Merge branch 'main' into update/README.md

.github/workflows/pr-agent-review.yaml

@@ -21,8 +21,8 @@ jobs:
         id: pragent
         uses: Codium-ai/pr-agent@main
         env:
-          OPENAI.KEY: ${{ secrets.OPENAI_KEY }}
+          OPENAI_KEY: ${{ secrets.OPENAI_KEY }}
-          OPENAI.ORG: ${{ secrets.OPENAI_ORG }} # optional
+          OPENAI_ORG: ${{ secrets.OPENAI_ORG }} # optional
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           PINECONE.API_KEY: ${{ secrets.PINECONE_API_KEY }}
           PINECONE.ENVIRONMENT: ${{ secrets.PINECONE_ENVIRONMENT }}

README.md

@@ -26,6 +26,8 @@ CodiumAI `PR-Agent` is an open-source tool aiming to help developers review pull
 ‣ **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`)**: 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`)**: Automatically retrieves and presents [similar issues](https://github.com/Alibaba-MIIL/ASL/issues/107).
 
 
 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.
@@ -106,6 +108,7 @@ See the [usage guide](./Usage.md) for instructions how to run the different tool
 |       | ⮑ 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:        |          |          |       |
+|       | Find similar issue                          |   :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:    |           |          |          |
@@ -183,7 +186,7 @@ Here are some advantages of PR-Agent:
 - [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)
-- [ ] PR-Agent for issues, and just for pull requests
+- [x] PR-Agent for issues
 - [ ] Adding more tools. Possible directions:
   - [x] PR description
   - [x] Inline code suggestions
@@ -201,3 +204,13 @@ Here are some advantages of PR-Agent:
 - [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)
+  
+## Links
+
+[![Join our Discord community](https://raw.githubusercontent.com/Codium-ai/codiumai-vscode-release/main/media/docs/Joincommunity.png)](https://discord.gg/kG35uSHDBc)
+
+- Discord community: https://discord.gg/kG35uSHDBc
+- CodiumAI site: https://codium.ai
+- Blog: https://www.codium.ai/blog/
+- Troubleshooting: https://www.codium.ai/blog/technical-faq-and-troubleshooting/
+- Support: support@codium.ai

Usage.md

@@ -248,3 +248,25 @@ 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)

pr_agent/algo/language_handler.py

@@ -42,6 +42,11 @@ def sort_files_by_main_languages(languages: Dict, files: list):
     files_sorted = []
     rest_files = {}
 
+    # if no languages detected, put all files in the "Other" category
+    if not languages:
+        files_sorted = [({"language": "Other", "files": list(files_filtered)})]
+        return files_sorted
+
     main_extensions_flat = []
     for ext in main_extensions:
         main_extensions_flat.extend(ext)

pr_agent/algo/utils.py

@@ -20,7 +20,7 @@ def get_setting(key: str) -> Any:
     except Exception:
         return global_settings.get(key, None)
 
-def convert_to_markdown(output_data: dict, gfm_supported: bool) -> str:
+def convert_to_markdown(output_data: dict, gfm_supported: bool=True) -> str:
     """
     Convert a dictionary of data into markdown format.
     Args:
@@ -42,6 +42,7 @@ def convert_to_markdown(output_data: dict, gfm_supported: bool) -> str:
         "General suggestions": "💡",
         "Insights from user's answers": "📝",
         "Code feedback": "🤖",
+        "Estimated effort to review [1-5]": "⏱️",
     }
 
     for key, value in output_data.items():

pr_agent/git_providers/git_provider.py

@@ -132,6 +132,10 @@ def get_main_pr_language(languages, files) -> str:
     Get the main language of the commit. Return an empty string if cannot determine.
     """
     main_language_str = ""
+    if not languages:
+        logging.info("No languages detected")
+        return main_language_str
+
     try:
         top_language = max(languages, key=languages.get).lower()
 

pr_agent/servers/github_action_runner.py

@@ -12,8 +12,8 @@ async def run_action():
     # Get environment variables
     GITHUB_EVENT_NAME = os.environ.get('GITHUB_EVENT_NAME')
     GITHUB_EVENT_PATH = os.environ.get('GITHUB_EVENT_PATH')
-    OPENAI_KEY = os.environ.get('OPENAI_KEY')
+    OPENAI_KEY = os.environ.get('OPENAI_KEY') or os.environ.get('OPENAI.KEY')
-    OPENAI_ORG = os.environ.get('OPENAI_ORG')
+    OPENAI_ORG = os.environ.get('OPENAI_ORG') or os.environ.get('OPENAI.ORG')
     GITHUB_TOKEN = os.environ.get('GITHUB_TOKEN')
     get_settings().set("CONFIG.PUBLISH_OUTPUT_PROGRESS", False)
 
