xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-04 21:00:40 +08:00
Code Issues Packages Projects Releases Wiki Activity

refine /add_docs

Browse Source
This commit is contained in:
Hussam.lawen
2023-09-28 20:11:18 +03:00
parent c3cbaaf09e
commit bb8a0f10f4
2 changed files with 50 additions and 125 deletions
Download Patch File Download Diff File Expand all files Collapse all files

51
pr_agent/settings/pr_add_docs.toml
View File

@ -1,6 +1,6 @@
[pr_add_docs_prompt] [pr_add_docs_prompt]
system="""You are a language model called PR-Code-Documentation Agent, that specializes in documenting code. system="""You are a language model called PR-Code-Documentation Agent, that specializes in generating documentation for code.
Your task is to provide meaningfull {{ docs_for_language }} in a PR (the '+' lines). Your task is to generate meaningfull {{ docs_for_language }} to a PR (the '+' lines).
Example for a PR Diff input: Example for a PR Diff input:
' '
@ -31,16 +31,12 @@ __old hunk__
' '
Specific instructions: Specific instructions:
- Try to identify edited/added code components (classes/functions/methods...) that are undocumented, generate {{ docs_for_language }} for each one of the edited/added code components. - Try to identify edited/added code components (classes/functions/methods...) that are undocumented. and generate {{ docs_for_language }} for each one.
- If there are no edited/added code components, don't generate {{ docs_for_language }} for the edited/added code lines. - If there are edited/added code components, but they are already documented, ignore them.
- If there are edited/added code components, but they are already documented, don't generate {{ docs_for_language }} for the edited/added code lines. - 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. - 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. - The {{ docs_for_language }} should be in standard format.
- Execpt of the {{ docs_for_language }}, the new code should be identical to the original code snippet. Keep existing code comments, line comments, blank lines, formatting, etc. - Provide the exact line number (inclusive) where the {{ docs_for_language }} should be added.
- Documentation should refer only to the 'new hunk' code, and focus on improving the new added code lines, with '+'.
- Provide the exact line number range (inclusive) for each issue.
- Assume there is additional code in the relevant file that is not included in the diff.
- Don't output line numbers in the 'documented code' snippets.
{%- if extra_instructions %} {%- if extra_instructions %}
@ -51,45 +47,34 @@ Extra instructions from the user:
You must use the following YAML schema to format your answer: You must use the following YAML schema to format your answer:
```yaml ```yaml
Code suggestions: Code Documentation:
type: array type: array
uniqueItems: true uniqueItems: true
items: items:
relevant file: relevant file:
type: string type: string
description: the relevant file full path description: the relevant file full path
existing code: relevant line:
type: string
description: |-
a code snippet showing the relevant code lines from a '__new hunk__' section.
It must be contiguous, correctly formatted and indented, and without line numbers.
relevant lines start:
type: integer type: integer
description: |- description: |-
The relevant line number from a '__new hunk__' section where the suggestion starts (inclusive). The relevant line number from a '__new hunk__' section where the {{ docs_for_language }} should be added.
Should be derived from the hunk line numbers, and correspond to the 'existing code' snippet above. documentation:
relevant lines end:
type: integer
description: |-
The relevant line number from a '__new hunk__' section where the suggestion ends (inclusive).
Should be derived from the hunk line numbers, and correspond to the 'existing code' snippet above.
documented code:
type: string type: string
description: |- description: |-
a new code snippet that can be used to replace the relevant lines in '__new hunk__' code. The {{ docs_for_language }} content. It should be complete, correctly formatted and indented, and without line numbers.
{{ language }} {{ docs_for_language }} Replacement {{ language }} {{ docs_for_language }} should be complete, correctly formatted and indented, and without line numbers.
``` ```
Example output: Example output:
```yaml ```yaml
Code suggestions: Code Documentation:
- relevant file: |- - relevant file: |-
src/file1.py src/file1.py
existing code: |- relevant lines: 12
def func1(): documentation: |-
relevant lines start: 12 \"\"\"
relevant lines end: 12 This is a python docstring for func1.
documented code: |- \"\"\"
- ...
... ...
``` ```

