Keysat
fd2e3ed78e
normalize()'s email regex matched non-@/non-space runs, so "Name <addr>" (the most common contact format) yielded "<addr"; only trailing punctuation was stripped, never leading. Tighten the regex to standard local@domain.tld so the bare address is extracted from <…>, (…), and trailing-period forms. Found via the live-deploy pre-flight. Add a regression test. Also log two intake backlog items in ROADMAP: the scoped service-credential auth path (deferred; bot uses a member login for now) and fuzzy match + in-thread confirm (post-deploy).
111 lines
3.9 KiB
Python
111 lines
3.9 KiB
Python
"""Tests for the intake parse/normalize layer — Spark/Qwen stubbed (no network)."""
|
|
import os
|
|
import sys
|
|
|
|
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
|
|
|
|
import parse # noqa: E402
|
|
|
|
|
|
def _stub(reply):
|
|
"""Return a parse_fn that ignores input and yields `reply` (simulating Qwen's JSON)."""
|
|
return lambda text, system=None, max_tokens=400: reply
|
|
|
|
|
|
def test_new_investor_basic():
|
|
p = parse.parse_message(
|
|
"New investor Acme Capital, contact Jane Doe jane@acme.com, met at the Austin conf",
|
|
parse_fn=_stub({"intent": "new_investor", "investor_name": "Acme Capital",
|
|
"contact_name": "Jane Doe", "contact_email": "jane@acme.com",
|
|
"contact_title": None, "note": "met at the Austin conf"}),
|
|
)
|
|
assert p["intent"] == "new_investor"
|
|
assert p["investor_name"] == "Acme Capital"
|
|
assert p["contact_email"] == "jane@acme.com"
|
|
|
|
|
|
def test_email_salvaged_from_source_when_model_misses():
|
|
p = parse.parse_message(
|
|
"add bob@example.org from Beta LP",
|
|
parse_fn=_stub({"intent": "new_investor", "investor_name": "Beta LP",
|
|
"contact_name": "Bob", "contact_email": None}),
|
|
)
|
|
assert p["contact_email"] == "bob@example.org"
|
|
|
|
|
|
def test_fabricated_email_dropped_when_not_in_source():
|
|
p = parse.parse_message(
|
|
"new prospect Gamma Partners, talked to their GP",
|
|
parse_fn=_stub({"intent": "new_investor", "investor_name": "Gamma Partners",
|
|
"contact_name": "their GP", "contact_email": "made-up@nowhere.test"}),
|
|
)
|
|
# the model invented an address that isn't in the source → must be dropped
|
|
assert p["contact_email"] is None
|
|
|
|
|
|
def test_email_extracted_without_surrounding_punctuation():
|
|
# "Name <addr>" is the most common contact format; parens / trailing period also occur.
|
|
# The salvage-from-source path must extract the bare address, never the brackets.
|
|
cases = [
|
|
("New investor: Larch Capital — Dana Reed <dana@larchcap.com>, met at conf", "dana@larchcap.com"),
|
|
("ping (sam@beta.io) re the deck", "sam@beta.io"),
|
|
("reach kim@acme.co.", "kim@acme.co"),
|
|
]
|
|
for src, expected in cases:
|
|
p = parse.parse_message(
|
|
src,
|
|
parse_fn=_stub({"intent": "new_investor", "investor_name": "X",
|
|
"contact_name": "Y", "contact_email": None}),
|
|
)
|
|
assert p["contact_email"] == expected, (src, p["contact_email"])
|
|
|
|
|
|
def test_meeting_note_intent_preserved():
|
|
p = parse.parse_message(
|
|
"Note for Acme Capital: wants the Q3 deck",
|
|
parse_fn=_stub({"intent": "meeting_note", "investor_name": "Acme Capital",
|
|
"note": "wants the Q3 deck"}),
|
|
)
|
|
assert p["intent"] == "meeting_note"
|
|
assert p["note"] == "wants the Q3 deck"
|
|
|
|
|
|
def test_unclear_when_no_entity():
|
|
p = parse.parse_message(
|
|
"hey what's up",
|
|
parse_fn=_stub({"intent": "new_investor", "investor_name": None, "contact_name": None}),
|
|
)
|
|
assert p["intent"] == "unclear"
|
|
|
|
|
|
def test_null_strings_normalized():
|
|
p = parse.parse_message(
|
|
"Delta Fund",
|
|
parse_fn=_stub({"intent": "new_investor", "investor_name": "Delta Fund",
|
|
"contact_name": "null", "contact_email": "N/A", "note": ""}),
|
|
)
|
|
assert p["contact_name"] is None
|
|
assert p["contact_email"] is None
|
|
assert p["note"] is None
|
|
|
|
|
|
def test_bad_intent_falls_back_to_unclear():
|
|
p = parse.parse_message(
|
|
"Epsilon Capital",
|
|
parse_fn=_stub({"intent": "garbage", "investor_name": "Epsilon Capital"}),
|
|
)
|
|
assert p["intent"] == "unclear"
|
|
|
|
|
|
def test_none_model_reply_is_unclear():
|
|
p = parse.parse_message("???", parse_fn=_stub(None))
|
|
assert p["intent"] == "unclear"
|
|
|
|
|
|
if __name__ == "__main__":
|
|
fns = [v for k, v in sorted(globals().items()) if k.startswith("test_") and callable(v)]
|
|
for fn in fns:
|
|
fn()
|
|
print(f"ok {fn.__name__}")
|
|
print(f"\n{len(fns)} passed")
|