Merge commit 'a134a8bf6d44de526d6fcbba13c1f9813a5dea09' into hl/flip_2_configs

# Conflicts:
#	pr_agent/settings/configuration.toml

pr_agent/agent/pr_agent.py

@@ -73,6 +73,9 @@ class PRAgent:
         args = update_settings_from_args(args)
 
         action = action.lstrip("/").lower()
+        if action not in command2class:
+            get_logger().debug(f"Unknown command: {action}")
+            return False
         with get_logger().contextualize(command=action):
             get_logger().info("PR-Agent request handler started", analytics=True)
             if action == "reflect_and_review":

pr_agent/algo/__init__.py

@@ -11,6 +11,8 @@ MAX_TOKENS = {
     'gpt-4-1106-preview': 128000, # 128K, but may be limited by config.max_model_tokens
     'gpt-4-0125-preview': 128000,  # 128K, but may be limited by config.max_model_tokens
     'gpt-4-turbo-preview': 128000,  # 128K, but may be limited by config.max_model_tokens
+    'gpt-4-turbo-2024-04-09': 128000,  # 128K, but may be limited by config.max_model_tokens
+    'gpt-4-turbo': 128000,  # 128K, but may be limited by config.max_model_tokens
     'claude-instant-1': 100000,
     'claude-2': 100000,
     'command-nightly': 4096,

pr_agent/algo/ai_handlers/base_ai_handler.py

@@ -15,7 +15,7 @@ class BaseAiHandler(ABC):
         pass
 
     @abstractmethod   
-    async def chat_completion(self, model: str, system: str, user: str, temperature: float = 0.2):
+    async def chat_completion(self, model: str, system: str, user: str, temperature: float = 0.2, img_path: str = None):
         """
         This method should be implemented to return a chat completion from the AI model.
         Args:

pr_agent/algo/ai_handlers/litellm_ai_handler.py

@@ -1,5 +1,5 @@
 import os
-
+import requests
 import boto3
 import litellm
 import openai
@@ -61,6 +61,9 @@ class LiteLLMAIHandler(BaseAiHandler):
         if get_settings().get("HUGGINGFACE.API_BASE", None) and 'huggingface' in get_settings().config.model:
             litellm.api_base = get_settings().huggingface.api_base
             self.api_base = get_settings().huggingface.api_base
+        if get_settings().get("OLLAMA.API_BASE", None) :
+            litellm.api_base = get_settings().ollama.api_base
+            self.api_base = get_settings().ollama.api_base
         if get_settings().get("HUGGINGFACE.REPITITION_PENALTY", None):
             self.repetition_penalty = float(get_settings().huggingface.repetition_penalty)
         if get_settings().get("VERTEXAI.VERTEX_PROJECT", None):
@@ -99,13 +102,27 @@ class LiteLLMAIHandler(BaseAiHandler):
         retry=retry_if_exception_type((openai.APIError, openai.APIConnectionError, openai.Timeout)), # No retry on RateLimitError
         stop=stop_after_attempt(OPENAI_RETRIES)
     )
-    async def chat_completion(self, model: str, system: str, user: str, temperature: float = 0.2):
+    async def chat_completion(self, model: str, system: str, user: str, temperature: float = 0.2, img_path: str = None):
         try:
             resp, finish_reason = None, None
             deployment_id = self.deployment_id
             if self.azure:
                 model = 'azure/' + model
             messages = [{"role": "system", "content": system}, {"role": "user", "content": user}]
+            if img_path:
+                try:
+                    # check if the image link is alive
+                    r = requests.head(img_path, allow_redirects=True)
+                    if r.status_code == 404:
+                        error_msg = f"The image link is not [alive](img_path).\nPlease repost the original image as a comment, and send the question again with 'quote reply' (see [instructions](https://pr-agent-docs.codium.ai/tools/ask/#ask-on-images-using-the-pr-code-as-context))."
+                        get_logger().error(error_msg)
+                        return f"{error_msg}", "error"
+                except Exception as e:
+                    get_logger().error(f"Error fetching image: {img_path}", e)
+                    return f"Error fetching image: {img_path}", "error"
+                messages[1]["content"] = [{"type": "text", "text": messages[1]["content"]},
+                                          {"type": "image_url", "image_url": {"url": img_path}}]
+
             kwargs = {
                 "model": model,
                 "deployment_id": deployment_id,
@@ -150,4 +167,4 @@ class LiteLLMAIHandler(BaseAiHandler):
             if get_settings().config.verbosity_level >= 2:
                 get_logger().info(f"\nAI response:\n{resp}")
 
