First MVP
This commit is contained in:
3
src/gitea_codex_bot/__init__.py
Normal file
3
src/gitea_codex_bot/__init__.py
Normal file
@@ -0,0 +1,3 @@
|
||||
__all__ = ["__version__"]
|
||||
|
||||
__version__ = "0.1.0"
|
||||
0
src/gitea_codex_bot/api/__init__.py
Normal file
0
src/gitea_codex_bot/api/__init__.py
Normal file
64
src/gitea_codex_bot/config.py
Normal file
64
src/gitea_codex_bot/config.py
Normal file
@@ -0,0 +1,64 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from functools import lru_cache
|
||||
from typing import Literal
|
||||
|
||||
from pydantic import Field, SecretStr, field_validator
|
||||
from pydantic_settings import BaseSettings, SettingsConfigDict
|
||||
|
||||
|
||||
class Settings(BaseSettings):
|
||||
model_config = SettingsConfigDict(env_file=".env", env_file_encoding="utf-8", extra="ignore")
|
||||
|
||||
gitea_base_url: str = Field(alias="GITEA_BASE_URL")
|
||||
gitea_token: SecretStr = Field(alias="GITEA_TOKEN")
|
||||
gitea_bot_username: str = Field(alias="GITEA_BOT_USERNAME")
|
||||
gitea_webhook_secret: SecretStr = Field(alias="GITEA_WEBHOOK_SECRET")
|
||||
|
||||
openai_api_key: SecretStr = Field(alias="OPENAI_API_KEY")
|
||||
openai_project_id: str | None = Field(default=None, alias="OPENAI_PROJECT_ID")
|
||||
openai_org_id: str | None = Field(default=None, alias="OPENAI_ORG_ID")
|
||||
openai_review_model: str = Field(default="gpt-5.3-codex", alias="OPENAI_REVIEW_MODEL")
|
||||
openai_reasoning_effort: Literal["none", "low", "medium", "high"] = Field(default="high", alias="OPENAI_REASONING_EFFORT")
|
||||
|
||||
allowed_repos: str = Field(alias="ALLOWED_REPOS")
|
||||
cooldown_seconds: int = Field(default=60, alias="COOLDOWN_SECONDS")
|
||||
webhook_mode: Literal["repo", "global"] = Field(default="repo", alias="WEBHOOK_MODE")
|
||||
|
||||
db_host: str = Field(alias="DB_HOST")
|
||||
db_port: int = Field(default=3306, alias="DB_PORT")
|
||||
db_name: str = Field(alias="DB_NAME")
|
||||
db_user: str = Field(alias="DB_USER")
|
||||
db_password: SecretStr = Field(alias="DB_PASSWORD")
|
||||
database_url: str | None = Field(default=None, alias="DATABASE_URL")
|
||||
|
||||
workdir: str = Field(default="/var/lib/gitea-codex/worktrees", alias="WORKDIR")
|
||||
max_diff_bytes: int = Field(default=200000, alias="MAX_DIFF_BYTES")
|
||||
max_review_minutes: int = Field(default=10, alias="MAX_REVIEW_MINUTES")
|
||||
concurrency: int = Field(default=1, alias="CONCURRENCY")
|
||||
|
||||
review_runner_image: str = Field(default="node:22-bookworm-slim", alias="REVIEW_RUNNER_IMAGE")
|
||||
enable_fix_commands: bool = Field(default=False, alias="ENABLE_FIX_COMMANDS")
|
||||
allow_untrusted_forks: bool = Field(default=False, alias="ALLOW_UNTRUSTED_FORKS")
|
||||
|
||||
@field_validator("gitea_base_url")
|
||||
@classmethod
|
||||
def normalize_base_url(cls, value: str) -> str:
|
||||
return value.rstrip("/")
|
||||
|
||||
@property
|
||||
def sqlalchemy_url(self) -> str:
|
||||
if self.database_url:
|
||||
return self.database_url
|
||||
password = self.db_password.get_secret_value()
|
||||
return f"mysql+pymysql://{self.db_user}:{password}@{self.db_host}:{self.db_port}/{self.db_name}?charset=utf8mb4"
|
||||
|
||||
@property
|
||||
def allowed_repo_set(self) -> set[str]:
|
||||
values = [item.strip() for item in self.allowed_repos.split(",")]
|
||||
return {value for value in values if value}
|
||||
|
||||
|
||||
@lru_cache(maxsize=1)
|
||||
def get_settings() -> Settings:
|
||||
return Settings()
|
||||
32
src/gitea_codex_bot/db.py
Normal file
32
src/gitea_codex_bot/db.py
Normal file
@@ -0,0 +1,32 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from collections.abc import Generator
|
||||
from functools import lru_cache
|
||||
|
||||
from sqlalchemy import create_engine
|
||||
from sqlalchemy.orm import DeclarativeBase, Session, sessionmaker
|
||||
|
||||
from gitea_codex_bot.config import get_settings
|
||||
|
||||
|
||||
class Base(DeclarativeBase):
|
||||
pass
|
||||
|
||||
|
||||
@lru_cache(maxsize=1)
|
||||
def get_engine():
|
||||
settings = get_settings()
|
||||
return create_engine(settings.sqlalchemy_url, pool_pre_ping=True, future=True)
|
||||
|
||||
|
||||
@lru_cache(maxsize=1)
|
||||
def get_session_factory():
|
||||
return sessionmaker(bind=get_engine(), class_=Session, autoflush=False, autocommit=False, expire_on_commit=False)
|
||||
|
||||
|
||||
def get_session() -> Generator[Session, None, None]:
|
||||
session = get_session_factory()()
|
||||
try:
|
||||
yield session
|
||||
finally:
|
||||
session.close()
|
||||
175
src/gitea_codex_bot/main.py
Normal file
175
src/gitea_codex_bot/main.py
Normal file
@@ -0,0 +1,175 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import logging
|
||||
from contextlib import asynccontextmanager
|
||||
from typing import Any
|
||||
|
||||
from fastapi import Depends, FastAPI, Header, HTTPException, Request, status
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from gitea_codex_bot.config import Settings, get_settings
|
||||
from gitea_codex_bot.db import Base, get_engine, get_session
|
||||
from gitea_codex_bot.services.commands import parse_command
|
||||
from gitea_codex_bot.services.gitea import GiteaClient
|
||||
from gitea_codex_bot.services.jobs import cooldown_remaining_seconds, enqueue_job, persist_webhook_event
|
||||
from gitea_codex_bot.services.review_format import (
|
||||
format_cooldown_ack,
|
||||
format_queue_ack,
|
||||
format_unsupported_ack,
|
||||
)
|
||||
from gitea_codex_bot.services.security import verify_gitea_signature
|
||||
from gitea_codex_bot.workers.dispatcher import worker_loop
|
||||
|
||||
logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(name)s %(message)s")
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def _validate_required_env(settings: Settings) -> None:
|
||||
if not settings.openai_api_key.get_secret_value().strip():
|
||||
raise RuntimeError("OPENAI_API_KEY is required")
|
||||
|
||||
|
||||
def _extract_pr_event(payload: dict[str, Any], event_name: str) -> tuple[str, int, str, int, str] | None:
|
||||
repository = payload.get("repository", {})
|
||||
repo = repository.get("full_name")
|
||||
if not repo:
|
||||
return None
|
||||
sender = payload.get("sender", {})
|
||||
sender_username = sender.get("username", "")
|
||||
comment = payload.get("comment", {})
|
||||
comment_id = int(comment.get("id", 0) or 0)
|
||||
if comment_id <= 0:
|
||||
return None
|
||||
|
||||
if event_name == "issue_comment":
|
||||
issue = payload.get("issue", {})
|
||||
if not issue.get("pull_request"):
|
||||
return None
|
||||
pr_number = int(issue.get("number", 0) or 0)
|
||||
head_sha = payload.get("pull_request", {}).get("head", {}).get("sha", "")
|
||||
elif event_name == "pull_request_comment":
|
||||
pull_request = payload.get("pull_request", {})
|
||||
if not pull_request:
|
||||
return None
|
||||
pr_number = int(pull_request.get("number", 0) or 0)
|
||||
head_sha = pull_request.get("head", {}).get("sha", "")
|
||||
else:
|
||||
return None
|
||||
|
||||
if pr_number <= 0:
|
||||
return None
|
||||
if not head_sha:
|
||||
head_sha = "unknown"
|
||||
return repo, pr_number, head_sha, comment_id, sender_username
|
||||
|
||||
|
||||
@asynccontextmanager
|
||||
async def lifespan(app: FastAPI):
|
||||
