Merge remote-tracking branch 'origin/main'

docker/Dockerfile

@@ -8,7 +8,7 @@ ENV PYTHONPATH=/app
 
 FROM base as github_app
 ADD pr_agent pr_agent
-CMD ["python", "pr_agent/servers/github_app.py"]
+CMD ["python", "-m", "gunicorn", "-k", "uvicorn.workers.UvicornWorker", "-c", "pr_agent/servers/gunicorn_config.py", "--forwarded-allow-ips", "*", "pr_agent.servers.github_app:app"]
 
 FROM base as bitbucket_app
 ADD pr_agent pr_agent

docs/docs/tools/describe.md

@@ -108,7 +108,7 @@ If you prefer to have the file summaries appear in the "Files changed" tab on ev
 
 ![Diffview table](https://codium.ai/images/pr_agent/diffview-table.png){width=512}
 
-- `true`: A collapsable file comment with changes title and a changes summary for each file in the PR.
+- `true`: A collapsible file comment with changes title and a changes summary for each file in the PR.
 
 ![Diffview changes](https://codium.ai/images/pr_agent/diffview_changes.png){width=512}
 
@@ -194,7 +194,7 @@ The description should be comprehensive and detailed, indicating when to add the
     ```
     pr_commands = ["/describe", ...]
     ```
-    meaning the `describe` tool will run automatically on every PR, with the default configurations. 
+    meaning the `describe` tool will run automatically on every PR, with the default configurations.
 
 
    - Markers are an alternative way to control the generated description, to give maximal control to the user. If you set:

docs/docs/tools/improve.md

@@ -157,7 +157,7 @@ the tool can automatically approve the PR when the user checks the self-review c
 
 !!! tip "Extra instructions"
 
-    Extra instructions are very important for the `imrpove` tool, since they enable you to guide the model to suggestions that are more relevant to the specific needs of the project.
+    Extra instructions are very important for the `improve` tool, since they enable you to guide the model to suggestions that are more relevant to the specific needs of the project.
     
     Be specific, clear, and concise in the instructions. With extra instructions, you are the prompter. Specify relevant aspects that you want the model to focus on.
     
@@ -190,6 +190,6 @@ the tool can automatically approve the PR when the user checks the self-review c
     - Only if the `Category` header is relevant, the user should move to the summarized suggestion description
     - Only if the summarized suggestion description is relevant, the user should click on the collapsible, to read the full suggestion description with a code preview example.
 
-In addition, we recommend to use the `exra_instructions` field to guide the model to suggestions that are more relevant to the specific needs of the project. 
+In addition, we recommend to use the `extra_instructions` field to guide the model to suggestions that are more relevant to the specific needs of the project. 
 <br>
 Consider also trying the [Custom Prompt Tool](./custom_prompt.md) 💎, that will **only** propose code suggestions that follow specific guidelines defined by user.

pr_agent/git_providers/bitbucket_provider.py

@@ -235,7 +235,7 @@ class BitbucketProvider(GitProvider):
         except Exception as e:
             get_logger().exception(f"Failed to remove comment, error: {e}")
 
-    # funtion to create_inline_comment
+    # function to create_inline_comment
     def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str, absolute_position: int = None):
         position, absolute_position = find_line_number_of_relevant_line_in_file(self.get_diff_files(),
                                                                             relevant_file.strip('`'),
@@ -404,7 +404,7 @@ class BitbucketProvider(GitProvider):
 
     def get_commit_messages(self):
         return ""  # not implemented yet
-    
+
     # bitbucket does not support labels
     def publish_description(self, pr_title: str, description: str):
         payload = json.dumps({
@@ -424,7 +424,7 @@ class BitbucketProvider(GitProvider):
     # bitbucket does not support labels
     def publish_labels(self, pr_types: list):
         pass
-    
+
     # bitbucket does not support labels
     def get_pr_labels(self, update=False):
         pass

pr_agent/git_providers/bitbucket_server_provider.py

@@ -211,7 +211,7 @@ class BitbucketServerProvider(GitProvider):
     def remove_comment(self, comment):
         pass
 