-        return resp, finish_reason
+        return resp, finish_reason

pr_agent/algo/pr_processing.py

@@ -9,7 +9,7 @@ from pr_agent.algo.git_patch_processing import convert_to_hunks_with_lines_numbe
 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
-from pr_agent.algo.utils import get_max_tokens, ModelType
+from pr_agent.algo.utils import get_max_tokens, clip_tokens, ModelType
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers.git_provider import GitProvider
 from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
@@ -87,22 +87,34 @@ def get_pr_diff(git_provider: GitProvider, token_handler: TokenHandler, model: s
     # if we are over the limit, start pruning
     get_logger().info(f"Tokens: {total_tokens}, total tokens over limit: {get_max_tokens(model)}, "
                       f"pruning diff.")
-    patches_compressed, modified_file_names, deleted_file_names, added_file_names = \
+    patches_compressed, modified_file_names, deleted_file_names, added_file_names, total_tokens_new = \
         pr_generate_compressed_diff(pr_languages, token_handler, model, add_line_numbers_to_hunks)
 
+    # Insert additional information about added, modified, and deleted files if there is enough space
+    max_tokens = get_max_tokens(model) - OUTPUT_BUFFER_TOKENS_HARD_THRESHOLD
+    curr_token = total_tokens_new  # == token_handler.count_tokens(final_diff)+token_handler.prompt_tokens
     final_diff = "\n".join(patches_compressed)
-    if added_file_names:
+    delta_tokens = 10
+    if added_file_names and (max_tokens - curr_token) > delta_tokens:
         added_list_str = ADDED_FILES_ + "\n".join(added_file_names)
-        final_diff = final_diff + "\n\n" + added_list_str
-    if modified_file_names:
+        added_list_str = clip_tokens(added_list_str, max_tokens - curr_token)
+        if added_list_str:
+            final_diff = final_diff + "\n\n" + added_list_str
+            curr_token += token_handler.count_tokens(added_list_str) + 2
+    if modified_file_names and (max_tokens - curr_token) > delta_tokens:
         modified_list_str = MORE_MODIFIED_FILES_ + "\n".join(modified_file_names)
-        final_diff = final_diff + "\n\n" + modified_list_str
-    if deleted_file_names:
+        modified_list_str = clip_tokens(modified_list_str, max_tokens - curr_token)
+        if modified_list_str:
+            final_diff = final_diff + "\n\n" + modified_list_str
+            curr_token += token_handler.count_tokens(modified_list_str) + 2
+    if deleted_file_names and (max_tokens - curr_token) > delta_tokens:
         deleted_list_str = DELETED_FILES_ + "\n".join(deleted_file_names)
-        final_diff = final_diff + "\n\n" + deleted_list_str
+        deleted_list_str = clip_tokens(deleted_list_str, max_tokens - curr_token)
+        if deleted_list_str:
+            final_diff = final_diff + "\n\n" + deleted_list_str
     try:
         get_logger().debug(f"After pruning, added_list_str: {added_list_str}, modified_list_str: {modified_list_str}, "
-                          f"deleted_list_str: {deleted_list_str}")
+                           f"deleted_list_str: {deleted_list_str}")
     except Exception as e:
         pass
     return final_diff
@@ -149,7 +161,7 @@ def pr_generate_extended_diff(pr_languages: list,
 
 
 def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, model: str,
-                                convert_hunks_to_line_numbers: bool) -> Tuple[list, list, list, list]:
+                                convert_hunks_to_line_numbers: bool) -> Tuple[list, list, list, list, int]:
     """
     Generate a compressed diff string for a pull request, using diff minimization techniques to reduce the number of
     tokens used.
@@ -195,10 +207,11 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, mo
         patch = handle_patch_deletions(patch, original_file_content_str,
                                        new_file_content_str, file.filename, file.edit_type)
         if patch is None:
-            if not deleted_files_list:
-                total_tokens += token_handler.count_tokens(DELETED_FILES_)
-            deleted_files_list.append(file.filename)
-            total_tokens += token_handler.count_tokens(file.filename) + 1
+            # if not deleted_files_list:
+            #     total_tokens += token_handler.count_tokens(DELETED_FILES_)
+            if file.filename not in deleted_files_list:
+                deleted_files_list.append(file.filename)
+            # total_tokens += token_handler.count_tokens(file.filename) + 1
             continue
 