settings = get_settings()
|
||||
_validate_required_env(settings)
|
||||
Base.metadata.create_all(bind=get_engine())
|
||||
|
||||
stop_event = asyncio.Event()
|
||||
task = asyncio.create_task(worker_loop(settings, stop_event))
|
||||
app.state.worker_stop_event = stop_event
|
||||
app.state.worker_task = task
|
||||
try:
|
||||
yield
|
||||
finally:
|
||||
stop_event.set()
|
||||
await task
|
||||
|
||||
|
||||
app = FastAPI(title="Gitea Codex Review Bot", lifespan=lifespan)
|
||||
|
||||
|
||||
@app.get("/healthz")
|
||||
def healthz(settings: Settings = Depends(get_settings)) -> dict[str, str]:
|
||||
_ = settings.gitea_base_url
|
||||
return {"status": "ok"}
|
||||
|
||||
|
||||
@app.post("/webhook/gitea")
|
||||
async def gitea_webhook(
|
||||
request: Request,
|
||||
x_gitea_event: str | None = Header(default=None),
|
||||
x_gitea_delivery: str | None = Header(default=None),
|
||||
x_gitea_signature: str | None = Header(default=None),
|
||||
session: Session = Depends(get_session),
|
||||
settings: Settings = Depends(get_settings),
|
||||
) -> dict[str, Any]:
|
||||
payload_bytes = await request.body()
|
||||
if not verify_gitea_signature(payload_bytes, settings.gitea_webhook_secret.get_secret_value(), x_gitea_signature):
|
||||
raise HTTPException(status_code=status.HTTP_401_UNAUTHORIZED, detail="invalid signature")
|
||||
|
||||
event_name = (x_gitea_event or "").strip()
|
||||
if event_name not in {"issue_comment", "pull_request_comment"}:
|
||||
return {"accepted": False, "reason": "event ignored"}
|
||||
|
||||
payload = await request.json()
|
||||
extracted = _extract_pr_event(payload, event_name)
|
||||
if not extracted:
|
||||
return {"accepted": False, "reason": "not a pull request comment"}
|
||||
repo, pr_number, head_sha, comment_id, sender_username = extracted
|
||||
|
||||
if sender_username == settings.gitea_bot_username:
|
||||
return {"accepted": False, "reason": "bot comment ignored"}
|
||||
|
||||
comment_body = str(payload.get("comment", {}).get("body", "")).strip()
|
||||
parsed_command = parse_command(comment_body)
|
||||
if not parsed_command:
|
||||
return {"accepted": False, "reason": "no codex command"}
|
||||
|
||||
if repo not in settings.allowed_repo_set:
|
||||
return {"accepted": False, "reason": "repo not allowed"}
|
||||
|
||||
inserted = persist_webhook_event(
|
||||
session,
|
||||
delivery_id=x_gitea_delivery,
|
||||
event_name=event_name,
|
||||
repo=repo,
|
||||
comment_id=comment_id,
|
||||
payload=payload_bytes,
|
||||
)
|
||||
if not inserted:
|
||||
return {"accepted": True, "reason": "duplicate event"}
|
||||
|
||||
gitea = GiteaClient(settings)
|
||||
if parsed_command.name in {"review", "rerun"}:
|
||||
if head_sha == "unknown":
|
||||
try:
|
||||
head_sha = gitea.get_pull_request(repo, pr_number).head_sha
|
||||
except Exception:
|
||||
pass
|
||||
if parsed_command.name != "rerun":
|
||||
remaining = cooldown_remaining_seconds(session, repo, pr_number, settings.cooldown_seconds)
|
||||
if remaining > 0:
|
||||
gitea.post_issue_comment(repo, pr_number, format_cooldown_ack(remaining))
|
||||
return {"accepted": True, "reason": "cooldown active", "cooldown_seconds_remaining": remaining}
|
||||
job = enqueue_job(
|
||||
session,
|
||||
repo=repo,
|
||||
pr_number=pr_number,
|
||||
head_sha=head_sha,
|
||||
trigger_comment_id=comment_id,
|
||||
requested_by=sender_username,
|
||||
command=parsed_command,
|
||||
)
|
||||
gitea.post_issue_comment(repo, pr_number, format_queue_ack(head_sha))
|
||||
return {"accepted": True, "job_id": job.id, "status": "queued"}
|
||||
|
||||
if parsed_command.name in {"fix", "explain", "ignore"}:
|
||||
job = enqueue_job(
|
||||
session,
|
||||
repo=repo,
|
||||
pr_number=pr_number,
|
||||
head_sha=head_sha,
|
||||
trigger_comment_id=comment_id,
|
||||
requested_by=sender_username,
|
||||
command=parsed_command,
|
||||
)
|
||||
return {"accepted": True, "job_id": job.id, "status": "queued"}
|
||||
|
||||
gitea.post_issue_comment(repo, pr_number, format_unsupported_ack(parsed_command))
|
||||
return {"accepted": False, "reason": "unsupported command"}
|
||||
113
src/gitea_codex_bot/models.py
Normal file
113
src/gitea_codex_bot/models.py
Normal file
@@ -0,0 +1,113 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import enum
|
||||
from datetime import datetime
|
||||
|
||||
from sqlalchemy import DateTime, Enum, ForeignKey, Index, Integer, JSON, String, Text, UniqueConstraint, func
|
||||
from sqlalchemy.orm import Mapped, mapped_column, relationship
|
||||
|
||||
from gitea_codex_bot.db import Base
|
||||
|
||||
|
||||
class JobStatus(str, enum.Enum):
|
||||
queued = "queued"
|
||||
running = "running"
|
||||
succeeded = "succeeded"
|
||||
failed = "failed"
|
||||
skipped = "skipped"
|
||||
|
||||
|
||||
class RunStatus(str, enum.Enum):
|
||||
running = "running"
|
||||
succeeded = "succeeded"
|
||||
failed = "failed"
|
||||
skipped = "skipped"
|
||||
|
||||
|
||||
class WebhookEvent(Base):
|
||||
__tablename__ = "webhook_events"
|
||||
|
||||
id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
|
||||
delivery_id: Mapped[str | None] = mapped_column(String(255), nullable=True)
|
||||
event_name: Mapped[str] = mapped_column(String(128), nullable=False)
|
||||
repo: Mapped[str] = mapped_column(String(255), nullable=False)
|
||||
comment_id: Mapped[int | None] = mapped_column(Integer, nullable=True)
|
||||
payload_sha256: Mapped[str] = mapped_column(String(64), nullable=False)
|
||||
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False, server_default=func.now())
|
||||
|
||||
__table_args__ = (
|
||||
UniqueConstraint("delivery_id", name="uq_webhook_events_delivery_id"),
|
||||
UniqueConstraint("repo", "comment_id", name="uq_webhook_events_repo_comment"),
|
||||
)
|
||||
|
||||
|
||||
class ReviewJob(Base):
|
||||
__tablename__ = "review_jobs"
|
||||
|
||||
id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
|
||||
repo: Mapped[str] = mapped_column(String(255), nullable=False)
|
||||
pr_number: Mapped[int] = mapped_column(Integer, nullable=False)
|
||||
head_sha: Mapped[str] = mapped_column(String(64), nullable=False)
|
||||
trigger_comment_id: Mapped[int] = mapped_column(Integer, nullable=False)
|
||||
command: Mapped[str] = mapped_column(String(64), nullable=False, default="review")
|
||||
command_args: Mapped[str | None] = mapped_column(Text, nullable=True)
|
||||
requested_by: Mapped[str] = mapped_column(String(255), nullable=False)
|
||||
status: Mapped[JobStatus] = mapped_column(Enum(JobStatus), nullable=False, default=JobStatus.queued)
|
||||
last_error: Mapped[str | None] = mapped_column(Text, nullable=True)
|
||||
result_json: Mapped[dict | None] = mapped_column(JSON, nullable=True)
|
||||
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False, server_default=func.now())
|
||||
updated_at: Mapped[datetime] = mapped_column(
|
||||
DateTime(timezone=True),
|
||||
nullable=False,
|
||||
server_default=func.now(),
|
||||
onupdate=func.now(),
|
||||
)
|
||||
started_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True)
|
||||
finished_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True)
|
||||
|
||||
runs: Mapped[list["ReviewRun"]] = relationship(back_populates="job", cascade="all, delete-orphan")
|
||||
|
||||
__table_args__ = (
|
