correlator/intelligence: close the incident-clearance gap (dispatch-to-10-8 lifecycle)

Two independent fixes, found by tracing why incidents never actually close
(only 2/281 incidents in 5 correlation debug windows ever got a non-empty
units_cleared; 183 resolved via the 90-min idle sweep instead of a real clear):

1. Pattern B (re-dispatch accept, no explicit 10-8): reassignment=True already
   fired correctly and suppressed the unit from re-linking to its prior
   incident, but nothing ever released the unit FROM that incident — it just
   sat "active" until the idle sweep timed it out. _release_reassigned_units
   now scans other active incidents for unit overlap on a reassignment and
   clears the unit there, reusing the same units_active/units_cleared merge
   (factored out as _apply_unit_clearance) that explicit 10-8 extraction uses.

2. Pattern A (self-clear) extraction was inconsistent for two reasons: no
   per-system unit ID format awareness anywhere in the pipeline (formats vary
   by department with zero shared convention), and the cleared_units prompt
   rule only accepted a unit self-reporting, missing dispatch confirming a
   unit's status back to them. Added system.unit_format_hint (owner-authored
   free text, GET/PUT /systems/{id}/unit-format, no auto-induction yet) fed
   into the extraction prompt, and broadened the cleared_units rule while
   still requiring an identifiable unit ID (guards against bare "10-8"/"clear"
   noise, including Whisper hallucination runs already caught upstream by
   _is_garbage_transcript).

Verified: 401 pass, 0 fail (local Linux venv ~/venvs/drb-5c — see CLAUDE.md
testing-reality note).

server-26#pending — not yet filed, Gitea unreachable from this sandbox.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

