Files
pragent/pilot/webhook_server.py
T
Marcos 90cea84f6f pilot: dedupe + repo config + inline comments w/ suggestions
- Dedupe: Gitea-as-state. Scan existing reviews for a hidden
  <!-- pragent:sha=... --> marker matching the head sha; skip if present
  (kills duplicate reviews on label-toggle / re-fire). Prior review bodies
  fed back as 'already said' context (light framework §6.1).
- Repo-local focus: optional .pr-review.json at repo root
  ({focus,exclude_paths,languages,instructions}), fetched at head ref.
- Inline comments + apply-able suggestions: model emits JSON findings
  {severity,path,line,problem,fix,suggestion}; diff hunks parsed into valid
  (path,new_line) RIGHT-side anchors; anchored findings become positional
  review comments with a ```suggestion fence (Gitea apply-button);
  unanchored findings fold into the summary body.
- Tests: parse_diff_anchors, parse_findings (tolerant JSON), split_findings,
  inline_comment_body, summary_bullets, parse_repo_config, reviewed_shas,
  prior_review_bodies, sha-marker. 35 pass.
- Bump OLLAMA_MAX_TOKENS default 6000 -> 8000 (suggestions add length).

Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-17 19:59:36 +00:00

206 lines
7.4 KiB
Python

#!/usr/bin/env python3
"""pragent pilot — central webhook receiver.
A stdlib-only HTTP server that Gitea posts user-webhook events to. It gates on
the `AI-REVIEW` PR label, then runs the same review core (`ai_review.review_pr`)
the CI-step pilot uses, posting findings back as `pragent-bot`.
Per-owner setup: one Gitea **user-level webhook** per repo-owner fires for every
repo that owner has; this service filters to labeled PRs. (Gitea 1.26.1 system
webhooks are broken — see pilot/README-webhook.md.) Onboarding a repo = add the
bot as a Write collaborator + create the label + label a PR.
Stdlib only — no pip install, runs on python:3-slim with the scripts mounted.
Endpoints:
POST /webhook Gitea webhook delivery (HMAC-verified)
GET /health liveness probe
Env:
WEBHOOK_SECRET shared secret used to register the Gitea webhook (HMAC)
GITEA_API in-cluster Gitea base URL
PRAGENT_BOT_TOKEN pragent-bot access token (non-admin; must be a Write
collaborator on each reviewed repo)
OLLAMA_URL headroom proxy URL, e.g. http://100.74.17.70:8789
OLLAMA_MODEL model id, e.g. glm-5.2:cloud
OLLAMA_MAX_TOKENS (optional) output cap, default 6000
DIFF_MAX_CHARS (optional) diff truncation cap, default 150000
WEBHOOK_PORT (optional) listen port, default 8080
"""
import hashlib
import hmac
import json
import os
import threading
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
from ai_review import review_pr
# Pull-request webhook `action` values worth reviewing on. Gitea emits
# GitHub-style payload `action` names (`labeled`, `synchronize`) even though the
# `X-Gitea-Event-Type` header uses `label_updated` / `synchronized` — accept both
# so the gate is robust to either. The label gate below means a non-AI-REVIEW
# label update is a no-op.
REVIEW_ACTIONS = {"opened", "reopened", "synchronize", "synchronized", "labeled", "label_updated"}
AI_REVIEW_LABEL = "AI-REVIEW"
GITEA_API = os.environ.get("GITEA_API", "http://gitea-http.gitea.svc.cluster.local:3000")
BOT_TOKEN = os.environ.get("PRAGENT_BOT_TOKEN", "")
OLLAMA_URL = os.environ.get("OLLAMA_URL", "http://100.74.17.70:8789")
OLLAMA_MODEL = os.environ.get("OLLAMA_MODEL", "glm-5.2:cloud")
OLLAMA_MAX_TOKENS = int(os.environ.get("OLLAMA_MAX_TOKENS", "8000"))
DIFF_MAX_CHARS = int(os.environ.get("DIFF_MAX_CHARS", "150000"))
WEBHOOK_SECRET = os.environ.get("WEBHOOK_SECRET", "").encode()
PORT = int(os.environ.get("WEBHOOK_PORT", "8080"))
def _labels_have_ai_review(labels) -> bool:
if not isinstance(labels, list):
return False
for lab in labels:
if isinstance(lab, dict) and lab.get("name") == AI_REVIEW_LABEL:
return True
if isinstance(lab, str) and lab == AI_REVIEW_LABEL:
return True
return False