116
pr_agent/tools/pr_add_docs.py
View File

@ -68,25 +68,20 @@ class PRAddDocs:
logging.info('Preparing PR review...') logging.info('Preparing PR review...')
if not self.is_extended: if not self.is_extended:
await retry_with_fallback_models(self._prepare_prediction) await retry_with_fallback_models(self._prepare_prediction)
data = self._prepare_pr_code_suggestions() data = self._prepare_pr_code_docs()
else: else:
data = await retry_with_fallback_models(self._prepare_prediction_extended) data = await retry_with_fallback_models(self._prepare_prediction_extended)
if (not data) or (not 'Code suggestions' in data): if (not data) or (not 'Code Documentation' in data):
logging.info('No code suggestions found for PR.') logging.info('No code documentation found for PR.')
return return
if (not self.is_extended and get_settings().pr_code_suggestions.rank_suggestions) or \
(self.is_extended and get_settings().pr_code_suggestions.rank_extended_suggestions):
logging.info('Ranking Suggestions...')
data['Code suggestions'] = await self.rank_suggestions(data['Code suggestions'])
if get_settings().config.publish_output: if get_settings().config.publish_output:
logging.info('Pushing PR review...') logging.info('Pushing PR review...')
self.git_provider.remove_initial_comment() self.git_provider.remove_initial_comment()
logging.info('Pushing inline code suggestions...') logging.info('Pushing inline code documentation...')
self.push_inline_code_suggestions(data) self.push_inline_docs_suggestions(data)
except Exception as e: except Exception as e:
logging.error(f"Failed to generate code suggestions for PR, error: {e}") logging.error(f"Failed to generate code documentation for PR, error: {e}")
async def _prepare_prediction(self, model: str): async def _prepare_prediction(self, model: str):
logging.info('Getting PR diff...') logging.info('Getting PR diff...')
@ -113,47 +108,44 @@ class PRAddDocs:
return response return response
def _prepare_pr_code_suggestions(self) -> Dict: def _prepare_pr_code_docs(self) -> Dict:
review = self.prediction.strip() review = self.prediction.strip()
data = load_yaml(review) data = load_yaml(review)
if isinstance(data, list): if isinstance(data, list):
data = {'Code suggestions': data} data = {'Code Documentation': data}
return data return data
def push_inline_code_suggestions(self, data): def push_inline_docs_suggestions(self, data):
code_suggestions = [] code_suggestions = []
if not data['Code suggestions']: if not data['Code Documentation']:
return self.git_provider.publish_comment('No suggestions found to improve this PR.') return self.git_provider.publish_comment('No code documentation found to improve this PR.')
for d in data['Code suggestions']: for d in data['Code Documentation']:
try: try:
if get_settings().config.verbosity_level >= 2: if get_settings().config.verbosity_level >= 2:
logging.info(f"suggestion: {d}") logging.info(f"add_docs: {d}")
relevant_file = d['relevant file'].strip() relevant_file = d['relevant file'].strip()
relevant_lines_start = int(d['relevant lines start']) # absolute position relevant_line = int(d['relevant line']) # absolute position
relevant_lines_end = int(d['relevant lines end']) documentation = d['documentation']
content = d['suggestion content'] if documentation:
new_code_snippet = d['documented code'] new_code_snippet = self.dedent_code(relevant_file, relevant_line, documentation, add_original_line=True)
if new_code_snippet: body = f"**Suggestion:** Proposed documentation\n```suggestion\n" + new_code_snippet + "\n```"
new_code_snippet = self.dedent_code(relevant_file, relevant_lines_start, new_code_snippet)
body = f"**Suggestion:** {content}\n```suggestion\n" + new_code_snippet + "\n```"
code_suggestions.append({'body': body, 'relevant_file': relevant_file, code_suggestions.append({'body': body, 'relevant_file': relevant_file,
'relevant_lines_start': relevant_lines_start, 'relevant_lines_start': relevant_line,
'relevant_lines_end': relevant_lines_end}) 'relevant_lines_end': relevant_line})
except Exception: except Exception:
if get_settings().config.verbosity_level >= 2: if get_settings().config.verbosity_level >= 2:
