feat(webhook): gate on .pr-review.json:enabled, drop labels

pilot/webhook_server.py

@@ -2,13 +2,15 @@
 """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`.
+the PR's base ref having `.pr-review.json` with `"enabled": true`, 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
+repo that owner has; this service filters to opted-in 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.
+bot as a Write collaborator + commit a `.pr-review.json` with `"enabled": true`
+on the base ref.
 
 Stdlib only — no pip install, runs on python:3-slim with the scripts mounted.
 
@@ -53,15 +55,13 @@ except ImportError:
     feedback_harvest = None
 
 # Pull-request webhook `action` values. We fire on EVERY pull_request action
-# except `closed` (no point reviewing a closed/merged PR) — the AI-REVIEW label
-# gate + sha dedupe downstream make broadening safe: a same-sha re-fire (title
-# edit, assignee, milestone, label toggle of another label…) is skipped by
-# `review_pr`'s dedupe, and an `unlabeled` event that removed AI-REVIEW fails
-# the label gate (payload `labels` reflect current state). Gitea emits
-# GitHub-style `action` names (`labeled`, `synchronize`) even though the
-# `X-Gitea-Event-Type` header uses `label_updated` / `synchronized`.
+# except `closed` (no point reviewing a closed/merged PR) — the
+# `.pr-review.json:enabled` gate + sha dedupe downstream make broadening safe:
+# a same-sha re-fire (title edit, assignee, milestone, label toggle…) is
+# skipped by `review_pr`'s dedupe. Gitea emits GitHub-style `action` names
+# (`labeled`, `synchronize`) even though the `X-Gitea-Event-Type` header uses
+# `label_updated` / `synchronized`.
 SKIP_ACTIONS = {"closed"}
-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", "")
@@ -87,30 +87,13 @@ _review_slots = threading.Semaphore(MAX_CONCURRENT)
 # Reviews currently accepted or running, keyed (repo, index, sha). The
 # sha-marker dedupe in `review_pr` reads Gitea *before* posting, so two
 # deliveries for the same commit in flight together both see "not yet reviewed"
-# and both post — the classic check-then-act race, and label-toggling is exactly
-# the kind of thing that fires two deliveries a second apart. This set closes
-# the window inside one process.
+# and both post — the classic check-then-act race. Common triggers are Gitea
+# retries after a slow 202 response and bursty re-fires from a rapid title /
+# assign / label toggle. This set closes the window inside one process.
 _inflight: set[tuple[str, str, str]] = set()
 _inflight_lock = threading.Lock()
 
 
-def _labels_have(labels, name: str) -> bool:
-    """True if the Gitea PR `labels` list (dicts with `name`, or bare strings)
-    contains `name`."""
-    if not isinstance(labels, list):
-        return False
-    for lab in labels:
-        if isinstance(lab, dict) and lab.get("name") == name:
-            return True
-        if isinstance(lab, str) and lab == name:
-            return True
-    return False
-
-
-def _labels_have_ai_review(labels) -> bool:
-    return _labels_have(labels, AI_REVIEW_LABEL)
-
-
 def is_repo_enabled(api: str, repo: str, ref: str, token: str) -> bool:
     """True iff `.pr-review.json` on `ref` has `"enabled": true`.
 
@@ -162,10 +145,6 @@ def _handle_pull_request(payload: dict) -> tuple[int, str]:
     if not repo:
         return 400, "no repository.full_name"
 
-    labels = pr.get("labels")
-    if not _labels_have_ai_review(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"
@@ -176,6 +155,9 @@ def _handle_pull_request(payload: dict) -> tuple[int, str]:
 
     base_ref = (pr.get("base") or {}).get("ref", "") or ""
 
+    if not is_repo_enabled(GITEA_API, repo, base_ref or "", BOT_TOKEN):
+        return 200, f"skip (repo not opted in) action={action}"
+
     if not BOT_TOKEN:
         return 500, "PRAGENT_BOT_TOKEN not set"
 
@@ -304,11 +286,9 @@ class Handler(BaseHTTPRequestHandler):
             self._send(200, f"ignore event={event}")
             return
 
-        pr0 = payload.get("pull_request") or {}
+        repo_full = (payload.get("repository") or {}).get("full_name")
         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'))}",
+            f"pragent-webhook: pull_request action={payload.get('action')} repo={repo_full}",
             flush=True,
         )
         status, msg = _handle_pull_request(payload)