mirror of
https://github.com/qodo-ai/pr-agent.git
synced 2025-07-10 15:50:37 +08:00
Merge branch 'main' into feature/gha-outputs-1
This commit is contained in:
@ -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,
|
||||
|
@ -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):
|
||||
@ -150,4 +153,4 @@ 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
|
||||
|
@ -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)
|
||||
|
||||
|
@ -13,7 +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
|
||||
@ -567,7 +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
|
||||
@ -576,7 +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}")
|
||||
|
@ -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:
|
||||
"""
|
||||
|
@ -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 {}
|
||||
|
@ -103,6 +103,8 @@ 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":
|
||||
|
@ -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)
|
||||
- ...
|
||||
|
@ -52,7 +52,6 @@ maximal_review_effort=5
|
||||
|
||||
[pr_description] # /describe #
|
||||
publish_labels=true
|
||||
publish_description_as_comment=false
|
||||
add_original_user_description=true
|
||||
keep_original_user_title=true
|
||||
use_bullet_points=true
|
||||
@ -61,6 +60,9 @@ enable_pr_type=true
|
||||
final_update_message = true
|
||||
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 +112,11 @@ 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
|
||||
|
@ -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
|
||||
|
@ -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)
|
||||
|
||||
|
@ -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:
|
||||
|
@ -358,6 +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:
|
||||
|
Reference in New Issue
Block a user