feat(v0.7-fire-tracker-4): fix LLM DM path + daily fire digest + ?status queries

Phase 4 of FIRMS+WFIGS fusion. Foundation: every direct LLM DM
mentioning a fire/weather/quake/avalanche/flood/etc. keyword was
failing silently in prod with UnboundLocalError because router.py
referenced scope_type before assigning it. With that path restored,
two new features land: a twice-daily fire-digest scheduled broadcast
(LLM-rendered) and a ?status <fire_name> on-demand mesh-DM intent.

BUG-FIX ROOT CAUSE (Job Zero):
  router.py:745 ("if should_inject_mesh and scope_type == 'env'") read
  `scope_type` -- a local variable bound only at line 761 inside an
  unrelated `if self.source_manager and self.mesh_reporter` block.
  Python's lexical scoping made scope_type a local of the whole
  generate_llm_response function, so reading it before the assignment
  raised UnboundLocalError on every env-keyword DM. The exception
  propagated to main.py's outer except, no response went out, bot
  appeared dead on fire/weather/quake/avalanche/flood queries.

  Evidence (synthetic in-process trace against the live container's
  config + GoogleBackend):
    "are there any fires near me?" -> UnboundLocalError (pre-fix)
                                  -> real LLM answer (post-fix)
                                     "Yes, there are a few active
                                      fires reported in the region.
                                      Salmon River: 4,200 acres, 78%
                                      contained. Cache Peak: 1,847
                                      acres, 23% contained. ..."
    "what's the weather?"          -> UnboundLocalError (pre-fix)
                                  -> "I do not have current weather
                                      information. I can tell you
                                      about active fires, stream gauge
                                      levels, space weather, or band
                                      conditions if you'd like." (post-fix)
    "hi there"                     -> normal LLM answer in both cases

  Fix: hoist `scope_type, scope_value = self._detect_mesh_scope(query)`
  to right after `should_inject_mesh` is computed; remove the
  now-duplicate detection inside the source_manager block.

  Secondary mitigation: tightened the "do not invent commands" prompt
  with an explicit "if no list appears above, you have NO commands"
  clause. The prior prompt told the LLM "answer based on the command
  list provided below" without always providing one, so the LLM
  hallucinated plausible-sounding !commands (the "use ! commands"
  canned-looking response Matt was seeing on non-env queries).

PHASE 4 FEATURES:

1. Fire-digest scheduler (meshai/notifications/scheduled/fire_digest.py).
   Modeled after BandConditionsScheduler. Runs in the pipeline's
   start_pipeline coroutine alongside band_conditions + reminders.
   On each slot (default 06:00 + 18:00 America/Boise):
     - Queries active fires (tombstoned_at IS NULL) + last 24h passes.
     - Builds a prompt asking for a single mesh-wire summary <= 200
       chars.
     - Calls the LLM (Google/Anthropic/OpenAI per config).
     - Falls back to a terse "Fires today (N): Cache Peak 1847 ac;
       Twin Peaks 320 ac; +N more" line when the LLM is unavailable.
     - Dispatches via dispatcher.dispatch_scheduled_broadcast (same
       path band_conditions uses).
   Idempotency: v16.sql adds fire_digest_broadcasts(slot_epoch PK,
   sent_at, summary, source). INSERT OR IGNORE pattern blocks the same
   slot firing twice (matters when container restarts mid-day).

2. ?status <fire_name> on-demand intent (router.py).
   Before falling through to the LLM, route() now checks for a leading
   "?status" / "status:" sigil or natural-language triggers like
   "how is X fire?". On match:
     - _lookup_fire_fuzzy walks fires by exact -> startswith ->
       contains -> word-overlap (skipping a trailing " fire" word so
       "cache peak fire" matches "Cache Peak"). Active fires rank
       above tombstoned ones.
     - _build_fire_status_context composes a small context block
       (name, acres, containment, county/state, last 3 passes with
       drift).
     - The query is REWRITTEN into an LLM prompt with that context
       inlined; the rest of the normal LLM path (chunking, history,
       summary persistence) runs unchanged.
   Live verification: "?status Cache Peak" -> "The Cache Peak fire is
   1,847 acres and 23% contained. It's located in Probe / ID.";
   "?status Salmon" -> word-overlap matches "Salmon River" ->
   "The Salmon River fire is 4,200 acres and 78% contained, located
   in Probe / ID."

