correlator: fix consensus orphan-gate to test call substance, not empty corr_debug (#115)

The gate added in ca1d8fb checked rules_decision["corr_debug"] for a positive
signal, but that dict is empty at preview time for action=="new" (corr_path is
written at apply time). The check was always False, so the gate fired on real
events — replayed against corr_dump_9-7_pm.json it dropped ~36 linked calls
including a major "extinguishing fire", a moderate fire-alarm, geocoded calls
and pursuit updates.

Gate now runs against ctx (fully populated at preview time). It fires ONLY when
the call is substanceless: routine severity, no vehicle/geocode/tag, and no
incident already running on the same talkgroup. Any of those escalates to the
tiebreak instead. The substance predicate (has_event_substance) is factored out
of incident_correlator's creation gate and shared, so the two cannot diverge.

recorrelation_sweep: a call the gate parked gets a longer link-only retry budget
(10 vs 3) — the gate fires before any incident for the job exists, so the
substantive call that justifies linking can land after the standard ~6 min.
Still create_if_new=False.

incident_correlator location path: evaluate every in-radius candidate and link
the nearest that carries corroboration, instead of the first in an unsorted
`recent`. A unit-overlap location link is now tagged "location_unit_overlap" so
it stops merging into the fast path's bucket in the admin fit-signal histogram.

