Restrict comms_by_user/email_counts_by_user to matched-investor email

Both NL-query intents counted/listed a user's ENTIRE captured sent corpus
(internal, vendor, personal mail) rather than only email to a matched investor
— they were missing the `EXISTS email_investor_links` gate that recent_emails
and the Communications panel's query_email_activity use. Their own docstrings
said "investor emails", so the behavior was wrong, not just loose.

Add the matched-only gate to both, mirroring query_email_activity. The runner
test now seeds an unmatched sent email and asserts it is excluded (without the
fix comms_by_user returns 3 not 2, this_week 2 not 1) — the prior fixture
linked every email, so the leak went uncaught.

Also documents the matched-only rule in the nl-query guide, and refreshes the
AGENTS.md Current state (v93 deployed; this fix pending a v94 s9pk since the
intents run on the box, not the bot).

backend/nl_query/intents.py

@@ -306,8 +306,11 @@ def run_investor_last_contact(conn, slots):
 
 
 def run_comms_by_user(conn, slots):
-    """The most recent `limit` outbound investor emails sent by a given user (matched by
-    username or full name). Soft-delete-correct (live sighting, is_sent)."""
+    """The most recent `limit` outbound **investor** emails sent by a given user (matched by
+    username or full name). MATCHED-ONLY: restricted to investor-linked email (an
+    email_investor_links row exists), mirroring query_email_activity / recent_emails — NOT the
+    user's entire sent corpus (internal/vendor/personal mail is captured but never surfaced
+    here). Soft-delete-correct (live sighting, is_sent)."""
     n, pat = slots["limit"], like_contains(slots["user"])
     rows = _rows(conn.execute(
         "SELECT e.subject, e.sent_at, u.full_name AS sender, "
@@ -318,6 +321,7 @@ def run_comms_by_user(conn, slots):
         "AND eam.deleted_at IS NULL AND eam.is_sent = 1 "
         "JOIN email_accounts ea ON ea.id = eam.account_id JOIN users u ON u.id = ea.user_id "
         "WHERE (u.username LIKE ? ESCAPE '\\' OR u.full_name LIKE ? ESCAPE '\\') "
+        "AND EXISTS (SELECT 1 FROM email_investor_links l2 WHERE l2.email_id = e.id) "
         "ORDER BY e.sent_at DESC LIMIT ?", (pat, pat, n)))
     return {"columns": ["sent_at", "subject", "sender", "investor"], "rows": rows,
             "truncated": False,
@@ -325,13 +329,16 @@ def run_comms_by_user(conn, slots):
 
 
 def run_email_counts_by_user(conn, slots):
-    """Per-user counts of outbound investor emails over this week / month / year-to-date.
+    """Per-user counts of outbound **investor** emails over this week / month / year-to-date.
+    MATCHED-ONLY: counts only investor-linked email (an email_investor_links row exists),
+    mirroring query_email_activity / recent_emails — not the user's entire sent corpus.
     Windows are calendar-based: week = since Monday, month = since the 1st, ytd = since Jan 1."""
     today = _today()
     wk = (today - timedelta(days=today.weekday())).isoformat()
     mo = today.replace(day=1).isoformat()
     yr = today.replace(month=1, day=1).isoformat()
-    where = "WHERE eam.deleted_at IS NULL AND eam.is_sent = 1"
+    where = ("WHERE eam.deleted_at IS NULL AND eam.is_sent = 1 "
+             "AND EXISTS (SELECT 1 FROM email_investor_links l WHERE l.email_id = e.id)")
     params = [wk, mo, yr]
     if slots.get("user"):
         pat = like_contains(slots["user"])

backend/nl_query/test_nl_query.py

@@ -101,6 +101,15 @@ def seed(conn):
     email("edel", "grant@ten31.xyz", "Grant Smith", 0, "i_beta", "a_grant", 1, deleted=True)  # tombstoned
     email("ej", "jon@ten31.xyz", "Jonathan Lee", 0, "i_acme", "a_jon", 1)             # jonathan today
     email("ein", "alice@acme.com", "Alice Acme", 3, "i_acme", "a_grant", 0)           # inbound 3d
+    # an UNMATCHED sent email by Grant (NO email_investor_links row) — captured, but not to a
+    # known investor. The investor-email intents are matched-only, so it must be EXCLUDED from
+    # comms_by_user / email_counts_by_user; without the matched-only filter it would inflate both.
+    c("INSERT INTO emails (id, rfc_message_id, from_email, from_name, sent_at, subject, "
+      "is_matched, match_status) VALUES ('eunm','rfc_eunm','grant@ten31.xyz','Grant Smith',?,"
+      "'Internal: team lunch',0,'unmatched')", (_ago(0),))
+    c("INSERT INTO email_account_messages (id, email_id, account_id, gmail_message_id, "
+      "gmail_thread_id, is_sent, deleted_at) VALUES "
+      "('eam_eunm','eunm','a_grant','g_eunm','t_eunm',1,NULL)")
 
     # communications (the other recency leg) — Delta has ONLY comms: one live (5d), one tombstoned
     # (today). If the soft-delete filter broke, Delta would read as contacted today.
@@ -187,9 +196,10 @@ def main():
     r = run("investor_last_contact", {"name": "beta"})
     check(r["rows"][0]["days_since"] >= 39, "investor_last_contact days_since")
     check(run("comms_by_user", {"user": "Grant"})["row_count"] == 2,
-          "comms_by_user: grant's 2 live outbound (tombstoned excluded)")
+          "comms_by_user: grant's 2 live MATCHED outbound (tombstoned + unmatched excluded)")
     r = run("email_counts_by_user", {"user": "grant"})
-    check(r["rows"][0]["this_week"] == 1, "email_counts this_week = 1 live (tombstoned excluded)")
+    check(r["rows"][0]["this_week"] == 1,
+          "email_counts this_week = 1 live matched (tombstoned + unmatched excluded)")
     check(r["rows"][0]["ytd"] >= 1, "email_counts ytd")
 
     print("trust boundary")