         if convert_hunks_to_line_numbers:
@@ -219,14 +232,17 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, mo
             if get_settings().config.verbosity_level >= 2:
                 get_logger().warning(f"Patch too large, minimizing it, {file.filename}")
             if file.edit_type == EDIT_TYPE.ADDED:
-                if not added_files_list:
-                    total_tokens += token_handler.count_tokens(ADDED_FILES_)
-                added_files_list.append(file.filename)
+                # if not added_files_list:
+                #     total_tokens += token_handler.count_tokens(ADDED_FILES_)
+                if file.filename not in added_files_list:
+                    added_files_list.append(file.filename)
+                # total_tokens += token_handler.count_tokens(file.filename) + 1
             else:
-                if not modified_files_list:
-                    total_tokens += token_handler.count_tokens(MORE_MODIFIED_FILES_)
-                modified_files_list.append(file.filename)
-                total_tokens += token_handler.count_tokens(file.filename) + 1
+                # if not modified_files_list:
+                #     total_tokens += token_handler.count_tokens(MORE_MODIFIED_FILES_)
+                if file.filename not in modified_files_list:
+                    modified_files_list.append(file.filename)
+                # total_tokens += token_handler.count_tokens(file.filename) + 1
             continue
 
         if patch:
@@ -239,7 +255,7 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, mo
             if get_settings().config.verbosity_level >= 2:
                 get_logger().info(f"Tokens: {total_tokens}, last filename: {file.filename}")
 
-    return patches, modified_files_list, deleted_files_list, added_files_list
+    return patches, modified_files_list, deleted_files_list, added_files_list, total_tokens
 
 
 async def retry_with_fallback_models(f: Callable, model_type: ModelType = ModelType.REGULAR):
@@ -382,4 +398,4 @@ def get_pr_multi_diffs(git_provider: GitProvider,
         final_diff = "\n".join(patches)
         final_diff_list.append(final_diff)
 
-    return final_diff_list
+    return final_diff_list

pr_agent/algo/token_handler.py

@@ -1,12 +1,25 @@
 from jinja2 import Environment, StrictUndefined
 from tiktoken import encoding_for_model, get_encoding
-
 from pr_agent.config_loader import get_settings
+from threading import Lock
 
 
-def get_token_encoder():
-    return encoding_for_model(get_settings().config.model) if "gpt" in get_settings().config.model else get_encoding(
-        "cl100k_base")
+class TokenEncoder:
+    _encoder_instance = None
+    _model = None
+    _lock = Lock()  # Create a lock object
+
+    @classmethod
+    def get_token_encoder(cls):
+        model = get_settings().config.model
+        if cls._encoder_instance is None or model != cls._model:  # Check without acquiring the lock for performance
+            with cls._lock:  # Lock acquisition to ensure thread safety
+                if cls._encoder_instance is None or model != cls._model:
+                    cls._model = model
+                    cls._encoder_instance = encoding_for_model(cls._model) if "gpt" in cls._model else get_encoding(
+                        "cl100k_base")
+        return cls._encoder_instance
+
 
 class TokenHandler:
     """
@@ -31,7 +44,7 @@ class TokenHandler:
         - system: The system string.
         - user: The user string.
         """
-        self.encoder = get_token_encoder()
+        self.encoder = TokenEncoder.get_token_encoder()
         if pr is not None:
             self.prompt_tokens = self._get_system_user_tokens(pr, self.encoder, vars, system, user)
 

pr_agent/algo/utils.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import difflib
 import json
+import os
 import re
 import textwrap
 from datetime import datetime
@@ -12,7 +13,7 @@ import yaml
 from starlette_context import context
 
 from pr_agent.algo import MAX_TOKENS
-from pr_agent.algo.token_handler import get_token_encoder
+from pr_agent.algo.token_handler import TokenEncoder
 from pr_agent.config_loader import get_settings, global_settings
 from pr_agent.algo.types import FilePatchInfo
 from pr_agent.log import get_logger
@@ -566,7 +567,7 @@ def clip_tokens(text: str, max_tokens: int, add_three_dots=True) -> str:
         return text
 
     try:
-        encoder = get_token_encoder()
+        encoder = TokenEncoder.get_token_encoder()
         num_input_tokens = len(encoder.encode(text))
         if num_input_tokens <= max_tokens:
             return text
@@ -575,7 +576,7 @@ def clip_tokens(text: str, max_tokens: int, add_three_dots=True) -> str:
         num_output_chars = int(chars_per_token * max_tokens)
         clipped_text = text[:num_output_chars]
         if add_three_dots:
-            clipped_text += "...(truncated)"
+            clipped_text += "\n...(truncated)"
         return clipped_text
     except Exception as e:
         get_logger().warning(f"Failed to clip tokens: {e}")
@@ -661,3 +662,15 @@ def find_line_number_of_relevant_line_in_file(diff_files: List[FilePatchInfo],
                             absolute_position = start2 + delta - 1
                             break
     return position, absolute_position
+
+def github_action_output(output_data: dict, key_name: str):
+    try:
+        if not get_settings().get('github_action_config.enable_output', False):
+            return
+        
+        key_data = output_data.get(key_name, {})
+        with open(os.environ['GITHUB_OUTPUT'], 'a') as fh:
+            print(f"{key_name}={json.dumps(key_data, indent=None, ensure_ascii=False)}", file=fh)
+    except Exception as e:
+        get_logger().error(f"Failed to write to GitHub Action output: {e}")
+    return