@@ -61,12 +61,21 @@ async def run_action():
         if action in ["created", "edited"]:
             comment_body = event_payload.get("comment", {}).get("body")
             if comment_body:
-                pr_url = event_payload.get("issue", {}).get("pull_request", {}).get("url")
+                is_pr = False
-                if pr_url:
+                # check if issue is pull request
+                if event_payload.get("issue", {}).get("pull_request"):
+                    url = event_payload.get("issue", {}).get("pull_request", {}).get("url")
+                    is_pr = True
+                else:
+                    url = event_payload.get("issue", {}).get("url")
+                if url:
                     body = comment_body.strip().lower()
                     comment_id = event_payload.get("comment", {}).get("id")
-                    provider = get_git_provider()(pr_url=pr_url)
+                    provider = get_git_provider()(pr_url=url)
-                    await PRAgent().handle_request(pr_url, body, notify=lambda: provider.add_eyes_reaction(comment_id))
+                    if is_pr:
+                        await PRAgent().handle_request(url, body, notify=lambda: provider.add_eyes_reaction(comment_id))
+                    else:
+                        await PRAgent().handle_request(url, body)
 
 
 if __name__ == '__main__':

pr_agent/settings/configuration.toml

@@ -11,12 +11,14 @@ ai_timeout=180
 max_description_tokens = 500
 max_commits_tokens = 500
 secret_provider="google_cloud_storage"
+cli_mode=false
 
 [pr_reviewer] # /review #
 require_focused_review=false
 require_score_review=false
 require_tests_review=true
 require_security_review=true
+require_estimate_effort_to_review=true
 num_code_suggestions=4
 inline_code_comments = false
 ask_and_reflect=false
@@ -24,10 +26,14 @@ automatic_review=true
 extra_instructions = ""
 
 [pr_description] # /describe #
+publish_labels=true
 publish_description_as_comment=false
 add_original_user_description=false
 keep_original_user_title=false
 extra_instructions = ""
+# markers
+use_description_markers=false
+include_generated_by_header=true
 
 [pr_questions] # /ask #
 

pr_agent/settings/pr_reviewer_prompts.toml

@@ -85,6 +85,14 @@ PR Analysis:
       code diff changes are too scattered, then the PR is not focused. Explain
       your answer shortly.
 {%- endif %}
+{%- if require_estimate_effort_to_review %}
+  Estimated effort to review [1-5]:
+    type: string
+    description: >-
+      Estimate, on a scale of 1-5 (inclusive), the time and effort required to review this PR by an experienced and knowledgeable developer. 1 means short and easy review , 5 means long and hard review.
+      Take into account the size, complexity, quality, and the needed changes of the PR code diff.
+      Explain your answer shortly (1-2 sentences).
+{%- endif %}
 PR Feedback:
   General suggestions:
     type: string

pr_agent/tools/pr_description.py

@@ -1,5 +1,6 @@
 import copy
 import json
+import re
 import logging
 from typing import List, Tuple
 
@@ -28,6 +29,7 @@ class PRDescription:
         self.main_pr_language = get_main_pr_language(
             self.git_provider.get_languages(), self.git_provider.get_files()
         )
+        self.pr_id = f"{self.git_provider.repo}/{self.git_provider.pr_num}"
 
         # Initialize the AI handler
         self.ai_handler = AiHandler()
@@ -61,26 +63,39 @@ class PRDescription:
         """
         Generates a PR description using an AI model and publishes it to the PR.
         """
-        logging.info('Generating a PR description...')
+        logging.info(f"Generating a PR description {self.pr_id}")
         if get_settings().config.publish_output:
             self.git_provider.publish_comment("Preparing pr description...", is_temporary=True)
 
         await retry_with_fallback_models(self._prepare_prediction)
 
