Add one-time tool to redact resolved review cards

Cards decided before the auto-redact behavior shipped are already 'closed' in the CRM, so the bot's to_close sweep never redacts them. redact_resolved.py walks the review room, keeps cards still pending (CRM 'open' list), and redacts the rest. Dry-run by default; --apply to act. Run via docker compose on the Spark.
2026-06-18 12:09:48 -05:00
parent a10889b10b
commit 9044641b08
1 changed files with 73 additions and 0 deletions
@@ -0,0 +1,73 @@
+#!/usr/bin/env python3
+"""One-time maintenance: redact already-resolved email-proposal review cards.
+
+The bot redacts a card when it's decided going forward, but cards that were decided BEFORE that
+behavior shipped (e.g. smoke-test remnants) are already `closed` in the CRM, so the normal
+to_close sweep never touches them. This walks the review room's history, finds the bot's own
+"proposed grid note" cards, and redacts every one that is NOT still pending (i.e. not in the CRM
+`open` work-list) — leaving the room showing only what still needs handling.
+
+Safe by default: prints what it WOULD redact and does nothing. Pass --apply to actually redact.
+Run on the Spark via the bot's own creds/image:
+    docker compose run --rm matrix-intake python -u backend/matrix_intake/redact_resolved.py
+    docker compose run --rm matrix-intake python -u backend/matrix_intake/redact_resolved.py --apply
+"""
+import asyncio
+import sys
+
+from nio import AsyncClient, MessageDirection
+
+import crm_client
+import settings
+
+CARD_MARKER = "📧 Proposed"   # present in every review card (old and dash-framed)
+MAX_PAGES = 30                # 30 * 100 events is far more history than this room holds
+
+
+async def main(apply):
+    mx = settings.matrix_settings()
+    review_room = settings.email_review_room()
+    if not review_room:
+        print("MATRIX_EMAIL_REVIEW_ROOM is not set — nothing to do.")
+        return
+    client = AsyncClient(mx["homeserver"], mx["user_id"])
+    client.restore_login(user_id=mx["user_id"], device_id=mx["device_id"], access_token=mx["token"])
+    try:
+        # Cards still pending (must be KEPT) — their thread-root event id is the card event id.
+        open_ids = {it["event_id"] for it in crm_client.list_email_proposals().get("open", []) if it.get("event_id")}
+        print(f"pending cards to keep: {len(open_ids)}")
+
+        sync = await client.sync(timeout=10000, full_state=False)
+        token = sync.next_batch
+        cards = {}  # event_id -> snippet (dedup across pages)
+        for _ in range(MAX_PAGES):
+            resp = await client.room_messages(review_room, start=token,
+                                              direction=MessageDirection.back, limit=100)
+            chunk = getattr(resp, "chunk", None)
+            if not chunk:
+                break
+            for ev in chunk:
+                if getattr(ev, "sender", None) != mx["user_id"]:
+                    continue
+                body = getattr(ev, "body", "") or ""
+                if CARD_MARKER in body:
+                    cards[ev.event_id] = body.replace("\n", " ")[:70]
+            token = getattr(resp, "end", None)
+            if not token:
+                break
+
+        to_redact = [(eid, snip) for eid, snip in cards.items() if eid not in open_ids]
+        print(f"bot cards found: {len(cards)}; resolved (to redact): {len(to_redact)}")
+        for eid, snip in to_redact:
+            print(("APPLY redact " if apply else "WOULD redact ") + eid + "  ::  " + snip)
+            if apply:
+                r = await client.room_redact(review_room, eid, reason="retroactive cleanup of resolved cards")
+                if not hasattr(r, "event_id"):
+                    print(f"   ! redact failed: {r}")
+        print(("done — redacted " if apply else "dry run — would redact ") + f"{len(to_redact)} card(s).")
+    finally:
+        await client.close()
+
+
+if __name__ == "__main__":
+    asyncio.run(main(apply="--apply" in sys.argv[1:]))