-    # funtion to create_inline_comment
+    # function to create_inline_comment
     def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str,
                               absolute_position: int = None):
 

pr_agent/git_providers/github_provider.py

@@ -107,7 +107,7 @@ class GithubProvider(GitProvider):
             git_files = context.get("git_files", None)
             if git_files:
                 return git_files
-            self.git_files = list(self.pr.get_files()) # 'list' to hanlde pagination
+            self.git_files = list(self.pr.get_files()) # 'list' to handle pagination
             context["git_files"] = self.git_files
             return self.git_files
         except Exception:

pr_agent/servers/azuredevops_server_webhook.py

@@ -41,7 +41,7 @@ def handle_request(
 ):
     log_context["action"] = body
     log_context["api_url"] = url
-    
+
     async def inner():
         try:
             with get_logger().contextualize(**log_context):
@@ -89,7 +89,7 @@ async def handle_webhook(background_tasks: BackgroundTasks, request: Request):
     get_logger().info(json.dumps(data))
 
     actions = []
-    if data["eventType"] == "git.pullrequest.created": 
+    if data["eventType"] == "git.pullrequest.created":
         # API V1 (latest)
         pr_url = unquote(data["resource"]["_links"]["web"]["href"].replace("_apis/git/repositories", "_git"))
         log_context["event"] = data["eventType"]
@@ -102,7 +102,7 @@ async def handle_webhook(background_tasks: BackgroundTasks, request: Request):
                 repo = data["resource"]["pullRequest"]["repository"]["webUrl"]
                 pr_url = unquote(f'{repo}/pullrequest/{data["resource"]["pullRequest"]["pullRequestId"]}')
                 actions = [data["resource"]["comment"]["content"]]
-            else: 
+            else:
                 # API V1 not supported as it does not contain the PR URL
                 return JSONResponse(
                     status_code=status.HTTP_400_BAD_REQUEST,
@@ -120,7 +120,7 @@ async def handle_webhook(background_tasks: BackgroundTasks, request: Request):
 
     log_context["event"] = data["eventType"]
     log_context["api_url"] = pr_url
-    
+
     for action in actions:
         try:
             handle_request(background_tasks, pr_url, action, log_context)
@@ -131,13 +131,13 @@ async def handle_webhook(background_tasks: BackgroundTasks, request: Request):
                 content=json.dumps({"message": "Internal server error"}),
             )
     return JSONResponse(
-        status_code=status.HTTP_202_ACCEPTED, content=jsonable_encoder({"message": "webhook triggerd successfully"})
+        status_code=status.HTTP_202_ACCEPTED, content=jsonable_encoder({"message": "webhook triggered successfully"})
     )
 
 @router.get("/")
 async def root():
     return {"status": "ok"}
-    
+
 def start():
     app = FastAPI(middleware=[Middleware(RawContextMiddleware)])
     app.include_router(router)

pr_agent/servers/gunicorn_config.py

@@ -0,0 +1,191 @@
+import multiprocessing
+import os
+
+# from prometheus_client import multiprocess
+
+# Sample Gunicorn configuration file.
+
+#
+# Server socket
+#
+#   bind - The socket to bind.
+#
+#       A string of the form: 'HOST', 'HOST:PORT', 'unix:PATH'.
+#       An IP is a valid HOST.
+#
+#   backlog - The number of pending connections. This refers
+#       to the number of clients that can be waiting to be
+#       served. Exceeding this number results in the client
+#       getting an error when attempting to connect. It should
+#       only affect servers under significant load.
+#
+#       Must be a positive integer. Generally set in the 64-2048
+#       range.
+#
+
+# bind = '0.0.0.0:5000'
+bind = '0.0.0.0:3000'
+backlog = 2048
+
+#
+# Worker processes
+#
+#   workers - The number of worker processes that this server
+#       should keep alive for handling requests.
+#
+#       A positive integer generally in the 2-4 x $(NUM_CORES)
+#       range. You'll want to vary this a bit to find the best
+#       for your particular application's work load.
+#
+#   worker_class - The type of workers to use. The default
+#       sync class should handle most 'normal' types of work
+#       loads. You'll want to read
+#       http://docs.gunicorn.org/en/latest/design.html#choosing-a-worker-type
+#       for information on when you might want to choose one
+#       of the other worker classes.
+#
+#       A string referring to a Python path to a subclass of
+#       gunicorn.workers.base.Worker. The default provided values
+#       can be seen at
+#       http://docs.gunicorn.org/en/latest/settings.html#worker-class
+#
+#   worker_connections - For the eventlet and gevent worker classes
+#       this limits the maximum number of simultaneous clients that
+#       a single process can handle.
+#
+#       A positive integer generally set to around 1000.
+#
+#   timeout - If a worker does not notify the master process in this
+#       number of seconds it is killed and a new worker is spawned
+#       to replace it.
+#
+#       Generally set to thirty seconds. Only set this noticeably
+#       higher if you're sure of the repercussions for sync workers.
+#       For the non sync workers it just means that the worker
+#       process is still communicating and is not tied to the length
+#       of time required to handle a single request.
+#
+#   keepalive - The number of seconds to wait for the next request
+#       on a Keep-Alive HTTP connection.
+#
+#       A positive integer. Generally set in the 1-5 seconds range.
+#
+
+if os.getenv('GUNICORN_WORKERS', None):
+    workers = int(os.getenv('GUNICORN_WORKERS'))
+else:
+    cores = multiprocessing.cpu_count()
+    workers = cores * 2 + 1
+worker_connections = 1000
+timeout = 240
+keepalive = 2
+
+#
+#   spew - Install a trace function that spews every line of Python
+#       that is executed when running the server. This is the
+#       nuclear option.
+#
+#       True or False
+#
+
+spew = False
+
+#
+# Server mechanics
+#
+#   daemon - Detach the main Gunicorn process from the controlling
+#       terminal with a standard fork/fork sequence.
+#
+#       True or False
+#
+#   raw_env - Pass environment variables to the execution environment.
+#
+#   pidfile - The path to a pid file to write
+#
+#       A path string or None to not write a pid file.
+#
+#   user - Switch worker processes to run as this user.
+#
+#       A valid user id (as an integer) or the name of a user that
+#       can be retrieved with a call to pwd.getpwnam(value) or None
+#       to not change the worker process user.
+#
+#   group - Switch worker process to run as this group.
+#
+#       A valid group id (as an integer) or the name of a user that
+#       can be retrieved with a call to pwd.getgrnam(value) or None
+#       to change the worker processes group.
+#
+#   umask - A mask for file permissions written by Gunicorn. Note that
+#       this affects unix socket permissions.
+#
+#       A valid value for the os.umask(mode) call or a string
+#       compatible with int(value, 0) (0 means Python guesses
+#       the base, so values like "0", "0xFF", "0022" are valid
+#       for decimal, hex, and octal representations)
+#
+#   tmp_upload_dir - A directory to store temporary request data when
+#       requests are read. This will most likely be disappearing soon.
+#
+#       A path to a directory where the process owner can write. Or
+#       None to signal that Python should choose one on its own.
+#
+
+daemon = False
+raw_env = []
+pidfile = None
+umask = 0
+user = None
+group = None
+tmp_upload_dir = None
+
+#
+#   Logging
+#
+#   logfile - The path to a log file to write to.
+#
+#       A path string. "-" means log to stdout.
+#
+#   loglevel - The granularity of log output
+#
+#       A string of "debug", "info", "warning", "error", "critical"
+#
+
+errorlog = '-'
+loglevel = 'info'
+accesslog = None
+access_log_format = '%(h)s %(l)s %(u)s %(t)s "%(r)s" %(s)s %(b)s "%(f)s" "%(a)s"'
+
+#
+# Process naming
+#
+#   proc_name - A base to use with setproctitle to change the way
+#       that Gunicorn processes are reported in the system process
+#       table. This affects things like 'ps' and 'top'. If you're
+#       going to be running more than one instance of Gunicorn you'll
+#       probably want to set a name to tell them apart. This requires
+#       that you install the setproctitle module.
+#
+#       A string or None to choose a default of something like 'gunicorn'.
+#
+
+proc_name = None
+
+
+#
+# Server hooks
+#
+#   post_fork - Called just after a worker has been forked.
+#
+#       A callable that takes a server and worker instance
+#       as arguments.
+#
+#   pre_fork - Called just prior to forking the worker subprocess.
+#
+#       A callable that accepts the same arguments as after_fork
+#
+#   pre_exec - Called just prior to forking off a secondary
+#       master process during things like config reloading.
+#
+#       A callable that takes a server instance as the sole argument.
+#