pr_agent/git_providers/codecommit_provider.py

@@ -10,7 +10,7 @@ from ..algo.utils import load_large_diff
 from .git_provider import GitProvider
 from ..config_loader import get_settings
 from ..log import get_logger
-
+from pr_agent.algo.language_handler import is_valid_file
 
 class PullRequestCCMimic:
     """

pr_agent/git_providers/github_provider.py

@@ -745,22 +745,4 @@ class GithubProvider(GitProvider):
             return False
 
     def calc_pr_statistics(self, pull_request_data: dict):
-        try:
-            out = {}
-            from datetime import datetime
-            created_at = pull_request_data['created_at']
-            closed_at = pull_request_data['closed_at']
-            closed_at_datetime = datetime.strptime(closed_at, "%Y-%m-%dT%H:%M:%SZ")
-            created_at_datetime = datetime.strptime(created_at, "%Y-%m-%dT%H:%M:%SZ")
-            difference = closed_at_datetime - created_at_datetime
-            out['hours'] = difference.total_seconds() / 3600
-            out['commits'] = pull_request_data['commits']
-            out['comments'] = pull_request_data['comments']
-            out['review_comments'] = pull_request_data['review_comments']
-            out['changed_files'] = pull_request_data['changed_files']
-            out['additions'] = pull_request_data['additions']
-            out['deletions'] = pull_request_data['deletions']
-        except Exception as e:
-            get_logger().exception(f"Failed to calculate PR statistics, error: {e}")
-            return {}
-        return out
+        return {}

pr_agent/servers/github_action_runner.py

@@ -46,19 +46,22 @@ async def run_action():
     if not GITHUB_EVENT_PATH:
         print("GITHUB_EVENT_PATH not set")
         return
-    if not OPENAI_KEY:
-        print("OPENAI_KEY not set")
-        return
     if not GITHUB_TOKEN:
         print("GITHUB_TOKEN not set")
         return
 
     # Set the environment variables in the settings
-    get_settings().set("OPENAI.KEY", OPENAI_KEY)
+    if OPENAI_KEY:
+        get_settings().set("OPENAI.KEY", OPENAI_KEY)
+    else:
+        # Might not be set if the user is using models not from OpenAI
+        print("OPENAI_KEY not set")
     if OPENAI_ORG:
         get_settings().set("OPENAI.ORG", OPENAI_ORG)
     get_settings().set("GITHUB.USER_TOKEN", GITHUB_TOKEN)
     get_settings().set("GITHUB.DEPLOYMENT_TYPE", "user")
+    enable_output = get_setting_or_env("GITHUB_ACTION_CONFIG.ENABLE_OUTPUT", True)
+    get_settings().set("GITHUB_ACTION_CONFIG.ENABLE_OUTPUT", enable_output)
 
     # Load the event payload
     try:
@@ -101,6 +104,8 @@ async def run_action():
                     await PRReviewer(pr_url).run()
                 if auto_improve is None or is_true(auto_improve):
                     await PRCodeSuggestions(pr_url).run()
+        else:
+            get_logger().info(f"Skipping action: {action}")
 
     # Handle issue comment event
     elif GITHUB_EVENT_NAME == "issue_comment" or GITHUB_EVENT_NAME == "pull_request_review_comment":

pr_agent/servers/github_app.py

@@ -86,8 +86,13 @@ async def handle_comments_on_pr(body: Dict[str, Any],
         return {}
     comment_body = body.get("comment", {}).get("body")
     if comment_body and isinstance(comment_body, str) and not comment_body.lstrip().startswith("/"):
-        get_logger().info("Ignoring comment not starting with /")
-        return {}
+        if '/ask' in comment_body and comment_body.strip().startswith('> ![image]'):
+            comment_body_split = comment_body.split('/ask')
+            comment_body = '/ask' + comment_body_split[1] +' \n' +comment_body_split[0].strip().lstrip('>')
+            get_logger().info(f"Reformatting comment_body so command is at the beginning: {comment_body}")
+        else:
+            get_logger().info("Ignoring comment not starting with /")
+            return {}
     disable_eyes = False
     if "issue" in body and "pull_request" in body["issue"] and "url" in body["issue"]["pull_request"]:
         api_url = body["issue"]["pull_request"]["url"]

pr_agent/servers/help.py

@@ -128,7 +128,7 @@ Be specific, clear, and concise in the instructions. With extra instructions, yo
 Examples for extra instructions:
 ```
 [pr_description] 
-extra_instructions="""
+extra_instructions="""\
 - The PR title should be in the format: '<PR type>: <title>'
 - The title should be short and concise (up to 10 words)
 - ...
@@ -160,16 +160,17 @@ It can be invoked manually by commenting on any PR:
 /ask "..."
 ```
 