tests/test_consensus_gate.py: replaced the corr_debug-signal cases with ctx
substance cases (severity, coords, tags, vehicles, same-tg incident); added a
nearest-wins location test; the two location guard tests now assert they reach
the new guard. Full drb-c2-core suite 322 -> 325.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tbknwttzou4s46PAykmtix
This commit is contained in:
Logan Cusano
2026-09-07 23:50:41 -04:00
co-authored by Claude Sonnet 5
parent ca1d8fbdae
commit dd426572fc
4 changed files with 290 additions and 119 deletions
+62 -34
View File
@@ -246,6 +246,22 @@ def _matching_units(call_units: Optional[list[str]], inc_units: Optional[list[st
return [u for u in (call_units or []) if _normalize_unit(u) in inc_keys]
def has_event_substance(ctx: dict) -> bool:
"""
True when the call carries content beyond who-was-speaking-and-where:
a vehicle, a geocode, or a tag.
This is the substance half of the incident-creation gate (see
`_run_decision`, "Severity, not type, decides..."), factored out so the
consensus LLM-orphan gate in routers/upload.py mirrors it exactly and can
never drop a call the creation gate would have opened. `call_units` and
`location` are deliberately excluded — radio protocol puts a unit ID and a
place name in almost every transmission, so counting them as substance
makes the check trivially true.
"""
return bool(ctx.get("call_vehicles") or ctx.get("coords") or ctx.get("tags"))
def _infer_type_from_tags(tags: list[str]) -> Optional[str]:
"""Return an incident type inferred from tags, or None if ambiguous."""
for tag in tags:
@@ -1180,6 +1196,10 @@ def _run_decision(ctx: dict) -> dict:
# ── 2. Location path: proximity match (time-limited, cross-type) ─────────
if not matched_incident and coords:
# server-26#115 — score every in-radius candidate and link the NEAREST
# that carries corroboration, rather than whichever incident happened to
# come first in an unsorted `recent`.
loc_candidates: list[tuple] = []
for inc in recent:
inc_coords = inc.get("location_coords")
if not inc_coords:
@@ -1196,41 +1216,49 @@ def _run_decision(ctx: dict) -> dict:
elapsed_min = max(_incident_idle_minutes(inc, now), 0.1)
if (dist_km / elapsed_min) > _MAX_PURSUIT_SPEED_KM_PER_MIN:
continue # implausible speed — skip this candidate
if dist_km <= radius:
# server-26#115 — a bare sub-radius distance is not enough on its
# own. Require corroboration: unit overlap with the candidate, OR
# a much tighter proximity. Pursuit incidents keep their
# movement-speed-validated wide radius (they passed the speed
# check above), so they are exempt.
unit_overlap = bool(
_unit_keys(call_units) & _unit_keys(inc.get("units"))
)
tight_proximity = dist_km <= _LOCATION_TIGHT_PROXIMITY_KM
if not (is_pursuit_inc or unit_overlap or tight_proximity):
logger.info(
f"Correlator location-path skipped: call {call_id} vs "
f"{inc['incident_id']} — dist={dist_km:.2f}km within radius "
f"but no unit overlap and not tight-proximity "
f"(<= {_LOCATION_TIGHT_PROXIMITY_KM}km)"
)
continue
matched_incident = inc
fit_signal = "unit_overlap" if unit_overlap else "location_proximity"
corr_debug = {
"corr_path": "location",
"corr_distance_km": round(dist_km, 3),
"corr_pursuit_mode": is_pursuit_inc,
"corr_fit_signal": fit_signal,
}
if unit_overlap and call_units:
corr_debug["corr_matched_units"] = _matching_units(
call_units, inc.get("units")
)
if dist_km > radius:
continue
# server-26#115 — a bare sub-radius distance is not enough on its
# own. Require corroboration: unit overlap with the candidate, OR
# a much tighter proximity. Pursuit incidents keep their
# movement-speed-validated wide radius (they passed the speed
# check above), so they are exempt.
unit_overlap = bool(
_unit_keys(call_units) & _unit_keys(inc.get("units"))
)
tight_proximity = dist_km <= _LOCATION_TIGHT_PROXIMITY_KM
if not (is_pursuit_inc or unit_overlap or tight_proximity):
logger.info(
f"Correlator location-path: call {call_id} → {inc['incident_id']} "
f"(dist={dist_km:.2f}km, pursuit={is_pursuit_inc}, signal={fit_signal})"
f"Correlator location-path skipped: call {call_id} vs "
f"{inc['incident_id']} — dist={dist_km:.2f}km within radius "
f"but no unit overlap and not tight-proximity "
f"(<= {_LOCATION_TIGHT_PROXIMITY_KM}km)"
)
break
continue
loc_candidates.append((dist_km, unit_overlap, is_pursuit_inc, inc))
if loc_candidates:
loc_candidates.sort(key=lambda c: c[0])
dist_km, unit_overlap, is_pursuit_inc, inc = loc_candidates[0]
matched_incident = inc
# Distinct from the fast path's "unit_overlap" so the admin
# corr_fit_signal histogram (routers/admin.py) does not merge a
# location-path link into the fast-path bucket (#35).
fit_signal = "location_unit_overlap" if unit_overlap else "location_proximity"
corr_debug = {
"corr_path": "location",
"corr_distance_km": round(dist_km, 3),
"corr_pursuit_mode": is_pursuit_inc,
"corr_fit_signal": fit_signal,
}
if unit_overlap and call_units:
corr_debug["corr_matched_units"] = _matching_units(
call_units, inc.get("units")
)
logger.info(
f"Correlator location-path: call {call_id} → {inc['incident_id']} "
f"(dist={dist_km:.2f}km, pursuit={is_pursuit_inc}, signal={fit_signal})"
)
# ── 2.5. Cross-TG path: same department, overlapping units, moderate similarity ──
#
@@ -1367,7 +1395,7 @@ def _run_decision(ctx: dict) -> dict:
# each. A vehicle, a geocode, or a tag means the extractor found something
# beyond who was speaking and where they stood.
if not resolved_type:
has_substance = bool(call_vehicles or coords or tags)
has_substance = has_event_substance(ctx)
if call_severity in ("minor", "moderate", "major") or has_substance:
resolved_type = "other"
logger.info(
@@ -20,6 +20,22 @@ from app.internal.logger import logger
from app.internal import firestore as fstore
from app.config import settings
# Standard link-only retry budget before a call is tombstoned corr_path="unlinked".
MAX_SWEEP_ATTEMPTS = 3
# server-26#115 — a call the consensus LLM-orphan gate parked (llm=orphan vs
# rules=new, no substance) gets a longer budget. The gate fires before any
# incident for the job may exist, so the substantive call that would justify
# linking can land well after the standard ~6 min. Still link-only: a genuinely
# thin call must not mint an incident, and the rules creation gate would re-orphan
# it anyway.
GATED_ORPHAN_SWEEP_ATTEMPTS = 10
def _max_sweep_attempts(call: dict) -> int:
if call.get("corr_consensus") == "llm_orphan_gate":
return GATED_ORPHAN_SWEEP_ATTEMPTS
return MAX_SWEEP_ATTEMPTS
async def recorrelation_loop() -> None:
interval = settings.summary_interval_minutes * 60
@@ -46,10 +62,9 @@ async def _run_sweep_pass() -> None:
("status", "==", "ended"),
("ended_at", ">=", cutoff),
])
# corr_path="unlinked" is written after MAX_SWEEP_ATTEMPTS failures.
# corr_path="unlinked" is written after the attempt budget is exhausted.
# Allows a few retries so a welfare-check call can link to an escalation
# incident that is created a few minutes later, without sweeping 30× forever.
MAX_SWEEP_ATTEMPTS = 3
orphans = [
c for c in recent_ended
if not c.get("incident_ids") and not c.get("incident_id")
@@ -61,7 +76,7 @@ async def _run_sweep_pass() -> None:
# the thin path minutes later and attached to whatever was most recent —
# a second route into the over-merge the thin fix above addresses.
and not c.get("skip_reason")
and c.get("corr_sweep_count", 0) < MAX_SWEEP_ATTEMPTS
and c.get("corr_sweep_count", 0) < _max_sweep_attempts(c)
]
if not orphans:
@@ -120,12 +135,12 @@ async def _recorrelate_orphan(call: dict) -> bool:
)
return True
# Increment the attempt counter. Once MAX_SWEEP_ATTEMPTS is reached the
# orphan filter above will stop picking this call up, and we write
# corr_path="unlinked" as a permanent tombstone.
# Increment the attempt counter. Once the budget is reached the orphan filter
# above will stop picking this call up, and we write corr_path="unlinked" as
# a permanent tombstone.
attempts = call.get("corr_sweep_count", 0) + 1
update: dict = {"corr_sweep_count": attempts}
if attempts >= 3:
if attempts >= _max_sweep_attempts(call):
update["corr_path"] = "unlinked"
await fstore.doc_set("calls", call_id, update)
return False