pr_agent/settings/pr_evaluate_prompt_response.toml

@@ -40,8 +40,8 @@ After that, rank each response. Criterions to rank each response:
 - How well does the response follow the specific task instructions and requirements?
 - How well does the response analyze and understand the PR code diff?
 - How well will a person perceive it as a good response that correctly addresses the task?
-- How well does the reponse prioritize key feedback, related to the task instructions, that a human reader seeing that feedback would also consider as important?
-- Don't neccessarily rank higher a response that is longer. A shorter response might be better if it is more concise, and still addresses the task better.
+- How well does the response prioritize key feedback, related to the task instructions, that a human reader seeing that feedback would also consider as important?
+- Don't necessarily rank higher a response that is longer. A shorter response might be better if it is more concise, and still addresses the task better.
 
 
 The output must be a YAML object equivalent to type $PRRankRespones, according to the following Pydantic definitions:

pr_agent/settings/pr_reviewer_prompts.toml

@@ -73,7 +73,7 @@ class Review(BaseModel):
     security_concerns: str = Field(description="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 ? Answer 'No' if there are no possible issues. If there are security concerns or issues, start your answer with a short header, such as: 'Sensitive information exposure: ...', 'SQL injection: ...' etc. Explain your answer. Be specific and give examples if possible")
 {%- endif %}
 {%- if require_can_be_split_review %}
-    can_be_split: List[SubPR] = Field(min_items=0, max_items=3, description="Can this PR, which contains {{ num_pr_files }} changed files in total, be divided into smaller sub-PRs with distinct tasks that can be reviewed and merged independently, regardless of the order ? Make sure that the sub-PRs are indeed independent, with no code dependencies between them, and that each sub-PR represent a meaningfull independent task. Output an empty list if the PR code does not needd to be split.")
+    can_be_split: List[SubPR] = Field(min_items=0, max_items=3, description="Can this PR, which contains {{ num_pr_files }} changed files in total, be divided into smaller sub-PRs with distinct tasks that can be reviewed and merged independently, regardless of the order ? Make sure that the sub-PRs are indeed independent, with no code dependencies between them, and that each sub-PR represent a meaningful independent task. Output an empty list if the PR code does not need to be split.")
 {%- endif %}
 {%- if num_code_suggestions > 0 %}
 

requirements.txt

@@ -24,6 +24,7 @@ tiktoken==0.7.0
 ujson==5.8.0
 uvicorn==0.22.0
 tenacity==8.2.3
+gunicorn==20.1.0
 # Uncomment the following lines to enable the 'similar issue' tool
 # pinecone-client
 # pinecone-datasets @ git+https://github.com/mrT23/pinecone-datasets.git@main