-Note that the tool does not have "memory" of previous questions, and answers each question independently.        
+Note that the tool does not have "memory" of previous questions, and answers each question independently.   
+You can ask questions about the entire PR, about specific code lines, or about an image related to the PR code changes.     
         """
-        output += "\n\n<table>"
-
-        # general
-        output += "\n\n<tr><td><details> <summary><strong> More PR-Agent commands</strong></summary><hr> \n\n"
-        output += HelpMessage.get_general_bot_help_text()
-        output += "\n\n</details></td></tr>\n\n"
-
-        output += "</table>"
+        # output += "\n\n<table>"
+        #
+        # # # general
+        # # output += "\n\n<tr><td><details> <summary><strong> More PR-Agent commands</strong></summary><hr> \n\n"
+        # # output += HelpMessage.get_general_bot_help_text()
+        # # output += "\n\n</details></td></tr>\n\n"
+        #
+        # output += "</table>"
 
         output += f"\n\nSee the [ask usage](https://pr-agent-docs.codium.ai/tools/ask/) page for a comprehensive guide on using this tool.\n\n"
 

pr_agent/settings/configuration.toml

@@ -1,7 +1,7 @@
 [config]
-model="gpt-4" # "gpt-4-0125-preview"
-model_turbo="gpt-4-0125-preview"
-fallback_models=["gpt-3.5-turbo-16k"]
+model="gpt-4-turbo-2024-04-09"
+model_turbo="gpt-4-turbo-2024-04-09"
+fallback_models=["gpt-4-0125-preview"]
 git_provider="github"
 publish_output=true
 publish_output_progress=true
@@ -61,6 +61,9 @@ enable_pr_type=true
 disable_final_update_message = false
 enable_help_text=false
 enable_help_comment=true
+# describe as comment
+publish_description_as_comment=false
+publish_description_as_comment_persistent=true
 ## changes walkthrough section
 enable_semantic_files_types=true
 collapsible_file_list='adaptive' # true, false, 'adaptive'
@@ -110,6 +113,11 @@ file = ""              # in case there are several components with the same name
 class_name = ""        # in case there are several methods with the same name in the same file, you can specify the relevant class name
 enable_help_text=true
 
+[pr_improve_component] # /improve_component #
+num_code_suggestions=4
+extra_instructions = ""
+file = ""              # in case there are several components with the same name, you can specify the relevant file
+class_name = ""
 
 [checks] # /checks (pro feature) #
 enable_auto_checks_feedback=true
@@ -133,6 +141,7 @@ try_fix_invalid_inline_comments = true
 # auto_review = true    # set as env var in .github/workflows/pr-agent.yaml
 # auto_describe = true  # set as env var in .github/workflows/pr-agent.yaml
 # auto_improve = true   # set as env var in .github/workflows/pr-agent.yaml
+# enable_output = true   # set as env var in .github/workflows/pr-agent.yaml
 
 [github_app]
 # these toggles allows running the github app from custom deployments

