ten31-database/backend/mcp/test_outreach.py

#!/usr/bin/env python3
"""Test the outreach agent's context assembly: it pulls the investor's CRM notes +
recent matched email into the de-identifiable context block. Synthetic data only
(guardrail #9). The scrub/Claude/rehydrate round-trip is exercised live in the preview.
Run: cd backend && python3 mcp/test_outreach.py
"""
import os
import sqlite3
import sys
import tempfile

sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
import outreach_agent as oa  # noqa: E402

FAILS = []


def check(cond, msg):
    print(("  PASS " if cond else "  FAIL ") + msg)
    if not cond:
        FAILS.append(msg)


def main():
    db = os.path.join(tempfile.mkdtemp(), "t.db")
    c = sqlite3.connect(db)
    c.row_factory = sqlite3.Row
    c.executescript("""
        CREATE TABLE fundraising_investors (id TEXT PRIMARY KEY, investor_name TEXT, notes TEXT);
        CREATE TABLE emails (id TEXT PRIMARY KEY, subject TEXT, body_text TEXT, snippet TEXT, sent_at TEXT, is_matched INT);
        CREATE TABLE email_investor_links (id TEXT, email_id TEXT, fundraising_investor_id TEXT);
    """)
    c.execute("INSERT INTO fundraising_investors VALUES ('inv1','Harbor & Vine','Met at the conference; interested in Fund III.')")
    c.executemany("INSERT INTO emails (id,subject,body_text,sent_at,is_matched) VALUES (?,?,?,?,1)", [
        ("e1", "Re: Fund III", "Thanks for the call. We are still weighing the lock-up terms.", "2026-06-02T10:00:00"),
        ("e2", "Intro", "Good to meet you at the dinner.", "2026-05-01T10:00:00"),
        ("e3", "Spam", "ignore me", "2026-04-01T10:00:00"),  # not linked -> excluded
    ])
    c.executemany("INSERT INTO email_investor_links (id,email_id,fundraising_investor_id) VALUES (?,?, 'inv1')",
                  [("l1", "e1"), ("l2", "e2")])
    c.commit()

    name, ctx = oa._context(c, "inv1")
    check(name == "Harbor & Vine", f"resolves investor name (got {name!r})")
    check("Met at the conference" in ctx, "includes CRM notes")
    check("lock-up terms" in ctx, "includes matched email body")
    check("Good to meet you" in ctx, "includes a second matched email")
    check("ignore me" not in ctx, "excludes email not linked to this investor")
    check(ctx.index("lock-up terms") < ctx.index("Good to meet you"), "newest email first")

    n2, c2 = oa._context(c, "missing")
    check(n2 is None and c2 is None, "unknown investor -> (None, None)")

    # type catalogue is intact
    check(set(["intro", "follow_up", "fund_update", "meeting_follow_up", "nurture"]) <= set(oa.OUTREACH_TYPES),
          "outreach types catalogue present")

    # ── follow-up radar ──
    rc = sqlite3.connect(os.path.join(tempfile.mkdtemp(), "radar.db"))
    rc.row_factory = sqlite3.Row
    rc.executescript("""
        CREATE TABLE fundraising_investors (id TEXT PRIMARY KEY, investor_name TEXT, follow_up TEXT, graveyard TEXT);
        CREATE TABLE emails (id TEXT PRIMARY KEY, from_email TEXT, sent_at TEXT, is_matched INT);
        CREATE TABLE email_investor_links (id TEXT, email_id TEXT, fundraising_investor_id TEXT);
    """)
    rc.executemany("INSERT INTO fundraising_investors (id,investor_name,follow_up,graveyard) VALUES (?,?,?,?)", [
        ("owe", "Owe Reply LP", None, None),     # they emailed last, 5d ago -> tier 0
        ("warm", "Warm Quiet LP", None, None),   # we emailed last, 60d ago -> tier 2
        ("fresh", "Fresh LP", None, None),       # we emailed 4d ago -> not surfaced
        ("buried", "Buried LP", None, "1"),      # graveyard -> excluded
    ])
    OURS = "grant@ten31.xyz"
    em = [
        ("o1", "lp@owe.example", "2026-06-04T10:00:00", "owe"),     # inbound, 5 days before 06-09
        ("w1", OURS, "2026-04-10T10:00:00", "warm"),                # outbound, ~60 days
        ("w0", "lp@warm.example", "2026-04-01T10:00:00", "warm"),   # 2nd email for history
        ("f1", OURS, "2026-06-05T10:00:00", "fresh"),               # outbound, 4 days -> too recent
        ("b1", "lp@buried.example", "2026-01-01T10:00:00", "buried"),
    ]
    for eid, frm, sent, inv in em:
        rc.execute("INSERT INTO emails (id,from_email,sent_at,is_matched) VALUES (?,?,?,1)", (eid, frm, sent))
        rc.execute("INSERT INTO email_investor_links (id,email_id,fundraising_investor_id) VALUES (?,?,?)", (eid + "l", eid, inv))
    rc.commit()
    radar = oa.follow_up_radar(rc, [OURS], "2026-06-09T00:00:00", warm_days=45)
    names = [x["name"] for x in radar]
    check("Owe Reply LP" in names and "Warm Quiet LP" in names, f"surfaces owe-reply + warm-quiet (got {names})")
    check("Fresh LP" not in names, "recent contact not surfaced")
    check("Buried LP" not in names, "graveyard excluded")
    check(radar[0]["name"] == "Owe Reply LP" and radar[0]["tier"] == 0, "owe-a-reply ranked first (tier 0)")
    owe = next(x for x in radar if x["name"] == "Owe Reply LP")
    check("owe a reply" in owe["reason"] and owe["suggested_type"] == "follow_up", "owe-reply reason + suggested type")
    warm = next(x for x in radar if x["name"] == "Warm Quiet LP")
    check(warm["tier"] == 2 and warm["suggested_type"] == "nurture", "warm-quiet is tier 2, suggests nurture")

    if FAILS:
        print(f"\nFAILED ({len(FAILS)})")
        for f in FAILS:
            print("  - " + f)
        sys.exit(1)
    print("\nALL PASS (outreach context assembly)")


if __name__ == "__main__":
    main()