||||
Index("ix_review_jobs_lookup", "repo", "pr_number", "head_sha", "status", "created_at"),
|
||||
UniqueConstraint("repo", "trigger_comment_id", name="uq_review_jobs_repo_trigger_comment"),
|
||||
)
|
||||
|
||||
|
||||
class ReviewRun(Base):
|
||||
__tablename__ = "review_runs"
|
||||
|
||||
id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
|
||||
job_id: Mapped[int] = mapped_column(ForeignKey("review_jobs.id", ondelete="CASCADE"), nullable=False)
|
||||
status: Mapped[RunStatus] = mapped_column(Enum(RunStatus), nullable=False, default=RunStatus.running)
|
||||
runner_container_id: Mapped[str | None] = mapped_column(String(128), nullable=True)
|
||||
result_json: Mapped[dict | None] = mapped_column(JSON, nullable=True)
|
||||
error_message: Mapped[str | None] = mapped_column(Text, nullable=True)
|
||||
started_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False, server_default=func.now())
|
||||
finished_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True)
|
||||
|
||||
job: Mapped["ReviewJob"] = relationship(back_populates="runs")
|
||||
|
||||
__table_args__ = (Index("ix_review_runs_job_status", "job_id", "status"),)
|
||||
|
||||
|
||||
class BotComment(Base):
|
||||
__tablename__ = "bot_comments"
|
||||
|
||||
id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
|
||||
repo: Mapped[str] = mapped_column(String(255), nullable=False)
|
||||
pr_number: Mapped[int] = mapped_column(Integer, nullable=False)
|
||||
head_sha: Mapped[str] = mapped_column(String(64), nullable=False)
|
||||
gitea_comment_id: Mapped[int] = mapped_column(Integer, nullable=False)
|
||||
marker: Mapped[str] = mapped_column(String(255), nullable=False)
|
||||
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False, server_default=func.now())
|
||||
updated_at: Mapped[datetime] = mapped_column(
|
||||
DateTime(timezone=True),
|
||||
nullable=False,
|
||||
server_default=func.now(),
|
||||
onupdate=func.now(),
|
||||
)
|
||||
|
||||
__table_args__ = (
|
||||
UniqueConstraint("repo", "pr_number", "marker", name="uq_bot_comments_marker"),
|
||||
Index("ix_bot_comments_repo_pr", "repo", "pr_number"),
|
||||
)
|
||||
0
src/gitea_codex_bot/services/__init__.py
Normal file
0
src/gitea_codex_bot/services/__init__.py
Normal file
30
src/gitea_codex_bot/services/commands.py
Normal file
30
src/gitea_codex_bot/services/commands.py
Normal file
@@ -0,0 +1,30 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
|
||||
from gitea_codex_bot.types import ParsedCommand
|
||||
|
||||
COMMAND_RE = re.compile(r"^@codex\s+(review|explain|fix|ignore|rerun)\b(.*)$", re.IGNORECASE | re.DOTALL)
|
||||
|
||||
|
||||
def parse_command(body: str) -> ParsedCommand | None:
|
||||
stripped = body.strip()
|
||||
match = COMMAND_RE.match(stripped)
|
||||
if not match:
|
||||
return None
|
||||
name = match.group(1).lower()
|
||||
rest = match.group(2).strip()
|
||||
tokens = [token for token in rest.split() if token]
|
||||
|
||||
parsed = ParsedCommand(name=name, raw=stripped, arguments=tokens)
|
||||
if name == "review":
|
||||
if "--full" in tokens:
|
||||
parsed.full = True
|
||||
parsed.mode = "full"
|
||||
for mode in ("security", "performance", "tests"):
|
||||
if mode in tokens:
|
||||
parsed.mode = mode
|
||||
break
|
||||
elif name == "fix":
|
||||
parsed.branch_fix = "--branch" in tokens
|
||||
return parsed
|
||||
40
src/gitea_codex_bot/services/comments.py
Normal file
40
src/gitea_codex_bot/services/comments.py
Normal file
@@ -0,0 +1,40 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from sqlalchemy import select
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from gitea_codex_bot.models import BotComment
|
||||
|
||||
|
||||
REVIEW_MARKER = "codex-review"
|
||||
|
||||
|
||||
def get_persistent_review_comment_id(session: Session, repo: str, pr_number: int) -> int | None:
|
||||
row = session.execute(
|
||||
select(BotComment)
|
||||
.where(BotComment.repo == repo, BotComment.pr_number == pr_number, BotComment.marker == REVIEW_MARKER)
|
||||
.limit(1)
|
||||
).scalar_one_or_none()
|
||||
return row.gitea_comment_id if row else None
|
||||
|
||||
|
||||
def upsert_persistent_review_comment_id(
|
||||
session: Session,
|
||||
*,
|
||||
repo: str,
|
||||
pr_number: int,
|
||||
head_sha: str,
|
||||
comment_id: int,
|
||||
) -> None:
|
||||
row = session.execute(
|
||||
select(BotComment)
|
||||
.where(BotComment.repo == repo, BotComment.pr_number == pr_number, BotComment.marker == REVIEW_MARKER)
|
||||
.limit(1)
|
||||
).scalar_one_or_none()
|
||||
if not row:
|
||||
row = BotComment(repo=repo, pr_number=pr_number, head_sha=head_sha, gitea_comment_id=comment_id, marker=REVIEW_MARKER)
|
||||
session.add(row)
|
||||
else:
|
||||
row.head_sha = head_sha
|
||||
row.gitea_comment_id = comment_id
|
||||
session.commit()
|
||||
97
src/gitea_codex_bot/services/gitea.py
Normal file
97
src/gitea_codex_bot/services/gitea.py
Normal file
@@ -0,0 +1,97 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from typing import Any
|
||||
from urllib.parse import quote
|
||||
|
||||
import httpx
|
||||
|
||||
from gitea_codex_bot.config import Settings
|
||||
|
||||
|
||||
@dataclass(slots=True)
|
||||
class PullRequestContext:
|
||||
repo: str
|
||||
pr_number: int
|
||||
base_ref: str
|
||||
base_sha: str
|
||||
head_ref: str
|
||||
head_sha: str
|
||||
clone_url: str
|
||||
html_url: str
|
||||
is_fork: bool
|
||||
|
||||
|
||||
class GiteaClient:
|
||||
def __init__(self, settings: Settings) -> None:
|
||||
self.settings = settings
|
||||
self.base_url = settings.gitea_base_url
|
||||
self.headers = {
|
||||
"Authorization": f"token {settings.gitea_token.get_secret_value()}",
|
||||
"Accept": "application/json",
|
||||
"Content-Type": "application/json",
|
||||
}
|
||||
|
||||
def _request(self, method: str, path: str, *, json_body: dict[str, Any] | None = None) -> Any:
|
||||
with httpx.Client(timeout=20.0) as client:
|
||||
response = client.request(
|
||||
method,
|
||||
f"{self.base_url}{path}",
|
||||
headers=self.headers,
|
||||
json=json_body,
|
||||
)
|
||||
response.raise_for_status()
|
||||
if response.status_code == 204:
|
||||
return None
|
||||
return response.json()
|
||||
|
||||
@staticmethod
|
||||
def split_repo(repo: str) -> tuple[str, str]:
|
||||
owner, name = repo.split("/", 1)
|
||||
return owner, name
|
||||
|
||||
def get_pull_request(self, repo: str, pr_number: int) -> PullRequestContext:
|
||||
owner, name = self.split_repo(repo)
|
||||
encoded_owner = quote(owner, safe="")
|
||||
encoded_name = quote(name, safe="")
|
||||
payload = self._request("GET", f"/api/v1/repos/{encoded_owner}/{encoded_name}/pulls/{pr_number}")
|
||||
return PullRequestContext(
|
||||
repo=repo,
|
||||
pr_number=pr_number,
|
||||
base_ref=payload["base"]["ref"],
|
||||
base_sha=payload["base"]["sha"],
|
||||
head_ref=payload["head"]["ref"],
|
||||
head_sha=payload["head"]["sha"],
|
||||
clone_url=payload["head"]["repo"]["clone_url"],
|
||||
html_url=payload["html_url"],
|
||||
is_fork=bool(payload["head"]["repo"]["full_name"] != payload["base"]["repo"]["full_name"]),
|
||||
)
|
||||
|
||||
def post_issue_comment(self, repo: str, pr_number: int, body: str) -> int:
|
||||
owner, name = self.split_repo(repo)
|
||||
encoded_owner = quote(owner, safe="")
|
||||