pr_agent/tools/pr_code_suggestions.py

@@ -76,7 +76,7 @@ class PRCodeSuggestions:
             relevant_configs = {'pr_code_suggestions': dict(get_settings().pr_code_suggestions),
                                 'config': dict(get_settings().config)}
             get_logger().debug("Relevant configs", artifacts=relevant_configs)
-            if get_settings().config.publish_output:
+            if get_settings().config.publish_output and get_settings().config.publish_output_progress:
                 if self.git_provider.is_supported("gfm_markdown"):
                     self.progress_response = self.git_provider.publish_comment(self.progress)
                 else:
@@ -196,24 +196,31 @@ class PRCodeSuggestions:
         suggestion_list = []
         one_sentence_summary_list = []
         for i, suggestion in enumerate(data['code_suggestions']):
-            if get_settings().pr_code_suggestions.summarize:
-                if not suggestion or 'one_sentence_summary' not in suggestion or 'label' not in suggestion or 'relevant_file' not in suggestion:
-                    get_logger().debug(f"Skipping suggestion {i + 1}, because it is invalid: {suggestion}")
-                    continue
-
-                if suggestion['one_sentence_summary'] in one_sentence_summary_list:
-                    get_logger().debug(f"Skipping suggestion {i + 1}, because it is a duplicate: {suggestion}")
-                    continue
-
-            if ('existing_code' in suggestion) and ('improved_code' in suggestion) and (
-                    suggestion['existing_code'] != suggestion['improved_code']):
-                suggestion = self._truncate_if_needed(suggestion)
+            try:
                 if get_settings().pr_code_suggestions.summarize:
-                    one_sentence_summary_list.append(suggestion['one_sentence_summary'])
-                suggestion_list.append(suggestion)
-            else:
-                get_logger().debug(
-                    f"Skipping suggestion {i + 1}, because existing code is equal to improved code {suggestion['existing_code']}")
+                    if not suggestion or 'one_sentence_summary' not in suggestion or 'label' not in suggestion or 'relevant_file' not in suggestion:
+                        get_logger().debug(f"Skipping suggestion {i + 1}, because it is invalid: {suggestion}")
+                        continue
+
+                    if suggestion['one_sentence_summary'] in one_sentence_summary_list:
+                        get_logger().debug(f"Skipping suggestion {i + 1}, because it is a duplicate: {suggestion}")
+                        continue
+
+                if 'const' in suggestion['suggestion_content'] and 'instead' in suggestion['suggestion_content'] and 'let' in suggestion['suggestion_content']:
+                    get_logger().debug(f"Skipping suggestion {i + 1}, because it uses 'const instead let': {suggestion}")
+                    continue
+
+                if ('existing_code' in suggestion) and ('improved_code' in suggestion) and (
+                        suggestion['existing_code'] != suggestion['improved_code']):
+                    suggestion = self._truncate_if_needed(suggestion)
+                    if get_settings().pr_code_suggestions.summarize:
+                        one_sentence_summary_list.append(suggestion['one_sentence_summary'])
+                    suggestion_list.append(suggestion)
+                else:
+                    get_logger().debug(
+                        f"Skipping suggestion {i + 1}, because existing code is equal to improved code {suggestion['existing_code']}")
+            except Exception as e:
+                get_logger().error(f"Error processing suggestion {i + 1}: {suggestion}, error: {e}")
         data['code_suggestions'] = suggestion_list
 
         return data

pr_agent/tools/pr_description.py

@@ -132,7 +132,14 @@ class PRDescription:
                 # publish description
                 if get_settings().pr_description.publish_description_as_comment:
                     full_markdown_description = f"## Title\n\n{pr_title}\n\n___\n{pr_body}"
-                    self.git_provider.publish_comment(full_markdown_description)
+                    if get_settings().pr_description.publish_description_as_comment_persistent:
+                        self.git_provider.publish_persistent_comment(full_markdown_description,
+                                                                     initial_header="## Title",
+                                                                     update_header=True,
+                                                                     name="describe",
+                                                                     final_update_message=False, )
+                    else:
+                        self.git_provider.publish_comment(full_markdown_description)
                 else:
                     self.git_provider.publish_description(pr_title, pr_body)
 

