Merge pull request #337 from Codium-ai/hl/add_docs

Add code documentations in PR
This commit is contained in:
mrT23
2023-10-02 10:55:36 +03:00
committed by GitHub
10 changed files with 315 additions and 2 deletions

View File

@ -28,7 +28,8 @@ CodiumAI `PR-Agent` is an open-source tool aiming to help developers review pull
**Update Changelog ([`/update_changelog`](./docs/UPDATE_CHANGELOG.md))**: Automatically updating the CHANGELOG.md file with the PR changes.
\
**Find similar issue ([`/similar_issue`](./docs/SIMILAR_ISSUE.md))**: Automatically retrieves and presents similar issues
\
**Add Documentation (`/add_docs`)**: Automatically adds [documentation](./docs/ADD_DOCUMENTATION.md) 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.
@ -111,6 +112,7 @@ See the [Release notes](./RELEASE_NOTES.md) for updates on the latest changes.
| | 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: | | | | | |
| | 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: | | | |
@ -197,7 +199,7 @@ 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)
- [ ] Documentation (is the PR properly documented)
- [x] Documentation (is the PR properly documented)
- [ ] ...
## Similar Projects

15
docs/ADD_DOCUMENTATION.md Normal file
View File

@ -0,0 +1,15 @@
# 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 ...".

View File

@ -5,5 +5,6 @@
- [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.

BIN
pics/add_docs.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 325 KiB

BIN
pics/add_docs_comment.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 51 KiB

View File

@ -6,6 +6,7 @@ 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
@ -32,6 +33,7 @@ command2class = {
"config": PRConfig,
"settings": PRConfig,
"similar_issue": PRSimilarIssue,
"add_docs": PRAddDocs,
}
commands = list(command2class.keys())

View File

@ -22,6 +22,7 @@ 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"
]]
)

View File

@ -47,6 +47,10 @@ 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 = ""

View File

@ -0,0 +1,115 @@
[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
"""

View File

@ -0,0 +1,173 @@
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=True)
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"