-        logging.info('Preparing answer...')
+        logging.info(f"Preparing answer {self.pr_id}")
-        pr_title, pr_body, pr_types, markdown_text, description = self._prepare_pr_answer()
+        if self.prediction:
+            self._prepare_data()
+        else:
+            return None
+
+        pr_labels = []
+        if get_settings().pr_description.publish_labels:
+            pr_labels = self._prepare_labels()
+
+        if get_settings().pr_description.use_description_markers:
+            pr_title, pr_body = self._prepare_pr_answer_with_markers()
+        else:
+            pr_title, pr_body,  = self._prepare_pr_answer()
+        full_markdown_description = f"## Title\n\n{pr_title}\n\n___\n{pr_body}"
 
         if get_settings().config.publish_output:
-            logging.info('Pushing answer...')
+            logging.info(f"Pushing answer {self.pr_id}")
             if get_settings().pr_description.publish_description_as_comment:
-                self.git_provider.publish_comment(pr_body)
+                self.git_provider.publish_comment(full_markdown_description)
             else:
                 self.git_provider.publish_description(pr_title, pr_body)
-                if self.git_provider.is_supported("get_labels"):
+                if get_settings().pr_description.publish_labels and self.git_provider.is_supported("get_labels"):
                     current_labels = self.git_provider.get_labels()
                     if current_labels is None:
                         current_labels = []
-                    self.git_provider.publish_labels(pr_types + current_labels)
+                    self.git_provider.publish_labels(pr_labels + current_labels)
             self.git_provider.remove_initial_comment()
         
         return ""
@@ -99,9 +114,12 @@ class PRDescription:
             Any exceptions raised by the 'get_pr_diff' and '_get_prediction' functions.
 
         """
-        logging.info('Getting PR diff...')
+        if get_settings().pr_description.use_description_markers and 'pr_agent:' not in self.user_description:
+            return None
+
+        logging.info(f"Getting PR diff {self.pr_id}")
         self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
-        logging.info('Getting AI prediction...')
+        logging.info(f"Getting AI prediction {self.pr_id}")
         self.prediction = await self._get_prediction(model)
 
     async def _get_prediction(self, model: str) -> str:
@@ -134,35 +152,71 @@ class PRDescription:
 
         return response
 
-    def _prepare_pr_answer(self) -> Tuple[str, str, List[str], str]:
+
+    def _prepare_data(self):
+        # Load the AI prediction data into a dictionary
+        self.data = load_yaml(self.prediction.strip())
+
+        if get_settings().pr_description.add_original_user_description and self.user_description:
+            self.data["User Description"] = self.user_description
+
+
+    def _prepare_labels(self) -> List[str]:
+        pr_types = []
+
+        # If the 'PR Type' key is present in the dictionary, split its value by comma and assign it to 'pr_types'
+        if 'PR Type' in self.data:
+            if type(self.data['PR Type']) == list:
+                pr_types = self.data['PR Type']
+            elif type(self.data['PR Type']) == str:
+                pr_types = self.data['PR Type'].split(',')
+
+        return pr_types
+
+    def _prepare_pr_answer_with_markers(self) -> Tuple[str, str]:
+        logging.info(f"Using description marker replacements {self.pr_id}")
+        title = self.vars["title"]
+        body = self.user_description
+        if get_settings().pr_description.include_generated_by_header:
+            ai_header = f"### 🤖 Generated by PR Agent at {self.git_provider.last_commit_id.sha}\n\n"
+        else:
+            ai_header = ""
+
+        ai_summary = self.data.get('PR Description')
+        if ai_summary and not re.search(r'<!--\s*pr_agent:summary\s*-->', body):
+            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)
+
+        return title, body
+
+    def _prepare_pr_answer(self) -> Tuple[str, str]:
         """
         Prepare the PR description based on the AI prediction data.
 
         Returns:
         - title: a string containing the PR title.
-        - pr_body: a string containing the PR body in a markdown format.
+        - pr_body: a string containing the PR description body in a markdown format.
-        - pr_types: a list of strings containing the PR types.
-        - markdown_text: a string containing the AI prediction data in a markdown format. used for publishing a comment
-        - user_description: a string containing the user description
         """
-        # Load the AI prediction data into a dictionary
-        data = load_yaml(self.prediction.strip())
 
-        if get_settings().pr_description.add_original_user_description and self.user_description:
+        # Iterate over the dictionary items and append the key and value to 'markdown_text' in a markdown format
-            data["User Description"] = self.user_description
+        markdown_text = ""
-
+        for key, value in self.data.items():
-        # Initialization
+            markdown_text += f"## {key}\n\n"
-        pr_types = []
+            markdown_text += f"{value}\n\n"
-
-        # If the 'PR Type' key is present in the dictionary, split its value by comma and assign it to 'pr_types'
-        if 'PR Type' in data:
-            if type(data['PR Type']) == list:
-                pr_types = data['PR Type']
-            elif type(data['PR Type']) == str:
-                pr_types = data['PR Type'].split(',')
 