pr_agent/tools/pr_help_message.py

@@ -27,12 +27,13 @@ class PRHelpMessage:
             tool_names.append(f"[DESCRIBE]({base_path}/describe/)")
             tool_names.append(f"[REVIEW]({base_path}/review/)")
             tool_names.append(f"[IMPROVE]({base_path}/improve/)")
-            tool_names.append(f"[ANALYZE]({base_path}/analyze/) 💎")
             tool_names.append(f"[UPDATE CHANGELOG]({base_path}/update_changelog/)")
-            tool_names.append(f"[ADD DOCUMENTATION]({base_path}/documentation/) 💎")
-            tool_names.append(f"[ASK]({base_path}/ask/)")
-            tool_names.append(f"[GENERATE CUSTOM LABELS]({base_path}/custom_labels/)")
+            tool_names.append(f"[ADD DOCS]({base_path}/documentation/) 💎")
             tool_names.append(f"[TEST]({base_path}/test/) 💎")
+            tool_names.append(f"[IMPROVE COMPONENT]({base_path}/improve_component/) 💎")
+            tool_names.append(f"[ANALYZE]({base_path}/analyze/) 💎")
+            tool_names.append(f"[ASK]({base_path}/ask/)")
+            tool_names.append(f"[GENERATE CUSTOM LABELS]({base_path}/custom_labels/) 💎")
             tool_names.append(f"[CI FEEDBACK]({base_path}/ci_feedback/) 💎")
             tool_names.append(f"[CUSTOM SUGGESTIONS]({base_path}/custom_suggestions/) 💎")
             tool_names.append(f"[SIMILAR ISSUE]({base_path}/similar_issues/)")
@@ -40,27 +41,29 @@ class PRHelpMessage:
             descriptions = []
             descriptions.append("Generates PR description - title, type, summary, code walkthrough and labels")
             descriptions.append("Adjustable feedback about the PR, possible issues, security concerns, review effort and more")
-            descriptions.append("Code suggestions for improving the PR.")
-            descriptions.append("Identifies code components that changed in the PR, and enables to interactively generate tests, docs, and code suggestions for each component.")
-            descriptions.append("Automatically updates the changelog.")
-            descriptions.append("Generates documentation to methods/functions/classes that changed in the PR.")
-            descriptions.append("Answering free-text questions about the PR.")
+            descriptions.append("Code suggestions for improving the PR")
+            descriptions.append("Automatically updates the changelog")
+            descriptions.append("Generates documentation to methods/functions/classes that changed in the PR")
+            descriptions.append("Generates unit tests for a specific component, based on the PR code change")
+            descriptions.append("Code suggestions for a specific component that changed in the PR")
+            descriptions.append("Identifies code components that changed in the PR, and enables to interactively generate tests, docs, and code suggestions for each component")
+            descriptions.append("Answering free-text questions about the PR")
             descriptions.append("Generates custom labels for the PR, based on specific guidelines defined by the user")
-            descriptions.append("Generates unit tests for a specific component, based on the PR code change.")
-            descriptions.append("Generates feedback and analysis for a failed CI job.")
-            descriptions.append("Generates custom suggestions for improving the PR code, based on specific guidelines defined by the user.")
-            descriptions.append("Automatically retrieves and presents similar issues.")
+            descriptions.append("Generates feedback and analysis for a failed CI job")
+            descriptions.append("Generates custom suggestions for improving the PR code, based only on specific guidelines defined by the user")
+            descriptions.append("Automatically retrieves and presents similar issues")
 
             commands  =[]
             commands.append("`/describe`")
             commands.append("`/review`")
             commands.append("`/improve`")
-            commands.append("`/analyze`")
             commands.append("`/update_changelog`")
             commands.append("`/add_docs`")
+            commands.append("`/test`")
+            commands.append("`/improve_component`")
+            commands.append("`/analyze`")
             commands.append("`/ask`")
             commands.append("`/generate_labels`")
-            commands.append("`/test`")
             commands.append("`/checks`")
             commands.append("`/custom_suggestions`")
             commands.append("`/similar_issue`")
@@ -69,9 +72,13 @@ class PRHelpMessage:
             checkbox_list.append(" - [ ] Run <!-- /describe -->")
             checkbox_list.append(" - [ ] Run <!-- /review -->")
             checkbox_list.append(" - [ ] Run <!-- /improve -->")
-            checkbox_list.append(" - [ ] Run <!-- /analyze -->")
             checkbox_list.append(" - [ ] Run <!-- /update_changelog -->")
             checkbox_list.append(" - [ ] Run <!-- /add_docs -->")
+            checkbox_list.append(" - [ ] Run <!-- /test -->")
+            checkbox_list.append(" - [ ] Run <!-- /improve_component -->")
+            checkbox_list.append(" - [ ] Run <!-- /analyze -->")
+            checkbox_list.append("[*]")
+            checkbox_list.append("[*]")
             checkbox_list.append("[*]")
             checkbox_list.append("[*]")
             checkbox_list.append("[*]")
@@ -80,16 +87,16 @@ class PRHelpMessage:
             checkbox_list.append("[*]")
 
