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).
64 lines
2.9 KiB
Python
64 lines
2.9 KiB
Python
"""Turn a free-text intake message into a normalized proposal via local Qwen.
|
|
|
|
The model only EXTRACTS structure; it never decides to write anything. New-vs-existing is
|
|
finalized in M2 against the CRM matcher — here `intent` is the model's first read.
|
|
"""
|
|
import re
|
|
|
|
import spark
|
|
|
|
SYSTEM = (
|
|
"You extract structured investor-intake data from a short message a venture-fund "
|
|
"team member typed. Reply with ONLY a JSON object, no prose, with these keys:\n"
|
|
' "intent": "new_investor" if the message introduces a new investor or prospect, '
|
|
'"meeting_note" if it logs a note/update about an investor, else "unclear".\n'
|
|
' "investor_name": the investing firm or entity name (e.g. "Acme Capital"), or null.\n'
|
|
' "contact_name": the individual person mentioned, or null.\n'
|
|
' "contact_email": the person\'s email if explicitly present, else null. Never invent one.\n'
|
|
' "contact_title": the person\'s role/title if stated, else null.\n'
|
|
' "note": any meeting note, context, or next step, else null.\n'
|
|
"Use null (not empty string) for anything not present. Output JSON only."
|
|
)
|
|
|
|
_EMAIL_RE = re.compile(r"[A-Za-z0-9._%+\-]+@[A-Za-z0-9.\-]+\.[A-Za-z]{2,}")
|
|
_VALID_INTENTS = {"new_investor", "meeting_note", "unclear"}
|
|
_FIELDS = ("intent", "investor_name", "contact_name", "contact_email", "contact_title", "note")
|
|
|
|
|
|
def _clean(v):
|
|
if v is None:
|
|
return None
|
|
s = str(v).strip()
|
|
if not s or s.lower() in ("null", "none", "n/a", "na", "unknown"):
|
|
return None
|
|
return s
|
|
|
|
|
|
def normalize(raw, source_text=""):
|
|
"""Coerce the model's dict into a stable proposal shape; salvage an email from the
|
|
source text if the model missed one. Returns a dict with all _FIELDS keys."""
|
|
raw = raw or {}
|
|
out = {k: _clean(raw.get(k)) for k in _FIELDS}
|
|
|
|
intent = (out["intent"] or "").lower().replace("-", "_").replace(" ", "_")
|
|
out["intent"] = intent if intent in _VALID_INTENTS else "unclear"
|
|
|
|
# Email integrity: only accept an address that literally appears in the source message.
|
|
# The model is unreliable for verbatim strings and must never mint an address — anything
|
|
# not present in what the human typed is dropped (a wrong email in the CRM is worse than
|
|
# none). This both salvages a missed address and rejects a hallucinated one.
|
|
m = _EMAIL_RE.search(source_text or "")
|
|
out["contact_email"] = m.group(0).rstrip(".,;:!?)]}>\"'") if m else None
|
|
|
|
# An intake with no firm AND no person is not actionable.
|
|
if not out["investor_name"] and not out["contact_name"]:
|
|
out["intent"] = "unclear"
|
|
return out
|
|
|
|
|
|
def parse_message(text, parse_fn=spark.parse_json):
|
|
"""Parse one intake message. `parse_fn` is injectable for tests (defaults to Spark/Qwen).
|
|
Returns a normalized proposal dict. On a model/transport failure, raises (caller decides)."""
|
|
raw = parse_fn(text, system=SYSTEM, max_tokens=400)
|
|
return normalize(raw, source_text=text)
|