outreach: voice by-purpose (larger sample) + Tier-B Gmail draft creation (v0.1.0:71)

(1) Voice: _voice_examples now picks the sender's prior sent emails OF THE SAME PURPOSE
(PURPOSE_PATTERNS keyword cues per outreach type), larger sample (8) weighted by purpose
then recency — not just recent. meta carries on_topic for transparency.

(2) Tier-B sending (gmail.compose now authorized in Workspace DWD). New
email_integration/compose.py create_outreach_draft: mints a compose-scoped DWD token for
the sender (credentials._mint/access_token_for parameterized by scope; GMAIL_COMPOSE_SCOPE),
builds an RFC822 message, and POSTs gmail.drafts.create into the SENDER's mailbox — as an
in-thread reply (threadId + In-Reply-To/References, recipient = matched LP address) when
there's an active thread, else a fresh email. NEVER sends — the human sends from Gmail
(guardrails #4, #6). Route POST /api/outreach/gmail-draft; UI "Create Gmail draft" button +
"Open Gmail Drafts" link. Tests: test_compose.py (parse/reply-target/RFC822+threading).
Message construction unit-verified; the live drafts.create runs on the box.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

backend/email_integration/test_compose.py

@@ -0,0 +1,62 @@
+#!/usr/bin/env python3
+"""Test the Gmail-draft message construction (the part that doesn't need live Gmail):
+subject/body parsing, reply-target resolution, and the RFC822 build incl. threading
+headers. The actual drafts.create call is exercised on the box. Synthetic data only.
+Run: cd backend && python3 email_integration/test_compose.py
+"""
+import base64
+import os
+import sqlite3
+import sys
+
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+from email_integration import compose as cp  # noqa: E402
+
+FAILS = []
+
+
+def check(cond, msg):
+    print(("  PASS " if cond else "  FAIL ") + msg)
+    if not cond:
+        FAILS.append(msg)
+
+
+def main():
+    s, b = cp._parse_subject_body("Subject: Following up\n\nHi Sarah,\n\nthanks for the call.")
+    check(s == "Following up" and b.startswith("Hi Sarah"), "parses 'Subject:' line + body")
+    s2, b2 = cp._parse_subject_body("No subject prefix here")
+    check(s2 == "" and b2 == "No subject prefix here", "no subject line -> empty subject, full body")
+
+    c = sqlite3.connect(":memory:")
+    c.row_factory = sqlite3.Row
+    c.executescript("""
+        CREATE TABLE emails(id TEXT, rfc_message_id TEXT, gmail_thread_id TEXT, sent_at TEXT, is_matched INT);
+        CREATE TABLE email_investor_links(email_id TEXT, fundraising_investor_id TEXT, matched_address TEXT);
+    """)
+    c.execute("INSERT INTO emails VALUES('e1','<m1@x>','t1','2026-06-01',1)")
+    c.execute("INSERT INTO email_investor_links VALUES('e1','inv1','lp@harborvine.example')")
+    c.commit()
+    t = cp._reply_target(c, "inv1")
+    check(t and t["to"] == "lp@harborvine.example" and t["thread_id"] == "t1" and t["in_reply_to"] == "<m1@x>",
+          "reply target resolves LP address + thread + in-reply-to")
+    check(cp._reply_target(c, "nope") is None, "no history -> no reply target")
+
+    raw = cp._build_raw("grant@ten31.xyz", "lp@x.example", "Hi", "Body text here", "<m1@x>")
+    dec = base64.urlsafe_b64decode(raw).decode("utf-8", "replace")
+    check("From: grant@ten31.xyz" in dec and "To: lp@x.example" in dec, "RFC822 has From + To")
+    check("Subject: Hi" in dec and "Body text here" in dec, "RFC822 has Subject + body")
+    check("In-Reply-To: <m1@x>" in dec and "References: <m1@x>" in dec, "threading headers set for replies")
+    raw2 = cp._build_raw("a@b.co", "c@d.co", "", "body", None)
+    dec2 = base64.urlsafe_b64decode(raw2).decode("utf-8", "replace")
+    check("Subject: (no subject)" in dec2 and "In-Reply-To" not in dec2, "no subject / no thread -> fresh email")
+
+    if FAILS:
+        print(f"\nFAILED ({len(FAILS)})")
+        for f in FAILS:
+            print("  - " + f)
+        sys.exit(1)
+    print("\nALL PASS (gmail compose message construction)")
+
+
+if __name__ == "__main__":
+    main()