encoded_name = quote(name, safe="")
|
||||
payload = self._request(
|
||||
"POST",
|
||||
f"/api/v1/repos/{encoded_owner}/{encoded_name}/issues/{pr_number}/comments",
|
||||
json_body={"body": body},
|
||||
)
|
||||
return int(payload["id"])
|
||||
|
||||
def edit_issue_comment(self, repo: str, comment_id: int, body: str) -> int:
|
||||
owner, name = self.split_repo(repo)
|
||||
encoded_owner = quote(owner, safe="")
|
||||
encoded_name = quote(name, safe="")
|
||||
payload = self._request(
|
||||
"PATCH",
|
||||
f"/api/v1/repos/{encoded_owner}/{encoded_name}/issues/comments/{comment_id}",
|
||||
json_body={"body": body},
|
||||
)
|
||||
return int(payload["id"])
|
||||
|
||||
def list_issue_comments(self, repo: str, pr_number: int) -> list[dict[str, Any]]:
|
||||
owner, name = self.split_repo(repo)
|
||||
encoded_owner = quote(owner, safe="")
|
||||
encoded_name = quote(name, safe="")
|
||||
payload = self._request("GET", f"/api/v1/repos/{encoded_owner}/{encoded_name}/issues/{pr_number}/comments")
|
||||
return list(payload)
|
||||
136
src/gitea_codex_bot/services/jobs.py
Normal file
136
src/gitea_codex_bot/services/jobs.py
Normal file
@@ -0,0 +1,136 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from datetime import datetime, timedelta, timezone
|
||||
|
||||
from sqlalchemy import select
|
||||
from sqlalchemy.exc import IntegrityError
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from gitea_codex_bot.models import JobStatus, ReviewJob, ReviewRun, RunStatus, WebhookEvent
|
||||
from gitea_codex_bot.services.security import payload_digest
|
||||
from gitea_codex_bot.types import ParsedCommand
|
||||
|
||||
|
||||
def persist_webhook_event(
|
||||
session: Session,
|
||||
*,
|
||||
delivery_id: str | None,
|
||||
event_name: str,
|
||||
repo: str,
|
||||
comment_id: int | None,
|
||||
payload: bytes,
|
||||
) -> bool:
|
||||
event = WebhookEvent(
|
||||
delivery_id=delivery_id,
|
||||
event_name=event_name,
|
||||
repo=repo,
|
||||
comment_id=comment_id,
|
||||
payload_sha256=payload_digest(payload),
|
||||
)
|
||||
session.add(event)
|
||||
try:
|
||||
session.commit()
|
||||
return True
|
||||
except IntegrityError:
|
||||
session.rollback()
|
||||
return False
|
||||
|
||||
|
||||
def cooldown_remaining_seconds(session: Session, repo: str, pr_number: int, cooldown_seconds: int) -> int:
|
||||
cutoff = datetime.now(timezone.utc) - timedelta(seconds=cooldown_seconds)
|
||||
row = session.execute(
|
||||
select(ReviewJob)
|
||||
.where(ReviewJob.repo == repo, ReviewJob.pr_number == pr_number, ReviewJob.created_at >= cutoff)
|
||||
.order_by(ReviewJob.created_at.desc())
|
||||
.limit(1)
|
||||
).scalar_one_or_none()
|
||||
if not row:
|
||||
return 0
|
||||
created_at = row.created_at
|
||||
if created_at.tzinfo is None:
|
||||
created_at = created_at.replace(tzinfo=timezone.utc)
|
||||
age = (datetime.now(timezone.utc) - created_at).total_seconds()
|
||||
remaining = int(max(cooldown_seconds - age, 0))
|
||||
return remaining
|
||||
|
||||
|
||||
def enqueue_job(
|
||||
session: Session,
|
||||
*,
|
||||
repo: str,
|
||||
pr_number: int,
|
||||
head_sha: str,
|
||||
trigger_comment_id: int,
|
||||
requested_by: str,
|
||||
command: ParsedCommand,
|
||||
) -> ReviewJob:
|
||||
job = ReviewJob(
|
||||
repo=repo,
|
||||
pr_number=pr_number,
|
||||
head_sha=head_sha,
|
||||
trigger_comment_id=trigger_comment_id,
|
||||
command=command.name,
|
||||
command_args=" ".join(command.arguments) if command.arguments else None,
|
||||
requested_by=requested_by,
|
||||
status=JobStatus.queued,
|
||||
)
|
||||
session.add(job)
|
||||
session.commit()
|
||||
session.refresh(job)
|
||||
return job
|
||||
|
||||
|
||||
def claim_next_job(session: Session) -> ReviewJob | None:
|
||||
job = session.execute(
|
||||
select(ReviewJob).where(ReviewJob.status == JobStatus.queued).order_by(ReviewJob.created_at.asc()).limit(1).with_for_update(skip_locked=True)
|
||||
).scalar_one_or_none()
|
||||
if not job:
|
||||
session.rollback()
|
||||
return None
|
||||
job.status = JobStatus.running
|
||||
job.started_at = datetime.now(timezone.utc)
|
||||
run = ReviewRun(job_id=job.id, status=RunStatus.running)
|
||||
session.add(run)
|
||||
session.commit()
|
||||
session.refresh(job)
|
||||
return job
|
||||
|
||||
|
||||
def finish_job(
|
||||
session: Session,
|
||||
*,
|
||||
job_id: int,
|
||||
success: bool,
|
||||
skipped: bool,
|
||||
result: dict | None,
|
||||
error_message: str | None,
|
||||
) -> None:
|
||||
job = session.get(ReviewJob, job_id)
|
||||
if not job:
|
||||
return
|
||||
latest_run = (
|
||||
session.execute(select(ReviewRun).where(ReviewRun.job_id == job_id).order_by(ReviewRun.id.desc()).limit(1)).scalar_one_or_none()
|
||||
)
|
||||
if skipped:
|
||||
job.status = JobStatus.skipped
|
||||
run_status = RunStatus.skipped
|
||||
elif success:
|
||||
job.status = JobStatus.succeeded
|
||||
run_status = RunStatus.succeeded
|
||||
else:
|
||||
job.status = JobStatus.failed
|
||||
run_status = RunStatus.failed
|
||||
|
||||
now = datetime.now(timezone.utc)
|
||||
job.finished_at = now
|
||||
job.last_error = error_message
|
||||
if result is not None:
|
||||
job.result_json = result
|
||||
|
||||
if latest_run:
|
||||
latest_run.status = run_status
|
||||
latest_run.finished_at = now
|
||||
latest_run.result_json = result
|
||||
latest_run.error_message = error_message
|
||||
|
||||
session.commit()
|
||||
35
src/gitea_codex_bot/services/repo_config.py
Normal file
35
src/gitea_codex_bot/services/repo_config.py
Normal file
@@ -0,0 +1,35 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass, field
|
||||
from pathlib import Path
|
||||
|
||||
import yaml
|
||||
|
||||
|
||||
@dataclass(slots=True)
|
||||
class RepoReviewConfig:
|
||||
enabled: bool = True
|
||||
default_mode: str = "summary"
|
||||
max_diff_bytes: int = 200000
|
||||
include_tests: bool = True
|
||||
focus: list[str] = field(default_factory=lambda: ["correctness", "security", "maintainability"])
|
||||
ignore: list[str] = field(default_factory=list)
|
||||
allow_fix: bool = False
|
||||
|
||||
|
||||
def load_repo_review_config(repo_root: Path) -> RepoReviewConfig:
|
||||
path = repo_root / ".codex-review.yml"
|
||||
if not path.exists():
|
||||
return RepoReviewConfig()
|
||||
raw = yaml.safe_load(path.read_text(encoding="utf-8")) or {}
|
||||
review = raw.get("review", {}) or {}
|
||||
commands = raw.get("commands", {}) or {}
|
||||
return RepoReviewConfig(
|
||||
enabled=bool(raw.get("enabled", True)),
|
||||
default_mode=str(review.get("default_mode", "summary")),
|
||||
max_diff_bytes=int(review.get("max_diff_bytes", 200000)),
|
||||
include_tests=bool(review.get("include_tests", True)),
|
||||
focus=list(review.get("focus", ["correctness", "security", "maintainability"])),
|
||||
ignore=list(raw.get("ignore", [])),
|
||||
allow_fix=bool(commands.get("allow_fix", False)),
|
||||
)
|
||||
50
src/gitea_codex_bot/services/review_format.py
Normal file
50
src/gitea_codex_bot/services/review_format.py
Normal file
@@ -0,0 +1,50 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from gitea_codex_bot.types import ParsedCommand
|
||||
|
||||
|
||||
def format_queue_ack(head_sha: str) -> str:
|
||||
short_sha = head_sha[:7]
|
||||
return f"👀 Codex review queued for commit `{short_sha}`."
