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

@@ -108,16 +108,31 @@ _ROAD_RE = re.compile(
 )
 
 
+# Street-type synonyms collapsed to one token so "Mohegan Park Avenue" and
+# "Mohegan Park Ave" produce the same road id (server-26#115 — that one
+# difference was splitting a car-alarm incident into two).
+_ROAD_SUFFIX_CANON = {
+    "avenue": "ave", "street": "st", "road": "rd", "drive": "dr",
+    "boulevard": "blvd", "lane": "ln", "court": "ct", "place": "pl",
+    "highway": "hwy", "parkway": "pkwy",
+}
+
+
 def _extract_road_ids(text: str) -> set[str]:
     """
     Extract normalised road/route identifiers from a location string.
     e.g. "suspect east on Route 202" → {"route 202"}
-         "at Main Street and Oak Ave" → {"main street", "oak ave"}
+         "at Main Street and Oak Ave" → {"main st", "oak ave"}
     """
-    return {
+    ids: set[str] = set()
-        re.sub(r"[\s.\-]+", " ", m.group().lower()).strip()
+    for m in _ROAD_RE.finditer(text):
-        for m in _ROAD_RE.finditer(text)
+        key = re.sub(r"[\s.\-]+", " ", m.group().lower()).strip()
-    }
+        parts = key.split()
+        if parts and parts[-1] in _ROAD_SUFFIX_CANON:
+            parts[-1] = _ROAD_SUFFIX_CANON[parts[-1]]
+            key = " ".join(parts)
+        ids.add(key)
+    return ids
 
 
 def _location_mentions_road_overlap(new_location: str, inc_mentions: list[str]) -> bool:

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

@@ -45,7 +45,18 @@ def _fmt_idle(inc: dict, now: datetime) -> str:
 
 
 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,
+    # Mohegan Park Avenue" on the same channel were one incident — it defaulted
+    # to "new". Title is the single strongest human-readable signal for "is
+    # this the same event"; talkgroup is what makes same-channel continuation
+    # obvious.
     parts = [f"id:{inc['incident_id']}", f"type:{inc.get('type') or '?'}"]
+    tgs = inc.get("talkgroup_ids") or []
+    if tgs:
+        parts.append(f"tg:[{', '.join(str(t) for t in tgs[:3])}]")
+    if inc.get("title"):
+        parts.append(f"title:{inc['title']!r}")
     if inc.get("location"):
         parts.append(f"loc:{inc['location']}")
     units = inc.get("units") or []
@@ -80,19 +91,50 @@ 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["talkgroup_name"]:
+    if ctx["talkgroup_name"] or ctx.get("talkgroup_id") is not None:
-        lines.append(f"Talkgroup: {ctx['talkgroup_name']}")
+        # 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
+        # (server-26#115 review).
+        tgid = ctx.get("talkgroup_id")
+        name = ctx["talkgroup_name"] or "?"
+        lines.append(f"Talkgroup: {name}" + (f" (id {tgid})" if tgid is not None else ""))
     return "\n".join(lines) if lines else "(no details)"
 
 
+def _prompt_incidents(recent: list[dict]) -> list[dict]:
+    """The ≤20 candidates shown to the model, most-recently-active first.
+
+    `ctx["recent"]` is an unordered slice of a Firestore result with no
+    order_by, so a busy 2h window (~40 active incidents) meant the model saw
+    an arbitrary half of the candidates (server-26#115 review). Sorting by
+    updated_at desc also makes each row's `idle:` field monotonic.
+    """
+    def _key(inc: dict):
+        return str(inc.get("updated_at") or inc.get("started_at") or "")
+    return sorted(recent, key=_key, reverse=True)[:20]
+
+
 _SCHEMA = '{"action": "link" | "new" | "orphan", "incident_id": "<id_string or null>", "reasoning": "<one sentence>"}'
 
 _RULES = """
-Rules:
+Rules (this system OVER-SPLITS — a real incident routinely gets shattered into
-- "link" only with clear positive evidence: same units, same geocoded location, or semantically identical scene on the same talkgroup within the last few minutes.
+5-10 duplicates. A wrong link is cheap; a duplicate incident is the failure
-- A call on a DIFFERENT talkgroup than an incident requires unit overlap or geocoded location match — topic similarity alone is not enough.
+mode. Bias accordingly.):
-- "new" only if the call has a clear incident_type AND describes a distinct, identifiable scene.
+- Prefer "link" when the call plausibly continues a recent incident ON THE SAME
-- "orphan" when in doubt — conservative is always correct.
+  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.
+- 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.
+- "orphan" a call that is not an incident at all: radio checks, roll call,
+  a unit marking on/off duty or 10-8/10-98, mileage/log entries, a bare
+  acknowledgement. Do not open a "new" incident for these.
+- A call on a DIFFERENT talkgroup than an incident still requires unit overlap
+  or a geocoded/location match — topic similarity alone is not enough there.
 - Do NOT link just because both calls involve police or both mention a road.
 """
 