         # Remove the 'PR Title' key from the dictionary
-        ai_title = data.pop('PR Title')
+        ai_title = self.data.pop('PR Title', self.vars["title"])
         if get_settings().pr_description.keep_original_user_title:
             # Assign the original PR title to the 'title' variable
             title = self.vars["title"]
@@ -173,26 +227,27 @@ class PRDescription:
         # Iterate over the remaining dictionary items and append the key and value to 'pr_body' in a markdown format,
         # except for the items containing the word 'walkthrough'
         pr_body = ""
-        for idx, (key, value) in enumerate(data.items()):
+        for idx, (key, value) in enumerate(self.data.items()):
             pr_body += f"## {key}:\n"
             if 'walkthrough' in key.lower():
                 # for filename, description in value.items():
+                if self.git_provider.is_supported("gfm_markdown"):
+                    pr_body += "<details> <summary>files:</summary>\n\n"
                 for file in value:
                     filename = file['filename'].replace("'", "`")
                     description = file['changes in file']
                     pr_body += f'`{filename}`: {description}\n'
+                if self.git_provider.is_supported("gfm_markdown"):
+                    pr_body +="</details>\n"
             else:
                 # if the value is a list, join its items by comma
                 if type(value) == list:
                     value = ', '.join(v for v in value)
                 pr_body += f"{value}\n"
-            if idx < len(data) - 1:
+            if idx < len(self.data) - 1:
                 pr_body += "\n___\n"
 
-        markdown_text = f"## Title\n\n{title}\n\n___\n{pr_body}"
-        description = data['PR Description']
-
         if get_settings().config.verbosity_level >= 2:
             logging.info(f"title:\n{title}\n{pr_body}")
 
-        return title, pr_body, pr_types, markdown_text, description
+        return title, pr_body

pr_agent/tools/pr_reviewer.py

@@ -59,6 +59,7 @@ class PRReviewer:
             "require_tests": get_settings().pr_reviewer.require_tests_review,
             "require_security": get_settings().pr_reviewer.require_security_review,
             "require_focused": get_settings().pr_reviewer.require_focused_review,
+            "require_estimate_effort_to_review": get_settings().pr_reviewer.require_estimate_effort_to_review,
             'num_code_suggestions': get_settings().pr_reviewer.num_code_suggestions,
             'question_str': question_str,
             'answer_str': answer_str,

pr_agent/tools/pr_similar_issue.py

@@ -98,11 +98,14 @@ class PRSimilarIssue:
                 logging.info('No new issues to update')
 
     async def run(self):
+        logging.info('Getting issue...')
         repo_name, original_issue_number = self.git_provider._parse_issue_url(self.issue_url.split('=')[-1])
         issue_main = self.git_provider.repo_obj.get_issue(original_issue_number)
         issue_str, comments, number = self._process_issue(issue_main)
         openai.api_key = get_settings().openai.key
+        logging.info('Done')
 
+        logging.info('Querying...')
         res = openai.Embedding.create(input=[issue_str], engine=MODEL)
         embeds = [record['embedding'] for record in res['data']]
         pinecone_index = pinecone.Index(index_name=self.index_name)
@@ -111,22 +114,34 @@ class PRSimilarIssue:
                                    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']:
             issue_number = int(r["id"].split('.')[0].split('_')[-1])
             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(r['score'])))
+        logging.info('Done')
 
-        similar_issues_str = "Similar Issues:\n\n"
+        logging.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
             url = issue.html_url
-            similar_issues_str += f"{i + 1}. [{title}]({url})\n\n"
+            if relevant_comment_number_list[i] != -1:
+                url = list(issue.get_comments())[relevant_comment_number_list[i]].html_url
+            similar_issues_str += f"{i + 1}. **[{title}]({url})** (score={score_list[i]})\n\n"
         if get_settings().config.publish_output:
             response = issue_main.create_comment(similar_issues_str)
         logging.info(similar_issues_str)
+        logging.info('Done')
 
     def _process_issue(self, issue):
         header = issue.title

tests/unittest/test_language_handler.py

@@ -61,7 +61,7 @@ class TestSortFilesByMainLanguages:
             type('', (object,), {'filename': 'file1.py'})(),
             type('', (object,), {'filename': 'file2.java'})()
         ]
-        expected_output = [{'language': 'Other', 'files': []}]
+        expected_output = [{'language': 'Other', 'files': files}]
         assert sort_files_by_main_languages(languages, files) == expected_output
 
     # Tests that function handles empty files list