             if isinstance(self.git_provider, GithubProvider):
-                pr_comment += f"<table><tr align='center'><th align='center'>Tool</th><th align='center'>Description</th><th align='center'>Invoke Interactively :gem:</th></tr>"
+                pr_comment += f"<table><tr align='left'><th align='left'>Tool</th><th align='left'>Description</th><th align='left'>Trigger Interactively :gem:</th></tr>"
                 for i in range(len(tool_names)):
-                    pr_comment += f"\n<tr><td align='center'>\n\n<strong>{tool_names[i]}</strong></td>\n<td>{descriptions[i]}</td>\n<td>\n\n{checkbox_list[i]}\n</td></tr>"
+                    pr_comment += f"\n<tr><td align='left'>\n\n<strong>{tool_names[i]}</strong></td>\n<td>{descriptions[i]}</td>\n<td>\n\n{checkbox_list[i]}\n</td></tr>"
                 pr_comment += "</table>\n\n"
                 pr_comment += f"""\n\n(1) Note that each tool be [triggered automatically](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools-for-pr-actions) when a new PR is opened, or called manually by [commenting on a PR](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#online-usage)."""
                 pr_comment += f"""\n\n(2) Tools marked with [*] require additional parameters to be passed. For example, to invoke the `/ask` tool, you need to comment on a PR: `/ask "<question content>"`. See the relevant documentation for each tool for more details."""
             else:
-                pr_comment += f"<table><tr align='center'><th align='center'>Tool</th><th align='left'>Command</th><th align='left'>Description</th></tr>"
+                pr_comment += f"<table><tr align='left'><th align='left'>Tool</th><th align='left'>Command</th><th align='left'>Description</th></tr>"
                 for i in range(len(tool_names)):
-                    pr_comment += f"\n<tr><td align='center'>\n\n<strong>{tool_names[i]}</strong></td><td>{commands[i]}</td><td>{descriptions[i]}</td></tr>"
+                    pr_comment += f"\n<tr><td align='left'>\n\n<strong>{tool_names[i]}</strong></td><td>{commands[i]}</td><td>{descriptions[i]}</td></tr>"
                 pr_comment += "</table>\n\n"
                 pr_comment += f"""\n\nNote that each tool be [invoked automatically](https://pr-agent-docs.codium.ai/usage-guide/automations_and_usage/) when a new PR is opened, or called manually by [commenting on a PR](https://pr-agent-docs.codium.ai/usage-guide/automations_and_usage/#online-usage)."""
             if get_settings().config.publish_output:

pr_agent/tools/pr_questions.py

@@ -56,6 +56,12 @@ class PRQuestions:
         get_logger().debug("Relevant configs", artifacts=relevant_configs)
         if get_settings().config.publish_output:
             self.git_provider.publish_comment("Preparing answer...", is_temporary=True)
+
+        # identify image
+        img_path = self.idenfity_image_in_comment()
+        if img_path:
+            get_logger().debug(f"Image path identified", artifact=img_path)
+
         await retry_with_fallback_models(self._prepare_prediction)
 
         pr_comment = self._prepare_pr_answer()
@@ -71,6 +77,19 @@ class PRQuestions:
             self.git_provider.remove_initial_comment()
         return ""
 
+    def idenfity_image_in_comment(self):
+        img_path = ''
+        if '![image]' in self.question_str:
+            # assuming structure:
+            # /ask question ...  > ![image](img_path)
+            img_path = self.question_str.split('![image]')[1].strip().strip('()')
+            self.vars['img_path'] = img_path
+        elif 'https://' in self.question_str and ('.png' in self.question_str or 'jpg' in self.question_str): # direct image link
+            # include https:// in the image path
+            img_path = 'https://' + self.question_str.split('https://')[1]
+            self.vars['img_path'] = img_path
+        return img_path
+
     async def _prepare_prediction(self, model: str):
         self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
         if self.patches_diff:
@@ -86,8 +105,14 @@ class PRQuestions:
         environment = Environment(undefined=StrictUndefined)
         system_prompt = environment.from_string(get_settings().pr_questions_prompt.system).render(variables)
         user_prompt = environment.from_string(get_settings().pr_questions_prompt.user).render(variables)
-        response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
-                                                                        system=system_prompt, user=user_prompt)
+        if 'img_path' in variables:
+            img_path = self.vars['img_path']
+            response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
+                                                                            system=system_prompt, user=user_prompt,
+                                                                            img_path=img_path)
+        else:
+            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_answer(self) -> str:

pr_agent/tools/pr_reviewer.py

@@ -8,7 +8,7 @@ from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
 from pr_agent.algo.ai_handlers.litellm_ai_handler import LiteLLMAIHandler
 from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
 from pr_agent.algo.token_handler import TokenHandler
-from pr_agent.algo.utils import convert_to_markdown, load_yaml, ModelType
+from pr_agent.algo.utils import convert_to_markdown, github_action_output, load_yaml, ModelType
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
 from pr_agent.git_providers.git_provider import IncrementalPR, get_main_pr_language
@@ -192,6 +192,7 @@ class PRReviewer:
         data = load_yaml(self.prediction.strip(),
                          keys_fix_yaml=["estimated_effort_to_review_[1-5]:", "security_concerns:", "possible_issues:",
                                         "relevant_file:", "relevant_line:", "suggestion:"])
+        github_action_output(data, 'review')
 
         if 'code_feedback' in data:
             code_feedback = data['code_feedback']
@@ -357,6 +358,9 @@ class PRReviewer:
         return True
 
     def set_review_labels(self, data):
+        if not get_settings().config.publish_output:
+            return
+
         if (get_settings().pr_reviewer.enable_review_labels_security or
                 get_settings().pr_reviewer.enable_review_labels_effort):
             try: