Extraction: model in config, chatter gate, geocode cache (server-26#298, server-26#104, server-26#88)

EXTRACTION_MODEL / EMBEDDING_MODEL replace the gpt-4o-mini and
text-embedding-3-small literals. gate_chatter (classify_chatter with roll_call
narrowed to whole-transcript roll calls) skips correction, extraction,
embedding and geocoding for housekeeping, writes skip_reason=non_event_chatter
and still runs the free clearance/plate backstops; upload.py's no-scene
fallback admits it like transcript_too_short. Ships OFF (CHATTER_GATE_ENABLED
=false): a gated call has no units, so it takes the no-fit-check thin attach,
and #127 requires a clean live shadow window first.
In-process TTL cache (24h, negatives 1h, 5000 entries, LRU) in front of the
Geocoding API, keyed by address+bounds; holds coordinates only, inside the
Maps 30-day lat/lng caching limit; errors and key/quota statuses not cached.
#104: the no-scene fallback passes the call doc's severity.
#88: resolved/reassignment parsed by _llm_bool, not bool().

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

drb-c2-core/tests/conftest.py

@@ -96,3 +96,13 @@ def _no_real_discord(monkeypatch):
     monkeypatch.setattr(discord_rest, "_transport", httpx.MockTransport(_offline))
     yield
     discord_rest.reset()
+
+
+@pytest.fixture(autouse=True)
+def _fresh_geocode_cache():
+    """The geocode cache (server-26#298) is process-wide; a test that stubs
+    Maps must never be answered by a previous test's stub."""
+    from app.internal import intelligence
+    intelligence.clear_geocode_cache()
+    yield
+    intelligence.clear_geocode_cache()