Capture city + LinkedIn on card intake; sharpen the transcription prompt

The card transcription prompt now reads emails/URLs/phones character-by-character,
explicitly forbids autocompleting toward a plausible domain (the mara.com ->
marac.com failure), and emits labeled lines (which also feeds the field extractor
cleaner input).

The extractor gains city + linkedin_url. city is a plain field (low-harm if wrong;
the human sees it on the card). linkedin_url follows the email-integrity rule: kept
only if it literally appears in the source / a revise instruction, never minted -- a
wrong profile URL points at the wrong person. Both flow to the contact via the
existing log-communication upsert (city also syncs to the grid contact pill).

Phone is intentionally NOT included yet: the bot's write path can't store it until a
small server-side change lands (next s9pk). See the matrix-intake guide.

backend/matrix_intake/parse.py

@@ -24,6 +24,8 @@ SYSTEM = (
     '  "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'
+    '  "city": the person\'s city or location if stated (e.g. "New York"), else null.\n'
+    '  "linkedin_url": the person\'s LinkedIn URL if explicitly present, else null. Never invent one.\n'
     '  "note": any meeting note, context, or next step, else null.\n'
     "Use null (not empty string) for anything not present."
 )
@@ -51,8 +53,10 @@ def build_system(roster=None, base=SYSTEM):
     return "\n".join(parts)
 
 _EMAIL_RE = re.compile(r"[A-Za-z0-9._%+\-]+@[A-Za-z0-9.\-]+\.[A-Za-z]{2,}")
+_LINKEDIN_RE = re.compile(r"(?:https?://)?(?:[a-z]{2,3}\.)?linkedin\.com/[A-Za-z0-9_%/\-.]+", re.I)
 _VALID_INTENTS = {"new_investor", "meeting_note", "unclear"}
-_FIELDS = ("intent", "investor_name", "contact_name", "contact_email", "contact_title", "note")
+_FIELDS = ("intent", "investor_name", "contact_name", "contact_email", "contact_title",
+           "city", "linkedin_url", "note")
 
 
 def _clean(v):
@@ -80,6 +84,14 @@ def normalize(raw, source_text=""):
     m = _EMAIL_RE.search(source_text or "")
     out["contact_email"] = m.group(0).rstrip(".,;:!?)]}>\"'") if m else None
 
+    # LinkedIn integrity: same rule as email — a profile URL identifies a specific person, so
+    # never let the model mint one; keep only a linkedin.com URL literally present in the source.
+    lm = _LINKEDIN_RE.search(source_text or "")
+    out["linkedin_url"] = lm.group(0).rstrip(".,;:!?)]}>\"'") if lm else None
+
+    # City is left as a plain extracted field (no source gate): a wrong city is low-harm and the
+    # human sees it on the card before approving, unlike a wrong email/LinkedIn.
+
     # An intake with no firm AND no person is not actionable.
     if not out["investor_name"] and not out["contact_name"]:
         out["intent"] = "unclear"
@@ -101,13 +113,14 @@ REVISE_SYSTEM = (
     "You revise a structured investor-intake proposal from a short correction a venture-fund "
     "team member typed. You are given the CURRENT proposal as JSON and an INSTRUCTION. Apply "
     "the instruction and reply with ONLY the full revised JSON object, these keys:\n"
-    '  "investor_name", "contact_name", "contact_email", "contact_title", "note".\n'
+    '  "investor_name", "contact_name", "contact_email", "contact_title", "city", '
+    '"linkedin_url", "note".\n'
     "Change ONLY what the instruction asks; copy every other field through unchanged. Use null "
     "for a field the instruction clears or that is genuinely absent. Never invent an email "
-    "address."
+    "address or a LinkedIn URL."
 )
 
-_REVISABLE = ("investor_name", "contact_name", "contact_title", "note")
+_REVISABLE = ("investor_name", "contact_name", "contact_title", "city", "note")
 
 
 def _apply_revision(proposal, model_out, instruction):
@@ -126,6 +139,10 @@ def _apply_revision(proposal, model_out, instruction):
     if m:
         out["contact_email"] = m.group(0).rstrip(".,;:!?)]}>\"'")
     # else: keep proposal's current contact_email (untouched above; control key copied by dict())
+    # LinkedIn follows the same rule: a revised URL is taken only if it appears in the instruction.
+    lm = _LINKEDIN_RE.search(instruction or "")
+    if lm:
+        out["linkedin_url"] = lm.group(0).rstrip(".,;:!?)]}>\"'")
     # Don't let a revision strip the proposal down to nothing actionable.
     if not out.get("investor_name") and not out.get("contact_name"):
         out["investor_name"] = proposal.get("investor_name")