|
||||
|
||||
|
||||
def format_cooldown_ack(seconds: int) -> str:
|
||||
return f"⏳ Cooldown active. Please wait {seconds}s before requesting another review on this PR."
|
||||
|
||||
|
||||
def format_disabled_ack() -> str:
|
||||
return "🚫 Review is disabled by `.codex-review.yml` for this repository."
|
||||
|
||||
|
||||
def format_unsupported_ack(command: ParsedCommand) -> str:
|
||||
return f"⚠️ Command `@codex {command.name}` is not enabled on this repository."
|
||||
|
||||
|
||||
def format_result_comment(head_sha: str, result: dict) -> str:
|
||||
verdict = result.get("verdict", "has_issues")
|
||||
confidence = float(result.get("confidence", 0.0))
|
||||
summary = str(result.get("summary", "No summary returned."))
|
||||
findings = result.get("findings", []) or []
|
||||
|
||||
lines = [f"<!-- codex-review:head_sha={head_sha} -->", "## Codex Review", "", f"Verdict: `{verdict}`", f"Confidence: `{confidence:.2f}`", "", summary, ""]
|
||||
if not findings:
|
||||
lines.append("No blocking issues found.")
|
||||
else:
|
||||
lines.append("Findings:")
|
||||
for idx, finding in enumerate(findings, start=1):
|
||||
severity = finding.get("severity", "unknown")
|
||||
file_path = finding.get("file", "unknown")
|
||||
line_start = finding.get("line_start", "?")
|
||||
line_end = finding.get("line_end", line_start)
|
||||
title = finding.get("title", "Issue")
|
||||
body = finding.get("body", "")
|
||||
suggestion = finding.get("suggestion", "")
|
||||
lines.extend(
|
||||
[
|
||||
f"{idx}. `{file_path}:{line_start}-{line_end}` ({severity})",
|
||||
f" {title}",
|
||||
f" {body}",
|
||||
f" Suggestion: {suggestion}" if suggestion else " Suggestion: n/a",
|
||||
]
|
||||
)
|
||||
return "\n".join(lines).strip()
|
||||
290
src/gitea_codex_bot/services/reviewer.py
Normal file
290
src/gitea_codex_bot/services/reviewer.py
Normal file
@@ -0,0 +1,290 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
import shlex
|
||||
import subprocess
|
||||
from fnmatch import fnmatch
|
||||
from pathlib import Path
|
||||
from tempfile import TemporaryDirectory
|
||||
from typing import Any
|
||||
|
||||
import httpx
|
||||
|
||||
from gitea_codex_bot.config import Settings
|
||||
from gitea_codex_bot.services.gitea import GiteaClient, PullRequestContext
|
||||
from gitea_codex_bot.services.repo_config import RepoReviewConfig, load_repo_review_config
|
||||
from gitea_codex_bot.types import ParsedCommand
|
||||
|
||||
|
||||
class ReviewError(RuntimeError):
|
||||
pass
|
||||
|
||||
|
||||
def _run_git(args: list[str], cwd: Path | None = None) -> str:
|
||||
completed = subprocess.run(["git", *args], cwd=cwd, check=True, capture_output=True, text=True)
|
||||
return completed.stdout
|
||||
|
||||
|
||||
def checkout_pr(tmpdir: Path, pr: PullRequestContext) -> Path:
|
||||
repo_dir = tmpdir / "repo"
|
||||
_run_git(["clone", "--no-tags", "--depth", "50", pr.clone_url, str(repo_dir)])
|
||||
_run_git(["fetch", "origin", pr.base_ref, pr.head_ref], cwd=repo_dir)
|
||||
_run_git(["checkout", pr.head_sha], cwd=repo_dir)
|
||||
return repo_dir
|
||||
|
||||
|
||||
def collect_diff_context(repo_dir: Path, pr: PullRequestContext, max_diff_bytes: int) -> dict[str, Any]:
|
||||
diff = _run_git(["diff", f"{pr.base_sha}...{pr.head_sha}"], cwd=repo_dir)
|
||||
changed_files_raw = _run_git(["diff", "--name-only", f"{pr.base_sha}...{pr.head_sha}"], cwd=repo_dir)
|
||||
changed_files = [line.strip() for line in changed_files_raw.splitlines() if line.strip()]
|
||||
truncated = False
|
||||
if len(diff.encode("utf-8")) > max_diff_bytes:
|
||||
diff = diff.encode("utf-8")[:max_diff_bytes].decode("utf-8", errors="ignore")
|
||||
truncated = True
|
||||
return {"diff": diff, "changed_files": changed_files, "truncated": truncated}
|
||||
|
||||
|
||||
def _apply_ignore_patterns(changed_files: list[str], ignore_patterns: list[str]) -> list[str]:
|
||||
if not ignore_patterns:
|
||||
return changed_files
|
||||
kept: list[str] = []
|
||||
for path in changed_files:
|
||||
if any(fnmatch(path, pattern) for pattern in ignore_patterns):
|
||||
continue
|
||||
kept.append(path)
|
||||
return kept
|
||||
|
||||
|
||||
def _collect_changed_file_contents(repo_dir: Path, changed_files: list[str], max_total_bytes: int) -> str:
|
||||
chunks: list[str] = []
|
||||
total = 0
|
||||
for rel in changed_files:
|
||||
path = repo_dir / rel
|
||||
if not path.exists() or not path.is_file():
|
||||
continue
|
||||
try:
|
||||
content = path.read_text(encoding="utf-8", errors="ignore")
|
||||
except OSError:
|
||||
continue
|
||||
block = f"\n### {rel}\n{content}\n"
|
||||
block_bytes = len(block.encode("utf-8"))
|
||||
if total + block_bytes > max_total_bytes:
|
||||
break
|
||||
chunks.append(block)
|
||||
total += block_bytes
|
||||
return "".join(chunks).strip()
|
||||
|
||||
|
||||
def _collect_test_output(repo_dir: Path, timeout_seconds: int) -> str:
|
||||
try:
|
||||
completed = subprocess.run(
|
||||
["pytest", "-q"],
|
||||
cwd=repo_dir,
|
||||
capture_output=True,
|
||||
text=True,
|
||||
timeout=timeout_seconds,
|
||||
check=False,
|
||||
)
|
||||
output = (completed.stdout + "\n" + completed.stderr).strip()
|
||||
return output[:10000]
|
||||
except Exception as exc:
|
||||
return f"Test execution unavailable: {exc}"
|
||||
|
||||
|
||||
def _redact_secrets_from_diff(diff: str) -> str:
|
||||
secret_terms = ("api_key", "token", "secret", "password", "private_key", "-----begin")
|
||||
redacted_lines: list[str] = []
|
||||
for line in diff.splitlines():
|
||||
lower = line.lower()
|
||||
if any(term in lower for term in secret_terms):
|
||||
redacted_lines.append("[REDACTED_POTENTIAL_SECRET]")
|
||||
else:
|