def _verify_signature(raw_body: bytes, headers) -> bool:
if not WEBHOOK_SECRET:
return False # refuse to run without a configured secret
sig_header = headers.get("X-Gitea-Signature") or headers.get("X-Forgejo-Signature")
if not sig_header:
return False
mac = hmac.new(WEBHOOK_SECRET, raw_body, hashlib.sha256).hexdigest()
return hmac.compare_digest(mac, sig_header)
def _handle_pull_request(payload: dict) -> tuple[int, str]:
"""Decide whether to review; if so, kick it off in a background thread.
Returns (status, message) to Gitea immediately — the review itself runs
async so Gitea's delivery timeout never fires and causes a retry.
"""
action = payload.get("action", "")
pr = payload.get("pull_request") or {}
repo_obj = payload.get("repository") or {}
repo = repo_obj.get("full_name") or ""
if action not in REVIEW_ACTIONS:
return 200, f"ignore action={action}"
if not repo:
return 400, "no repository.full_name"
if not _labels_have_ai_review(pr.get("labels")):
return 200, f"ignore (no {AI_REVIEW_LABEL} label) action={action}"
index = pr.get("number")
if index is None:
return 400, "no pull_request.number"
title = pr.get("title", "") or ""
body = pr.get("body", "") or ""
head = pr.get("head") or {}
sha = head.get("sha", "") or ""
if not BOT_TOKEN:
return 500, "PRAGENT_BOT_TOKEN not set"
threading.Thread(
target=_run_review,
args=(repo, str(index), title, body, sha),
daemon=True,
).start()
return 202, f"reviewing {repo}#{index} action={action} sha={sha[:8]}"
def _run_review(repo: str, index: str, title: str, body: str, sha: str) -> None:
try:
ok = review_pr(
api=GITEA_API,
repo=repo,
index=index,
title=title,
body=body,
sha=sha,
token=BOT_TOKEN,
ollama_url=OLLAMA_URL,
model=OLLAMA_MODEL,
max_tokens=OLLAMA_MAX_TOKENS,
max_chars=DIFF_MAX_CHARS,
)
print(f"pragent-webhook: reviewed {repo}#{index} sha={sha[:8]} ok={ok}", flush=True)
except Exception as e: # review_pr is fail-open, but guard the thread anyway
print(f"pragent-webhook: thread crashed for {repo}#{index}: {e}", flush=True)
class Handler(BaseHTTPRequestHandler):
def _send(self, status: int, body: str) -> None:
data = body.encode()
self.send_response(status)
self.send_header("Content-Type", "text/plain")
self.send_header("Content-Length", str(len(data)))
self.end_headers()
self.wfile.write(data)
def do_GET(self):
if self.path == "/health":
self._send(200, "ok")
else:
self._send(404, "not found")
def do_POST(self):
if self.path != "/webhook":
self._send(404, "not found")
return
length = int(self.headers.get("Content-Length", "0") or "0")
raw = self.rfile.read(length) if length else b""
if not _verify_signature(raw, self.headers):
self._send(401, "invalid signature")
return
try:
payload = json.loads(raw)
except json.JSONDecodeError:
self._send(400, "invalid json")
return
event = self.headers.get("X-Gitea-Event") or payload.get("action") or ""
if event != "pull_request":
self._send(200, f"ignore event={event}")
return
pr0 = payload.get("pull_request") or {}
print(
f"pragent-webhook: pull_request action={payload.get('action')} "
f"repo={(payload.get('repository') or {}).get('full_name')} "
f"ai_review={_labels_have_ai_review(pr0.get('labels'))}",
flush=True,
)
status, msg = _handle_pull_request(payload)
self._send(status, msg)
def log_message(self, fmt, *args):
# Keep k8s logs to our own lines (see _run_review / _send paths).
print(f"pragent-webhook: {self.address_string()} {fmt % args}", flush=True)
def main() -> int:
if not WEBHOOK_SECRET:
print("pragent-webhook: FATAL: WEBHOOK_SECRET not set", flush=True)
return 1
if not BOT_TOKEN:
print("pragent-webhook: FATAL: PRAGENT_BOT_TOKEN not set", flush=True)
return 1
server = ThreadingHTTPServer(("0.0.0.0", PORT), Handler)
print(f"pragent-webhook: listening on :{PORT} (model={OLLAMA_MODEL})", flush=True)
try:
server.serve_forever()
except KeyboardInterrupt:
pass
return 0
if __name__ == "__main__":
raise SystemExit(main())