file5.py'})()
-        ]
-        expected = [
-            files[1],
-            files[2]
-        ]
-
-        filtered_files = filter_ignored(files)
-        assert filtered_files == expected, f"Expected {[file.filename for file in expected]}, but got {[file.filename for file in filtered_files]}."
-
-    def test_regex_ignores(self, monkeypatch):
-        """
-        Test files are ignored when regex patterns are specified.
-        """
-        monkeypatch.setattr(global_settings.ignore, 'regex', ['^file[2-4]\..*$'])
-
-        files = [
-            type('', (object,), {'filename': 'file1.py'})(),
-            type('', (object,), {'filename': 'file2.java'})(),
-            type('', (object,), {'filename': 'file3.cpp'})(),
-            type('', (object,), {'filename': 'file4.py'})(),
-            type('', (object,), {'filename': 'file5.py'})()
-        ]
-        expected = [
-            files[0],
-            files[4]
-        ]
-
-        filtered_files = filter_ignored(files)
-        assert filtered_files == expected, f"Expected {[file.filename for file in expected]}, but got {[file.filename for file in filtered_files]}."
-
-    def test_invalid_regex(self, monkeypatch):
-        """
-        Test invalid patterns are quietly ignored.
-        """
-        monkeypatch.setattr(global_settings.ignore, 'regex', ['(((||', '^file[2-4]\..*$'])
-
-        files = [
-            type('', (object,), {'filename': 'file1.py'})(),
-            type('', (object,), {'filename': 'file2.java'})(),
-            type('', (object,), {'filename': 'file3.cpp'})(),
-            type('', (object,), {'filename': 'file4.py'})(),
-            type('', (object,), {'filename': 'file5.py'})()
-        ]
-        expected = [
-            files[0],
-            files[4]
-        ]
-
-        filtered_files = filter_ignored(files)
-        assert filtered_files == expected, f"Expected {[file.filename for file in expected]}, but got {[file.filename for file in filtered_files]}."