||||
redacted_lines.append(line)
|
||||
return "\n".join(redacted_lines)
|
||||
|
||||
|
||||
def _build_prompt(
|
||||
pr: PullRequestContext,
|
||||
command: ParsedCommand,
|
||||
diff_context: dict[str, Any],
|
||||
repo_cfg: RepoReviewConfig,
|
||||
*,
|
||||
changed_file_contents: str,
|
||||
test_output: str | None,
|
||||
) -> str:
|
||||
mode = command.mode if command.name in {"review", "rerun"} else "summary"
|
||||
return (
|
||||
"You are reviewing a Gitea pull request.\n\n"
|
||||
"Focus only on issues introduced by this PR.\n"
|
||||
"Prioritize correctness, security, data loss, broken behavior, bad migrations, and missing tests.\n"
|
||||
"Avoid style nitpicks.\n\n"
|
||||
"Return JSON only with schema:\n"
|
||||
"{\n"
|
||||
' "verdict": "correct" | "has_issues",\n'
|
||||
' "confidence": 0.0,\n'
|
||||
' "summary": "...",\n'
|
||||
' "findings": [{"severity":"low|medium|high|critical","file":"...","line_start":1,"line_end":1,"title":"...","body":"...","suggestion":"..."}]\n'
|
||||
"}\n\n"
|
||||
f"PR URL: {pr.html_url}\n"
|
||||
f"Mode: {mode}\n"
|
||||
f"Repo focus: {', '.join(repo_cfg.focus)}\n"
|
||||
f"Diff truncated: {diff_context['truncated']}\n"
|
||||
f"Changed files:\n{os.linesep.join(diff_context['changed_files'])}\n\n"
|
||||
f"Unified diff:\n{diff_context['diff']}\n\n"
|
||||
f"Changed file content (optional):\n{changed_file_contents or '(not included)'}\n\n"
|
||||
f"Test output (optional):\n{test_output or '(not included)'}\n"
|
||||
)
|
||||
|
||||
|
||||
def _call_openai_review(settings: Settings, prompt: str) -> dict[str, Any]:
|
||||
headers: dict[str, str] = {
|
||||
"Authorization": f"Bearer {settings.openai_api_key.get_secret_value()}",
|
||||
"Content-Type": "application/json",
|
||||
}
|
||||
if settings.openai_org_id:
|
||||
headers["OpenAI-Organization"] = settings.openai_org_id
|
||||
if settings.openai_project_id:
|
||||
headers["OpenAI-Project"] = settings.openai_project_id
|
||||
|
||||
body = {
|
||||
"model": settings.openai_review_model,
|
||||
"input": prompt,
|
||||
"text": {"format": {"type": "json_object"}},
|
||||
"reasoning": {"effort": settings.openai_reasoning_effort},
|
||||
}
|
||||
with httpx.Client(timeout=120.0) as client:
|
||||
response = client.post("https://api.openai.com/v1/responses", headers=headers, json=body)
|
||||
response.raise_for_status()
|
||||
payload = response.json()
|
||||
|
||||
for item in payload.get("output", []):
|
||||
for content in item.get("content", []):
|
||||
text_value = content.get("text")
|
||||
if text_value:
|
||||
return json.loads(text_value)
|
||||
raise ReviewError("OpenAI response did not contain JSON output text.")
|
||||
|
||||
|
||||
def _fallback_review(diff_context: dict[str, Any]) -> dict[str, Any]:
|
||||
findings = []
|
||||
if "TODO" in diff_context["diff"]:
|
||||
findings.append(
|
||||
{
|
||||
"severity": "low",
|
||||
"file": "unknown",
|
||||
"line_start": 1,
|
||||
"line_end": 1,
|
||||
"title": "TODO marker in diff",
|
||||
"body": "The change introduces TODO markers that may indicate incomplete behavior.",
|
||||
"suggestion": "Resolve or track TODOs before merging.",
|
||||
}
|
||||
)
|
||||
return {
|
||||
"verdict": "correct" if not findings else "has_issues",
|
||||
"confidence": 0.4 if not findings else 0.6,
|
||||
"summary": "Fallback analysis was used because OpenAI review was unavailable.",
|
||||
"findings": findings,
|
||||
}
|
||||
|
||||
|
||||
def run_review_for_pr(
|
||||
settings: Settings,
|
||||
gitea: GiteaClient,
|
||||
repo: str,
|
||||
pr_number: int,
|
||||
command: ParsedCommand,
|
||||
) -> tuple[dict[str, Any], RepoReviewConfig]:
|
||||
prompt, diff_context, repo_cfg = prepare_review_prompt(settings, gitea, repo, pr_number, command)
|
||||
try:
|
||||
result = _call_openai_review(settings, prompt)
|
||||
except Exception:
|
||||
result = _fallback_review(diff_context)
|
||||
return normalize_review_result(result), repo_cfg
|
||||
|
||||
|
||||
def prepare_review_prompt(
|
||||
settings: Settings,
|
||||
gitea: GiteaClient,
|
||||
repo: str,
|
||||
pr_number: int,
|
||||
command: ParsedCommand,
|
||||
) -> tuple[str, dict[str, Any], RepoReviewConfig]:
|
||||
pr = gitea.get_pull_request(repo, pr_number)
|
||||
with TemporaryDirectory(prefix="gitea-codex-") as tmp:
|
||||
tmpdir = Path(tmp)
|
||||
repo_dir = checkout_pr(tmpdir, pr)
|
||||
repo_cfg = load_repo_review_config(repo_dir)
|
||||
diff_context = collect_diff_context(repo_dir, pr, min(settings.max_diff_bytes, repo_cfg.max_diff_bytes))
|
||||
diff_context["changed_files"] = _apply_ignore_patterns(diff_context["changed_files"], repo_cfg.ignore)
|
||||
diff_context["diff"] = _redact_secrets_from_diff(diff_context["diff"])
|
||||
changed_file_contents = ""
|
||||
if command.full:
|
||||
changed_file_contents = _collect_changed_file_contents(repo_dir, diff_context["changed_files"], settings.max_diff_bytes)
|
||||
test_output = None
|
||||
if repo_cfg.include_tests and command.mode == "tests":
|
||||
test_output = _collect_test_output(repo_dir, timeout_seconds=min(settings.max_review_minutes * 60, 300))
|
||||
prompt = _build_prompt(
|
||||
pr,
|
||||
command,
|
||||
diff_context,
|
||||
repo_cfg,
|
||||
changed_file_contents=changed_file_contents,
|
||||
test_output=test_output,
|
||||
)
|
||||
return prompt, diff_context, repo_cfg
|
||||
|
||||
|
||||
def normalize_review_result(result: Any) -> dict[str, Any]:
|
||||
if not isinstance(result, dict):
|
||||
raise ReviewError(f"Invalid review result type: {type(result)!r}")
|
||||
if "findings" not in result:
|
||||
result["findings"] = []
|
||||
if "summary" not in result:
|
||||
result["summary"] = "No summary returned."
