refactor(review): always render usage; drop report_usage flag

pilot/webhook_server.py

@@ -43,6 +43,13 @@ from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
 
 from ai_review import review_pr
 
+try:
+    import feedback_harvest  # optional — absent in CI-step pod, present in
+                              # central webhook service. Harvesting is the
+                              # collection side of the feedback loop.
+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
@@ -53,7 +60,6 @@ from ai_review import review_pr
 # `X-Gitea-Event-Type` header uses `label_updated` / `synchronized`.
 SKIP_ACTIONS = {"closed"}
 AI_REVIEW_LABEL = "AI-REVIEW"
-AI_USAGE_LABEL = "AI-USAGE"
 
 GITEA_API = os.environ.get("GITEA_API", "http://gitea-http.gitea.svc.cluster.local:3000")
 BOT_TOKEN = os.environ.get("PRAGENT_BOT_TOKEN", "")
@@ -65,6 +71,9 @@ WEBHOOK_SECRET = os.environ.get("WEBHOOK_SECRET", "").encode()
 PORT = int(os.environ.get("WEBHOOK_PORT", "8080"))
 MAX_CONCURRENT = max(1, int(os.environ.get("PRAGENT_MAX_CONCURRENT_REVIEWS", "2")))
 MAX_BODY_BYTES = int(os.environ.get("PRAGENT_MAX_BODY_BYTES", str(10 * 1024 * 1024)))
+# Feedback DB — SQLite mounted at PRAGENT_FEEDBACK_DB. Empty / unset =
+# feedback collection disabled (CI-step path doesn't have it).
+FEEDBACK_DB = os.environ.get("PRAGENT_FEEDBACK_DB", "")
 
 # Bound on reviews running at once. Every review forks an opencode process that
 # untars a repo, reads files and shells out to linters, so an unbounded thread
@@ -143,23 +152,16 @@ def _handle_pull_request(payload: dict) -> tuple[int, str]:
     if not BOT_TOKEN:
         return 500, "PRAGENT_BOT_TOKEN not set"
 
-    # AI-USAGE label (opt-in) → append the token-usage section + per-comment 🪙
-    # lines to the review. PRAGENT_USAGE_ALWAYS forces it on for testing / a
-    # future default-on.
-    report_usage = _labels_have(labels, AI_USAGE_LABEL) or bool(
-        os.environ.get("PRAGENT_USAGE_ALWAYS")
-    )
-
     key = (repo, str(index), sha)
     if not _claim(key):
         return 200, f"ignore (already in flight) {repo}#{index} sha={sha[:8]}"
 
     threading.Thread(
         target=_run_review,
-        args=(key, title, body, report_usage, base_ref),
+        args=(key, title, body, base_ref),
         daemon=True,
     ).start()
-    return 202, f"reviewing {repo}#{index} action={action} sha={sha[:8]} usage={report_usage}"
+    return 202, f"reviewing {repo}#{index} action={action} sha={sha[:8]}"
 
 
 def _claim(key: tuple[str, str, str]) -> bool:
@@ -177,9 +179,30 @@ def _release(key: tuple[str, str, str]) -> None:
 
 
 def _run_review(
-    key: tuple[str, str, str], title: str, body: str, report_usage: bool, base_ref: str
+    key: tuple[str, str, str], title: str, body: str, base_ref: str
 ) -> None:
     repo, index, sha = key
+    # Harvest reactions on PRIOR bot comments on this PR (best-effort —
+    # piggy-backs the webhook path so we don't need a separate cron).
+    # Disabled if feedback_harvest isn't importable (CI-step image) or
+    # FEEDBACK_DB isn't set.
+    if FEEDBACK_DB and feedback_harvest is not None:
+        try:
+            hstats = feedback_harvest.harvest_for_pr(
+                api=GITEA_API, token=BOT_TOKEN,
+                repo=repo, pr_index=int(index), db_path=FEEDBACK_DB,
+            )
+            print(
+                f"pragent-webhook: harvested {repo}#{index} "
+                f"reviews={hstats['reviews_seen']} "
+                f"findings={hstats['findings_seen']} "
+                f"reactions={hstats['reactions_recorded']}",
+                flush=True,
+            )
+        except Exception as e:
+            # Harvest must never abort a review.
+            print(f"pragent-webhook: harvest failed for {repo}#{index}: {e}", flush=True)
+
     try:
         with _review_slots:
             ok = review_pr(
@@ -194,10 +217,9 @@ def _run_review(
                 model=OLLAMA_MODEL,
                 max_tokens=OLLAMA_MAX_TOKENS,
                 max_chars=DIFF_MAX_CHARS,
-                report_usage=report_usage,
                 base_ref=base_ref,
             )
-        print(f"pragent-webhook: reviewed {repo}#{index} sha={sha[:8]} ok={ok} usage={report_usage}", flush=True)
+        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)
     finally: