Matrix intake: frame parse with team roster so a teammate isn't read as the prospect

Local-smoke found "jonathan is chatting with wyoming" extracted the teammate, not
the prospect. Feed the parser an optional team roster (INTAKE_TEAM_ROSTER) via a
build_system(roster) outreach frame: roster names/initials are the people doing
outreach and are never extracted; the other party is the investor/prospect. Same
framing on the revise leg. Unset roster = prior behavior.

backend/matrix_intake/parse.py

@@ -15,7 +15,9 @@ 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"
+    "team member typed about their fundraising outreach. The message is a note FROM a "
+    "team member ABOUT an investor or prospect they are contacting. 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'
@@ -23,9 +25,31 @@ SYSTEM = (
     '  "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."
+    "Use null (not empty string) for anything not present."
 )
 
+# Appended when the team roster is known, so the model reads a teammate's name as the person
+# DOING the outreach, not the investor — fixes "Jonathan is chatting with Wyoming" extracting
+# the teammate instead of the prospect. Names come from settings.team_roster() (INTAKE_TEAM_ROSTER).
+ROSTER_FRAME = (
+    "These names and initials (case-insensitive) are our OWN team members — the people doing "
+    "the outreach, NOT investors or prospects. Never extract one as investor_name or "
+    "contact_name: {names}. When a team member is described talking with, meeting, or chasing "
+    'someone (e.g. "Jonathan is chatting with Wyoming"), the OTHER party (here "Wyoming") is '
+    "the investor or prospect to extract."
+)
+
+
+def build_system(roster=None, base=SYSTEM):
+    """Assemble the extraction system prompt. With a `roster` (team-member names) it appends
+    the outreach frame so a teammate's name is read as the person doing outreach, not the
+    investor. JSON-only stays the last line for recency. Pure + offline-testable."""
+    parts = [base]
+    if roster:
+        parts.append(ROSTER_FRAME.format(names=", ".join(roster)))
+    parts.append("Output JSON only.")
+    return "\n".join(parts)
+
 _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")
@@ -62,10 +86,11 @@ def normalize(raw, source_text=""):
     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).
+def parse_message(text, parse_fn=spark.parse_json, roster=None):
+    """Parse one intake message. `parse_fn` is injectable for tests (defaults to Spark/Qwen);
+    `roster` is the team-member names that frame the extraction (see build_system).
     Returns a normalized proposal dict. On a model/transport failure, raises (caller decides)."""
-    raw = parse_fn(text, system=SYSTEM, max_tokens=400)
+    raw = parse_fn(text, system=build_system(roster), max_tokens=400)
     proposal = normalize(raw, source_text=text)
     # Stash the original message so a later revise() can re-check email integrity against it.
     proposal["_source_text"] = text
@@ -79,7 +104,7 @@ REVISE_SYSTEM = (
     '  "investor_name", "contact_name", "contact_email", "contact_title", "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. Output JSON only."
+    "address."
 )
 
 _REVISABLE = ("investor_name", "contact_name", "contact_title", "note")
@@ -108,12 +133,13 @@ def _apply_revision(proposal, model_out, instruction):
     return out
 
 
-def revise(proposal, instruction, parse_fn=spark.parse_json):
+def revise(proposal, instruction, parse_fn=spark.parse_json, roster=None):
     """Apply a natural-language correction to a pending proposal via local Qwen; return the
-    revised proposal dict. `parse_fn` is injectable for tests (defaults to Spark/Qwen)."""
+    revised proposal dict. `parse_fn` is injectable for tests (defaults to Spark/Qwen);
+    `roster` frames the revision the same way parse_message does (see build_system)."""
     current = {k: proposal.get(k) for k in
                ("investor_name", "contact_name", "contact_email", "contact_title", "note")}
     prompt = ("CURRENT:\n" + json.dumps(current, ensure_ascii=False)
               + "\n\nINSTRUCTION:\n" + (instruction or "").strip())
-    raw = parse_fn(prompt, system=REVISE_SYSTEM, max_tokens=400)
+    raw = parse_fn(prompt, system=build_system(roster, base=REVISE_SYSTEM), max_tokens=400)
     return _apply_revision(proposal, raw, instruction)