|
||||
if "verdict" not in result:
|
||||
result["verdict"] = "has_issues"
|
||||
if "confidence" not in result:
|
||||
result["confidence"] = 0.5
|
||||
return result
|
||||
|
||||
|
||||
def summarize_command(command: ParsedCommand) -> str:
|
||||
return " ".join(["@codex", command.name, *command.arguments]).strip()
|
||||
|
||||
|
||||
def fix_branch_name(pr_number: int, arguments: list[str] | None = None) -> str:
|
||||
suffix = "fix"
|
||||
if arguments:
|
||||
words = [token.lower().strip() for token in arguments if token.strip() and not token.startswith("--")]
|
||||
if words:
|
||||
clean = "-".join(words[:4])
|
||||
cleaned = "".join(ch if ch.isalnum() or ch == "-" else "-" for ch in clean).strip("-")
|
||||
if cleaned:
|
||||
suffix = f"fix-{cleaned}"
|
||||
return f"codex/pr-{pr_number}-{suffix}"
|
||||
|
||||
|
||||
def create_fix_patch_note(command: ParsedCommand) -> str:
|
||||
details = shlex.join(command.arguments) if command.arguments else "latest findings"
|
||||
return f"Fix command requested for {details}."
|
||||
|
||||
|
||||
def create_fix_branch(
|
||||
pr: PullRequestContext,
|
||||
*,
|
||||
note: str,
|
||||
arguments: list[str] | None = None,
|
||||
) -> str:
|
||||
branch = fix_branch_name(pr.pr_number, arguments=arguments)
|
||||
with TemporaryDirectory(prefix="gitea-codex-fix-") as tmp:
|
||||
tmpdir = Path(tmp)
|
||||
repo_dir = checkout_pr(tmpdir, pr)
|
||||
_run_git(["checkout", "-b", branch], cwd=repo_dir)
|
||||
notes_dir = repo_dir / ".codex"
|
||||
notes_dir.mkdir(parents=True, exist_ok=True)
|
||||
(notes_dir / "fix-note.md").write_text(f"# Codex Fix Note\n\n{note}\n", encoding="utf-8")
|
||||
_run_git(["add", ".codex/fix-note.md"], cwd=repo_dir)
|
||||
_run_git(["-c", "user.name=codex-bot", "-c", "user.email=codex-bot@example.invalid", "commit", "-m", f"Codex fix note for PR {pr.pr_number}"], cwd=repo_dir)
|
||||
_run_git(["push", "origin", f"{branch}:{branch}", "--force"], cwd=repo_dir)
|
||||
return branch
|
||||
16
src/gitea_codex_bot/services/security.py
Normal file
16
src/gitea_codex_bot/services/security.py
Normal file
@@ -0,0 +1,16 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
import hmac
|
||||
|
||||
|
||||
def verify_gitea_signature(payload: bytes, secret: str, received_signature: str | None) -> bool:
|
||||
if not received_signature:
|
||||
return False
|
||||
expected = hmac.new(secret.encode("utf-8"), payload, hashlib.sha256).hexdigest()
|
||||
normalized = received_signature.removeprefix("sha256=").strip()
|
||||
return hmac.compare_digest(expected, normalized)
|
||||
|
||||
|
||||
def payload_digest(payload: bytes) -> str:
|
||||
return hashlib.sha256(payload).hexdigest()
|
||||
17
src/gitea_codex_bot/types.py
Normal file
17
src/gitea_codex_bot/types.py
Normal file
@@ -0,0 +1,17 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass, field
|
||||
from typing import Literal
|
||||
|
||||
|
||||
CommandName = Literal["review", "explain", "fix", "ignore", "rerun"]
|
||||
|
||||
|
||||
@dataclass(slots=True)
|
||||
class ParsedCommand:
|
||||
name: CommandName
|
||||
raw: str
|
||||
mode: str = "summary"
|
||||
full: bool = False
|
||||
branch_fix: bool = False
|
||||
arguments: list[str] = field(default_factory=list)
|
||||
0
src/gitea_codex_bot/workers/__init__.py
Normal file
0
src/gitea_codex_bot/workers/__init__.py
Normal file
110
src/gitea_codex_bot/workers/container_runner.py
Normal file
110
src/gitea_codex_bot/workers/container_runner.py
Normal file
@@ -0,0 +1,110 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import subprocess
|
||||
import uuid
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
from gitea_codex_bot.config import Settings
|
||||
from gitea_codex_bot.services.gitea import GiteaClient
|
||||
from gitea_codex_bot.services.reviewer import normalize_review_result, prepare_review_prompt, run_review_for_pr
|
||||
from gitea_codex_bot.types import ParsedCommand
|
||||
|
||||
|
||||
def run_review_ephemeral(
|
||||
settings: Settings,
|
||||
*,
|
||||
repo: str,
|
||||
pr_number: int,
|
||||
command: ParsedCommand,
|
||||
) -> dict[str, Any]:
|
||||
gitea = GiteaClient(settings)
|
||||
prompt, _diff_context, _repo_cfg = prepare_review_prompt(settings, gitea, repo, pr_number, command)
|
||||
container_name = f"codex-review-{uuid.uuid4().hex[:12]}"
|
||||
install_and_run = (
|
||||
"set -euo pipefail; "
|
||||
"npm install -g @openai/codex >/tmp/codex-install.log 2>&1; "
|
||||
"codex exec --json -m gpt-5"
|
||||
)
|
||||
cmd = [
|
||||
"docker",
|
||||
"run",
|
||||
"--rm",
|
||||
"-i",
|
||||
"--name",
|
||||
container_name,
|
||||
"-e",
|
||||
"OPENAI_API_KEY",
|
||||
"-e",
|
||||
"OPENAI_ORG_ID",
|
||||
"-e",
|
||||
"OPENAI_PROJECT_ID",
|
||||
"-e",
|
||||
"CODEX_DISABLE_TELEMETRY=1",
|
||||
settings.review_runner_image,
|
||||
"bash",
|
||||
"-lc",
|
||||
install_and_run,
|
||||
]
|
||||
try:
|
||||
completed = subprocess.run(
|
||||
cmd,
|
||||
input=prompt,
|
||||
text=True,
|
||||
check=True,
|
||||
capture_output=True,
|
||||
timeout=settings.max_review_minutes * 60,
|
||||
)
|
||||
parsed = _parse_codex_exec_stdout(completed.stdout)
|
||||
return normalize_review_result(parsed)
|
||||
except Exception:
|
||||
result, _repo_cfg = run_review_for_pr(settings, gitea, repo, pr_number, command)
|
||||
return result
|
||||
|
||||
|
||||
def ensure_workdir(path: str) -> Path:
|
||||
target = Path(path)
|
||||
target.mkdir(parents=True, exist_ok=True)
|
||||
return target
|
||||
|
||||
|
||||
def _parse_codex_exec_stdout(stdout: str) -> dict[str, Any]:
|
||||
last_text: str | None = None
|
||||
for line in stdout.splitlines():
|
||||
line = line.strip()
|
||||
if not line:
|
||||
continue
|
||||
try:
|
||||
payload = json.loads(line)
|
||||
except json.JSONDecodeError:
|
||||
continue
|
||||
if isinstance(payload, dict) and {"verdict", "summary", "findings"}.issubset(payload.keys()):
|
||||
return payload
|
||||
extracted = _extract_text(payload)
|
||||
if extracted:
|
||||
last_text = extracted
|
||||
if not last_text:
|
||||
raise RuntimeError("codex exec output did not include parseable JSON text")
|
||||
return json.loads(last_text)
|
||||
|
||||
|
||||
def _extract_text(payload: Any) -> str | None:
|
||||
if isinstance(payload, str):
|
||||
return payload
|
||||
if isinstance(payload, dict):
|
||||
for key in ("text", "message", "content", "output"):
|
||||
value = payload.get(key)
|
||||
text = _extract_text(value)
|
||||
if text:
|
||||
return text
|
||||
for value in payload.values():
|
||||
text = _extract_text(value)
|
||||
if text:
|
||||
return text
|
||||
if isinstance(payload, list):
|
||||
for item in payload:
|
||||
text = _extract_text(item)
|
||||
if text:
|
||||
return text
|
||||
return None
|
||||
135
src/gitea_codex_bot/workers/dispatcher.py
Normal file
135
src/gitea_codex_bot/workers/dispatcher.py
Normal file
@@ -0,0 +1,135 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import logging
|
||||
from typing import Any
|
||||
|
||||
from sqlalchemy import select
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from gitea_codex_bot.config import Settings