logging.info(f"Could not parse suggestion: {d}") logging.info(f"Could not parse code docs: {d}")
is_successful = self.git_provider.publish_code_suggestions(code_suggestions) is_successful = self.git_provider.publish_code_suggestions(code_suggestions)
if not is_successful: if not is_successful:
logging.info("Failed to publish code suggestions, trying to publish each suggestion separately") logging.info("Failed to publish code docs, trying to publish each docs separately")
for code_suggestion in code_suggestions: for code_suggestion in code_suggestions:
self.git_provider.publish_code_suggestions([code_suggestion]) self.git_provider.publish_code_suggestions([code_suggestion])
def dedent_code(self, relevant_file, relevant_lines_start, new_code_snippet): def dedent_code(self, relevant_file, relevant_lines_start, new_code_snippet, add_original_line=False):
try: # dedent code snippet try: # dedent code snippet
self.diff_files = self.git_provider.diff_files if self.git_provider.diff_files \ self.diff_files = self.git_provider.diff_files if self.git_provider.diff_files \
else self.git_provider.get_diff_files() else self.git_provider.get_diff_files()
@ -169,6 +161,8 @@ class PRAddDocs:
delta_spaces = original_initial_spaces - suggested_initial_spaces delta_spaces = original_initial_spaces - suggested_initial_spaces
if delta_spaces > 0: if delta_spaces > 0:
new_code_snippet = textwrap.indent(new_code_snippet, delta_spaces * " ").rstrip('\n') new_code_snippet = textwrap.indent(new_code_snippet, delta_spaces * " ").rstrip('\n')
if add_original_line:
new_code_snippet = original_initial_line + "\n" + new_code_snippet
except Exception as e: except Exception as e:
if get_settings().config.verbosity_level >= 2: if get_settings().config.verbosity_level >= 2:
logging.info(f"Could not dedent code snippet for file {relevant_file}, error: {e}") logging.info(f"Could not dedent code snippet for file {relevant_file}, error: {e}")
@ -192,64 +186,10 @@ class PRAddDocs:
data = {} data = {}
for prediction in prediction_list: for prediction in prediction_list:
self.prediction = prediction self.prediction = prediction
data_per_chunk = self._prepare_pr_code_suggestions() data_per_chunk = self._prepare_pr_code_docs()
if "Code suggestions" in data: if "Code Documentation" in data:
data["Code suggestions"].extend(data_per_chunk["Code suggestions"]) data["Code Documentation"].extend(data_per_chunk["Code Documentation"])
else: else:
data.update(data_per_chunk) data.update(data_per_chunk)
self.data = data self.data = data
return data return data
async def rank_suggestions(self, data: List) -> List:
"""
Call a model to rank (sort) code suggestions based on their importance order.
Args:
data (List): A list of code suggestions to be ranked.
Returns:
List: The ranked list of code suggestions.
"""
suggestion_list = []
# remove invalid suggestions
for i, suggestion in enumerate(data):
if suggestion['existing code'] != suggestion['improved code']:
suggestion_list.append(suggestion)
data_sorted = [[]] * len(suggestion_list)
try:
suggestion_str = ""
for i, suggestion in enumerate(suggestion_list):
suggestion_str += f"suggestion {i + 1}: " + str(suggestion) + '\n\n'
variables = {'suggestion_list': suggestion_list, 'suggestion_str': suggestion_str}
model = get_settings().config.model
environment = Environment(undefined=StrictUndefined)
system_prompt = environment.from_string(get_settings().pr_sort_code_suggestions_prompt.system).render(
variables)
user_prompt = environment.from_string(get_settings().pr_sort_code_suggestions_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, system=system_prompt,
user=user_prompt)
sort_order = load_yaml(response)
for s in sort_order['Sort Order']:
suggestion_number = s['suggestion number']
importance_order = s['importance order']
data_sorted[importance_order - 1] = suggestion_list[suggestion_number - 1]
if get_settings().pr_code_suggestions.final_clip_factor != 1:
new_len = int(0.5 + len(data_sorted) * get_settings().pr_code_suggestions.final_clip_factor)
data_sorted = data_sorted[:new_len]
except Exception as e:
if get_settings().config.verbosity_level >= 1:
logging.info(f"Could not sort suggestions, error: {e}")
data_sorted = suggestion_list
return data_sorted