drb-c2-core/app/internal/llm_correlator.py

@@ -31,18 +31,24 @@ from app.config import settings
 # Prompt helpers
 # ─────────────────────────────────────────────────────────────────────────────
 
-def _fmt_idle(inc: dict, now: datetime) -> str:
+def _fmt_since(raw, now: datetime) -> str:
     try:
-        raw = inc.get("updated_at") or inc.get("started_at") or ""
-        dt  = datetime.fromisoformat(str(raw).replace("Z", "+00:00"))
+        dt  = datetime.fromisoformat(str(raw or "").replace("Z", "+00:00"))
         if dt.tzinfo is None:
             dt = dt.replace(tzinfo=timezone.utc)
-        minutes = int((now - dt).total_seconds() / 60)
-        return f"{minutes}min ago" if minutes < 60 else f"{minutes // 60}h{minutes % 60:02d}m ago"
+        # Clamped: the recorrelation sweep back-dates `now` (see
+        # _idle_gate_minutes), which would otherwise print "-12min".
+        minutes = max(int((now - dt).total_seconds() / 60), 0)
+        return f"{minutes}min" if minutes < 60 else f"{minutes // 60}h{minutes % 60:02d}m"
     except Exception:
         return "?"
 
 
+def _fmt_idle(inc: dict, now: datetime) -> str:
+    since = _fmt_since(inc.get("updated_at") or inc.get("started_at"), now)
+    return since if since == "?" else f"{since} ago"
+
+
 def _inc_summary(inc: dict, now: datetime) -> str:
     # server-26#115: the model was given no title and no talkgroup, so it
     # could not tell that "car alarms, Mohegan Park Ave" and "car alarms,
@@ -65,6 +71,19 @@ def _inc_summary(inc: dict, now: datetime) -> str:
     if tags:
         parts.append(f"tags:[{', '.join(tags[:4])}]")
     parts.append(f"idle:{_fmt_idle(inc, now)}")
+    # server-26#189: idle alone made a 2.5h-old job look as fresh as a
+    # 5-minute one — every link resets idle, so a busy channel's oldest
+    # incident always reads "2min ago" and keeps winning. Age and size let
+    # the model see it has become a catch-all.
+    if inc.get("started_at"):
+        from app.internal.incident_correlator import _incident_span_minutes
+        span = int(_incident_span_minutes(inc, now))
+        parts.append(f"open:{span}min" if span < 60 else f"open:{span // 60}h{span % 60:02d}m")
+    n_calls = inc.get("substantive_call_count")
+    if n_calls is None:
+        n_calls = len(inc.get("call_ids") or [])
+    if n_calls:
+        parts.append(f"calls:{n_calls}")
     return " | ".join(parts)
 
 
@@ -90,6 +109,8 @@ def _call_block(ctx: dict) -> str:
         lines.append(f"Units: {ctx['call_units']}")
     if ctx["call_vehicles"]:
         lines.append(f"Vehicles: {ctx['call_vehicles']}")
+    if ctx.get("reassignment"):
+        lines.append("Reassignment: yes — a unit is being sent to a NEW job")
     if ctx["talkgroup_name"] or ctx.get("talkgroup_id") is not None:
         # Both the name and the id — _inc_summary emits numeric tg ids, so the
         # id is what makes the "same talkgroup" rule in _RULES evaluable
@@ -116,16 +137,23 @@ def _prompt_incidents(recent: list[dict]) -> list[dict]:
 _SCHEMA = '{"action": "link" | "new" | "orphan", "incident_id": "<id_string or null>", "reasoning": "<one sentence>"}'
 
 _RULES = """
-Rules (this system OVER-SPLITS — a real incident routinely gets shattered into
-5-10 duplicates. A wrong link is cheap; a duplicate incident is the failure
-mode. Bias accordingly.):
+Rules (this system usually OVER-SPLITS — a real incident often gets shattered
+into 5-10 duplicates, so lean toward "link" for follow-ups. The exception is a
+call that reports a new event, below.):
 - Prefer "link" when the call plausibly continues a recent incident ON THE SAME
-  TALKGROUP: same or overlapping units, the same or an adjacent location (treat
-  "Ave"/"Avenue", "St"/"Street", "Rd"/"Road" as identical; a house number plus
-  the same street is the same place), the same subject/vehicle/case number, or a
-  follow-up beat ("units clearing", "negative contact", "tow en route", "event
-  number 214-201", a status update) to an incident that is only a few minutes
-  idle. The bar for "link" on the same talkgroup is LOW.
+  TALKGROUP: the same or an adjacent location (treat "Ave"/"Avenue",
+  "St"/"Street", "Rd"/"Road" as identical; a house number plus the same street
+  is the same place), the same subject/vehicle/case number, or a follow-up beat
+  ("units clearing", "negative contact", "tow en route", "event number
+  214-201", a status update) from units already on it. The bar for "link" on
+  the same talkgroup is LOW for follow-ups.
+- EXCEPT: a call that REPORTS an event is "new" unless it names the same place
+  or subject as the incident: "another accident", "a second MVA", "getting
+  flagged down for", "just got a report of", "respond to <address>", a
+  reassignment. Patrol units on a shared channel work many jobs back to back,
+  so a unit already on an incident is not evidence that its next job is the
+  same one — especially once that incident has been open a long time (see
+  open:/calls:).
 - Reserve "new" for a call that clearly describes a DIFFERENT event from every
   recent incident — a different place, different units, and a different subject,
   not merely a different transmission about the same job.

drb-c2-core/tests/test_correlator_115.py

@@ -65,3 +65,16 @@ def test_prompt_incidents_is_most_recently_active_first_and_capped():
     # falls back to started_at when updated_at is absent, and never raises
     assert _prompt_incidents([{"incident_id": "a", "started_at": NOW.isoformat()},
                               {"incident_id": "b"}])[0]["incident_id"] == "a"
+
+
+def test_inc_summary_shows_age_and_size_not_just_idle():
+    # server-26#189: every link resets idle, so a 2.5h catch-all read as fresh.
+    s = _inc_summary({
+        "incident_id": "sink",
+        "started_at": "2026-09-07T05:26:00+00:00",
+        "updated_at": "2026-09-07T07:58:00+00:00",
+        "call_ids": [f"c{n}" for n in range(40)],
+    }, NOW)
+    assert "idle:2min ago" in s
+    assert "open:2h34m" in s
+    assert "calls:40" in s