|
||||
from gitea_codex_bot.db import get_session_factory
|
||||
from gitea_codex_bot.models import ReviewJob
|
||||
from gitea_codex_bot.services.comments import get_persistent_review_comment_id, upsert_persistent_review_comment_id
|
||||
from gitea_codex_bot.services.gitea import GiteaClient
|
||||
from gitea_codex_bot.services.jobs import claim_next_job, finish_job
|
||||
from gitea_codex_bot.services.review_format import format_result_comment
|
||||
from gitea_codex_bot.services.reviewer import create_fix_branch, create_fix_patch_note
|
||||
from gitea_codex_bot.types import ParsedCommand
|
||||
from gitea_codex_bot.workers.container_runner import run_review_ephemeral
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def _command_from_job(job: ReviewJob) -> ParsedCommand:
|
||||
args = job.command_args.split() if job.command_args else []
|
||||
return ParsedCommand(name=job.command, raw=f"@codex {job.command}", arguments=args, full="--full" in args, branch_fix="--branch" in args)
|
||||
|
||||
|
||||
def _handle_non_review_command(
|
||||
settings: Settings,
|
||||
session: Session,
|
||||
gitea: GiteaClient,
|
||||
job: ReviewJob,
|
||||
command: ParsedCommand,
|
||||
) -> tuple[bool, bool, dict[str, Any] | None, str | None]:
|
||||
if command.name == "ignore":
|
||||
return True, True, {"summary": "Ignore command acknowledged. No review run executed."}, None
|
||||
if command.name == "explain":
|
||||
latest_review_job = session.execute(
|
||||
select(ReviewJob)
|
||||
.where(
|
||||
ReviewJob.repo == job.repo,
|
||||
ReviewJob.pr_number == job.pr_number,
|
||||
ReviewJob.command.in_(["review", "rerun"]),
|
||||
ReviewJob.status == "succeeded",
|
||||
)
|
||||
.order_by(ReviewJob.id.desc())
|
||||
.limit(1)
|
||||
).scalar_one_or_none()
|
||||
if latest_review_job and latest_review_job.result_json:
|
||||
message = f"## Codex Explain\n\n{latest_review_job.result_json.get('summary', 'No previous summary available.')}"
|
||||
else:
|
||||
message = "## Codex Explain\n\nNo previous result found for this command."
|
||||
gitea.post_issue_comment(job.repo, job.pr_number, message)
|
||||
return True, True, {"summary": message}, None
|
||||
if command.name == "fix":
|
||||
if not settings.enable_fix_commands:
|
||||
message = "⚠️ `@codex fix` is disabled on this bot instance."
|
||||
gitea.post_issue_comment(job.repo, job.pr_number, message)
|
||||
return True, True, {"summary": message}, None
|
||||
note = create_fix_patch_note(command)
|
||||
if command.branch_fix:
|
||||
try:
|
||||
pr = gitea.get_pull_request(job.repo, job.pr_number)
|
||||
branch = create_fix_branch(pr, note=note, arguments=command.arguments)
|
||||
message = f"## Codex Fix\n\n{note}\n\nCreated branch `{branch}`."
|
||||
gitea.post_issue_comment(job.repo, job.pr_number, message)
|
||||
return True, True, {"summary": note, "mode": "branch", "branch": branch}, None
|
||||
except Exception as exc:
|
||||
return True, False, None, f"Failed to create fix branch: {exc}"
|
||||
gitea.post_issue_comment(job.repo, job.pr_number, f"## Codex Fix\n\n{note}\n\nPatch suggestion mode.")
|
||||
return True, True, {"summary": note, "mode": "patch"}, None
|
||||
return False, False, None, None
|
||||
|
||||
|
||||
def process_one_job(settings: Settings) -> bool:
|
||||
session_factory = get_session_factory()
|
||||
with session_factory() as session:
|
||||
job = claim_next_job(session)
|
||||
if not job:
|
||||
return False
|
||||
|
||||
command = _command_from_job(job)
|
||||
gitea = GiteaClient(settings)
|
||||
|
||||
with session_factory() as session:
|
||||
db_job = session.execute(select(ReviewJob).where(ReviewJob.id == job.id)).scalar_one()
|
||||
handled, skipped, result, error = _handle_non_review_command(settings, session, gitea, db_job, command)
|
||||
if handled:
|
||||
finish_job(session, job_id=db_job.id, success=error is None, skipped=skipped, result=result, error_message=error)
|
||||
return True
|
||||
|
||||
try:
|
||||
pr_ctx = gitea.get_pull_request(job.repo, job.pr_number)
|
||||
if pr_ctx.is_fork and not settings.allow_untrusted_forks:
|
||||
with session_factory() as session:
|
||||
skip_message = "Skipped review for fork PR because `ALLOW_UNTRUSTED_FORKS=false`."
|
||||
gitea.post_issue_comment(job.repo, job.pr_number, skip_message)
|
||||
finish_job(
|
||||
session,
|
||||
job_id=job.id,
|
||||
success=True,
|
||||
skipped=True,
|
||||
result={"summary": skip_message},
|
||||
error_message=None,
|
||||
)
|
||||
return True
|
||||
result = run_review_ephemeral(settings, repo=job.repo, pr_number=job.pr_number, command=command)
|
||||
comment_body = format_result_comment(job.head_sha, result)
|
||||
with session_factory() as session:
|
||||
comment_id = get_persistent_review_comment_id(session, job.repo, job.pr_number)
|
||||
if comment_id:
|
||||
gitea.edit_issue_comment(job.repo, comment_id, comment_body)
|
||||
else:
|
||||
comment_id = gitea.post_issue_comment(job.repo, job.pr_number, comment_body)
|
||||
upsert_persistent_review_comment_id(
|
||||
session,
|
||||
repo=job.repo,
|
||||
pr_number=job.pr_number,
|
||||
head_sha=job.head_sha,
|
||||
comment_id=comment_id,
|
||||
)
|
||||
finish_job(session, job_id=job.id, success=True, skipped=False, result=result, error_message=None)
|
||||
except Exception as exc:
|
||||
logger.exception("Review job failed id=%s", job.id)
|
||||
with session_factory() as session:
|
||||
finish_job(session, job_id=job.id, success=False, skipped=False, result=None, error_message=str(exc))
|
||||
return True
|
||||
|
||||
|
||||
async def worker_loop(settings: Settings, stop_event: asyncio.Event) -> None:
|
||||
while not stop_event.is_set():
|
||||
processed = await asyncio.to_thread(process_one_job, settings)
|
||||
if not processed:
|
||||
await asyncio.sleep(1.0)
|
||||
31
src/gitea_codex_bot/workers/runner_entry.py
Normal file
31
src/gitea_codex_bot/workers/runner_entry.py
Normal file
@@ -0,0 +1,31 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import sys
|
||||
|
||||
from gitea_codex_bot.config import get_settings
|
||||
from gitea_codex_bot.services.gitea import GiteaClient
|
||||
from gitea_codex_bot.services.reviewer import run_review_for_pr
|
||||
from gitea_codex_bot.types import ParsedCommand
|
||||
|
||||
|
||||
def main() -> int:
|
||||
settings = get_settings()
|
||||
payload = json.loads(sys.stdin.read())
|
||||
command_payload = payload["command"]
|
||||
command = ParsedCommand(
|
||||
name=command_payload["name"],
|
||||
raw=f"@codex {command_payload['name']}",
|
||||
mode=command_payload.get("mode", "summary"),
|
||||
full=bool(command_payload.get("full", False)),
|
||||
branch_fix=bool(command_payload.get("branch_fix", False)),
|
||||
arguments=list(command_payload.get("arguments", [])),
|
||||
)
|
||||
gitea = GiteaClient(settings)
|
||||
result, _repo_cfg = run_review_for_pr(settings, gitea, payload["repo"], int(payload["pr_number"]), command)
|
||||
print(json.dumps(result))
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
Reference in New Issue
Block a user