@@ -101,7 +143,7 @@ def _build_decide_prompt(ctx: dict) -> str:
     now    = ctx["now"]
     recent = ctx["recent"]
     inc_block = (
-        "\n".join(_inc_summary(inc, now) for inc in recent[:20])
+        "\n".join(_inc_summary(inc, now) for inc in _prompt_incidents(recent))
         if recent else "(none)"
     )
     return (
@@ -119,7 +161,7 @@ def _build_tiebreak_prompt(rules_decision: dict, llm_decision: dict, ctx: dict)
     now    = ctx["now"]
     recent = ctx["recent"]
     inc_block = (
-        "\n".join(_inc_summary(inc, now) for inc in recent[:20])
+        "\n".join(_inc_summary(inc, now) for inc in _prompt_incidents(recent))
         if recent else "(none)"
     )
 

drb-c2-core/tests/test_correlator_115.py

@@ -0,0 +1,67 @@
+"""
+server-26#115 — the tiebreaker manufactured incidents because it was blind to
+what would tell it two incidents are one.
+
+Two low-risk supports for the reframed prompt:
+  1. `_extract_road_ids` collapses street-type synonyms, so "Mohegan Park Ave"
+     and "Mohegan Park Avenue" share a road id (they were splitting one
+     car-alarm incident into two).
+  2. `_inc_summary` now carries the incident title and talkgroup, the two
+     signals the model needs to recognise a same-channel continuation.
+"""
+from datetime import datetime, timezone
+
+from app.internal.incident_correlator import (
+    _extract_road_ids, _location_mentions_road_overlap,
+)
+from app.internal.llm_correlator import _inc_summary, _prompt_incidents
+
+NOW = datetime(2026, 9, 7, 8, 0, 0, tzinfo=timezone.utc)
+
+
+def test_avenue_and_ave_are_the_same_road_id():
+    assert _extract_road_ids("Mohegan Park Avenue") == _extract_road_ids("Mohegan Park Ave")
+    assert _extract_road_ids("191 Broadway Street") == _extract_road_ids("191 Broadway St")
+    assert _extract_road_ids("North State Road") == _extract_road_ids("North State Rd")
+
+
+def test_road_overlap_matches_across_the_synonym():
+    assert _location_mentions_road_overlap("multiple car alarms Mohegan Park Avenue",
+                                           ["patrol to Mohegan Park Ave"]) is True
+    # still discriminates genuinely different streets
+    assert _location_mentions_road_overlap("Oak Avenue", ["Elm Avenue"]) is False
+
+
+def test_inc_summary_carries_title_and_talkgroup():
+    s = _inc_summary({
+        "incident_id": "abc123",
+        "type": "police",
+        "talkgroup_ids": [9560],
+        "title": "Nuisance Alarm at Mohegan Park Ave",
+        "location": "Mohegan Park Ave",
+        "units": ["Headquarters"],
+        "tags": ["car-alarm"],
+        "updated_at": NOW.isoformat(),
+    }, NOW)
+    assert "title:'Nuisance Alarm at Mohegan Park Ave'" in s
+    assert "tg:[9560]" in s
+    assert "id:abc123" in s
+
+
+def test_inc_summary_omits_missing_optional_fields():
+    s = _inc_summary({"incident_id": "x", "updated_at": NOW.isoformat()}, NOW)
+    assert "title:" not in s and "tg:" not in s and "loc:" not in s
+    assert s.startswith("id:x")
+
+
+def test_prompt_incidents_is_most_recently_active_first_and_capped():
+    recent = [
+        {"incident_id": f"i{n}", "updated_at": f"2026-09-07T0{n}:00:00+00:00"}
+        for n in range(1, 8)
+    ]
+    ordered = _prompt_incidents(recent)
+    assert [i["incident_id"] for i in ordered] == ["i7", "i6", "i5", "i4", "i3", "i2", "i1"]
+    assert len(_prompt_incidents(recent * 5)) == 20
+    # 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"