drb-c2-core/tests/test_correlator_reassignment_clearance.py

@@ -0,0 +1,198 @@
+"""
+server-26#<pending> — pattern B clearance: a unit accepting a NEW dispatch
+("dispatch: are you able to clear and take a run at X / unit: 10-4") carries
+no self-reported clearance language intelligence.py's cleared_units
+extraction looks for (that only catches pattern A, "Unit 7, 10-8"). Before
+this fix, reassignment=True only ever suppressed the unit from re-linking to
+their prior incident (upload.py's corr_units=[] on reassignment) — nothing
+ever released them from it, so it sat "active" until the 90-minute idle
+sweep timed it out instead of being marked cleared by a real event.
+
+`_release_reassigned_units` closes that gap: when a scene is a reassignment,
+scan the OTHER active incidents for unit overlap and release the unit there,
+using the same units_active/units_cleared merge (`_apply_unit_clearance`)
+that explicit 10-8 extraction already used via `_update_incident`.
+"""
+from datetime import datetime, timedelta, timezone
+from unittest.mock import patch
+
+import pytest
+
+from app.internal.incident_correlator import (
+    _apply_unit_clearance, _release_reassigned_units,
+)
+
+NOW = datetime(2026, 9, 20, 12, 0, 0, tzinfo=timezone.utc)
+
+
+def _incident(incident_id="inc-1", units_active=None, units_cleared=None,
+              system_ids=("sys-1",), **overrides):
+    inc = {
+        "incident_id": incident_id,
+        "system_ids": list(system_ids),
+        "units_active": list(units_active or []),
+        "units_cleared": list(units_cleared or []),
+        "status": "active",
+        "updated_at": (NOW - timedelta(minutes=5)).isoformat(),
+    }
+    inc.update(overrides)
+    return inc
+
+
+def _ctx(call_units, all_active, system_id="sys-1", now=NOW):
+    return {"call_units": call_units, "all_active": all_active, "system_id": system_id, "now": now}
+
+
+# ---------------------------------------------------------------------------
+# _apply_unit_clearance — pure merge logic
+# ---------------------------------------------------------------------------
+
+def test_clearance_moves_unit_from_active_to_cleared():
+    inc = _incident(units_active=["6-3"], units_cleared=[])
+    active, cleared, resolved = _apply_unit_clearance(inc, ["6-3"])
+    assert active == []
+    assert cleared == ["6-3"]
+    assert resolved is True
+
+
+def test_clearance_leaves_other_active_units_alone():
+    inc = _incident(units_active=["6-3", "6-7"], units_cleared=[])
+    active, cleared, resolved = _apply_unit_clearance(inc, ["6-3"])
+    assert active == ["6-7"]
+    assert cleared == ["6-3"]
+    assert resolved is False  # 6-7 still active
+
+
+def test_clearing_a_unit_not_tracked_as_active_is_a_noop_for_active_list():
+    inc = _incident(units_active=["6-7"], units_cleared=[])
+    active, cleared, resolved = _apply_unit_clearance(inc, ["ghost-unit"])
+    assert active == ["6-7"]
+    assert cleared == ["ghost-unit"]
+    assert resolved is False
+
+
+def test_no_units_ever_tracked_does_not_auto_resolve():
+    # An incident that never had a unit signal at all — clearing nothing
+    # must not manufacture a resolve.
+    inc = _incident(units_active=[], units_cleared=[])
+    active, cleared, resolved = _apply_unit_clearance(inc, [])
+    assert resolved is False
+
+
+# ---------------------------------------------------------------------------
+# _release_reassigned_units — reassignment releases the unit from its
+# PRIOR incident, scoped correctly, without touching that incident's calls
+# ---------------------------------------------------------------------------
+
+@pytest.mark.asyncio
+async def test_reassignment_clears_unit_from_prior_incident():
+    prior = _incident(incident_id="inc-prior", units_active=["6-3", "6-7"])
+    ctx = _ctx(call_units=["6-3"], all_active=[prior])
+
+    doc_sets = []
+    async def fake_doc_set(collection, doc_id, data, merge=True):
+        doc_sets.append((collection, doc_id, data))
+
+    with patch("app.internal.incident_correlator.fstore") as mock_fstore:
+        mock_fstore.doc_set = fake_doc_set
+        await _release_reassigned_units(ctx, exclude_incident_id="inc-new")
+
+    assert len(doc_sets) == 1
+    collection, doc_id, data = doc_sets[0]
+    assert collection == "incidents" and doc_id == "inc-prior"
+    assert data["units_active"] == ["6-7"]
+    assert data["units_cleared"] == ["6-3"]
+    assert "status" not in data  # 6-7 still active — not auto-resolved
+
+
+@pytest.mark.asyncio
+async def test_reassignment_auto_resolves_when_last_unit_clears():
+    prior = _incident(incident_id="inc-prior", units_active=["6-3"])
+    ctx = _ctx(call_units=["6-3"], all_active=[prior])
+
+    doc_sets = []
+    async def fake_doc_set(collection, doc_id, data, merge=True):
+        doc_sets.append((collection, doc_id, data))
+    async def fake_doc_get(collection, doc_id):
+        return None  # no parent — maybe_resolve_parent exits immediately
+
+    with patch("app.internal.incident_correlator.fstore") as mock_fstore:
+        mock_fstore.doc_set = fake_doc_set
+        mock_fstore.doc_get = fake_doc_get
+        await _release_reassigned_units(ctx, exclude_incident_id=None)
+
+    collection, doc_id, data = doc_sets[0]
+    assert data["status"] == "resolved"
+    assert "resolved_at" in data
+
+
+@pytest.mark.asyncio
+async def test_reassignment_never_touches_the_calls_own_incident():
+    # The call's own decision (link/new) already handled its own incident —
+    # excluding it here prevents double-writing or self-clearing on it.
+    same = _incident(incident_id="inc-new", units_active=["6-3"])
+    ctx = _ctx(call_units=["6-3"], all_active=[same])
+
+    doc_sets = []
+    async def fake_doc_set(collection, doc_id, data, merge=True):
+        doc_sets.append((collection, doc_id, data))
+
+    with patch("app.internal.incident_correlator.fstore") as mock_fstore:
+        mock_fstore.doc_set = fake_doc_set
+        await _release_reassigned_units(ctx, exclude_incident_id="inc-new")
+
+    assert doc_sets == []
+
+
+@pytest.mark.asyncio
+async def test_reassignment_does_not_cross_systems():
+    other_system = _incident(incident_id="inc-other-sys", units_active=["6-3"], system_ids=("sys-2",))
+    ctx = _ctx(call_units=["6-3"], all_active=[other_system], system_id="sys-1")
+
+    doc_sets = []
+    async def fake_doc_set(collection, doc_id, data, merge=True):
+        doc_sets.append((collection, doc_id, data))
+
+    with patch("app.internal.incident_correlator.fstore") as mock_fstore:
+        mock_fstore.doc_set = fake_doc_set
+        await _release_reassigned_units(ctx, exclude_incident_id=None)
+
+    assert doc_sets == []
+
+
+@pytest.mark.asyncio
+async def test_reassignment_with_no_call_units_is_a_noop():
+    prior = _incident(incident_id="inc-prior", units_active=["6-3"])
+    ctx = _ctx(call_units=[], all_active=[prior])
+
+    doc_sets = []
+    async def fake_doc_set(collection, doc_id, data, merge=True):
+        doc_sets.append((collection, doc_id, data))
+
+    with patch("app.internal.incident_correlator.fstore") as mock_fstore:
+        mock_fstore.doc_set = fake_doc_set
+        await _release_reassigned_units(ctx, exclude_incident_id=None)
+
+    assert doc_sets == []
+
+
+@pytest.mark.asyncio
+async def test_reassignment_matches_units_by_normalized_key():
+    # "5-David" vs "5David" — same unit, different transcription — must
+    # still match via the existing _normalize_unit key, not exact string eq.
+    prior = _incident(incident_id="inc-prior", units_active=["5-David"])
+    ctx = _ctx(call_units=["5 David"], all_active=[prior])
+
+    doc_sets = []
+    async def fake_doc_set(collection, doc_id, data, merge=True):
+        doc_sets.append((collection, doc_id, data))
+    async def fake_doc_get(collection, doc_id):
+        return None  # no parent — maybe_resolve_parent exits immediately
+
+    with patch("app.internal.incident_correlator.fstore") as mock_fstore:
+        mock_fstore.doc_set = fake_doc_set
+        mock_fstore.doc_get = fake_doc_get
+        await _release_reassigned_units(ctx, exclude_incident_id=None)
+
+    assert len(doc_sets) == 1
+    assert doc_sets[0][2]["units_cleared"] == ["5-David"]

drb-c2-core/tests/test_intelligence_unit_format.py

@@ -0,0 +1,54 @@
+"""
+server-26#<pending> — no per-system unit-ID format awareness existed anywhere
+in the pipeline (vocabulary_learner's "known local terms" is a flat glossary,
+not a structured format). Departments use incompatible unit ID conventions
+(Yorktown: "5-David", sometimes spoken as bare "David"; County:
+"SAM-1"/"airport-3"/"parks-4", a location word + number) and the extraction
+prompt had no way to be told which one a given system uses. This pins the
+prompt-block builder and the template wiring that carries it.
+"""
+from app.internal.intelligence import (
+    _PROMPT_TEMPLATE, _build_unit_format_block, _build_ten_codes_block,
+    _build_transcript_block,
+)
+
+
+def test_empty_hint_produces_no_block():
+    assert _build_unit_format_block(None) == ""
+    assert _build_unit_format_block("") == ""
+
+
+def test_hint_is_labelled_and_fed_to_the_model_verbatim():
+    block = _build_unit_format_block(
+        "Yorktown: <district>-<phonetic name>, e.g. 5-David. Sometimes spoken as just the name alone."
+    )
+    assert "unit ID format" in block
+    assert "5-David" in block
+
+
+def test_prompt_template_renders_with_all_blocks_including_empty_unit_format():
+    # Regression guard: a missing placeholder in .format() raises KeyError at
+    # request time, not import time — this is the cheapest way to catch that
+    # before it reaches a live call.
+    rendered = _PROMPT_TEMPLATE.format(
+        transcript_block=_build_transcript_block("1. Test.", None),
+        talkgroup_name="Test TG",
+        system_id="sys-1",
+        ten_codes_block=_build_ten_codes_block({}),
+        vocabulary_block="",
+        unit_format_block=_build_unit_format_block(""),
+    )
+    assert "Test TG" in rendered
+    assert "1. Test." in rendered
+
+
+def test_prompt_template_renders_with_a_populated_unit_format_block():
+    rendered = _PROMPT_TEMPLATE.format(
+        transcript_block=_build_transcript_block("1. Test.", None),
+        talkgroup_name="Test TG",
+        system_id="sys-1",
+        ten_codes_block=_build_ten_codes_block({}),
+        vocabulary_block="",
+        unit_format_block=_build_unit_format_block("County: <location>-<number>, e.g. SAM-1, airport-3."),
+    )
+    assert "SAM-1" in rendered