3. adapter_config rows (GUI-editable per CONFIG-vs-CODE rule):
     fires.digest_enabled         = true   (master toggle)
     fires.digest_schedule        = ["06:00", "18:00"]
     fires.digest_timezone        = "America/Boise"
     fires.digest_max_chars       = 200

Schema (v16.sql):
- fire_digest_broadcasts(slot_epoch INTEGER PK, sent_at, summary,
  source) with source in {'llm', 'fallback_terse', 'skipped_no_fires'}.
- Index on sent_at for ops queries.

Tests (tests/test_fire_tracker_phase4.py, 10 cases all green):
- Regression guard: scope_type appears as an assignment BEFORE the
  env_reporter check (prevents the UnboundLocalError from coming back).
- adapter_config seeds all 4 digest keys with expected defaults.
- render_digest returns ('', 'no_fires') when no active fires.
- render_digest falls back to terse line when LLM is None; wire fits cap.
- render_digest with a stub LLM returns ('<llm text>', 'llm').
- _lookup_fire_fuzzy: exact, "X fire" trim, word-overlap, no-match.
- _maybe_rewrite_status_query: builds context-bearing prompt; returns
  None on non-status queries.

Combined suite: 60 passed in 3.81s across phase1+phase2+phase3+phase4
+or-arch+include-roundtrip.

Live verification on CT108 after rebuild:
- v16 migration applied (schema_meta=16, no Traceback in 3 min).
- FireDigestScheduler started: enabled=True schedule=['06:00','18:00']
  tz=America/Boise.
- LLM DM probe (real Gemini) returns real answers on env queries
  (Bug A fixed end-to-end).
- ?status Cache Peak + ?status Salmon return fire-specific summaries.
- render_digest with real LLM returns source=llm + non-empty wire.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

tests/test_fire_tracker_phase4.py

@@ -0,0 +1,187 @@
+"""v0.7-fire-tracker-4 tests."""
+from __future__ import annotations
+
+import asyncio
+import time
+import uuid
+
+import pytest
+
+
+@pytest.fixture(autouse=True)
+def _isolate_db(tmp_path, monkeypatch):
+    db_path = str(tmp_path / f"meshai-{uuid.uuid4().hex}.sqlite")
+    monkeypatch.setenv("MESHAI_DB_PATH", db_path)
+    from meshai.persistence import db as pdb
+    pdb.close_thread_connection()
+    pdb._initialised.discard(db_path)
+    from meshai.persistence import init_db
+    init_db(db_path)
+    yield db_path
+    pdb.close_thread_connection()
+    pdb._initialised.discard(db_path)
+
+
+def _seed_fire(*, irwin_id, name, lat, lon, acres=None,
+                contained=None, county="Test", state="ID"):
+    from meshai.persistence import get_db
+    get_db().execute(
+        "INSERT INTO fires(irwin_id, incident_name, current_acres, "
+        "current_contained_pct, lat, lon, county, state, last_event_at) "
+        "VALUES (?,?,?,?,?,?,?,?,?)",
+        (irwin_id, name, acres, contained, lat, lon, county, state,
+         int(time.time())),
+    )
+
+
+# ===========================================================================
+# Bug A regression: scope_type defined before use
+# ===========================================================================
+
+
+def test_router_scope_type_defined_before_env_check():
+    """The env_reporter check at the top of generate_llm_response reads
+    scope_type. Pre-fix it was UnboundLocalError on every env query."""
+    import re
+    from pathlib import Path
+    src = Path("/opt/meshai/meshai/router.py").read_text()
+    # Find the "if should_inject_mesh and scope_type" line + the
+    # nearest preceding `scope_type, scope_value = ` assignment.
+    env_use_line = None
+    for i, line in enumerate(src.splitlines(), start=1):
+        if "should_inject_mesh and scope_type" in line:
+            env_use_line = i
+            break
+    assert env_use_line is not None
+    # There must be an assignment on or before this line.
+    preceding = "\n".join(src.splitlines()[: env_use_line - 1])
+    assert re.search(r"scope_type[, ]+scope_value\s*=", preceding) \
+        or "scope_type:" in preceding
+
+
+# ===========================================================================
+# adapter_config seed + categories registration
+# ===========================================================================
+
+
+def test_adapter_config_seeds_digest_keys():
+    from meshai.persistence import get_db
+    rows = {
+        (r["adapter"], r["key"]): r["default_json"]
+        for r in get_db().execute(
+            "SELECT adapter, key, default_json FROM adapter_config "
+            "WHERE adapter='fires' AND key LIKE 'digest%'"
+        )
+    }
+    assert rows[("fires", "digest_enabled")] == "true"
+    assert rows[("fires", "digest_schedule")] == '["06:00", "18:00"]'
+    assert rows[("fires", "digest_timezone")] == '"America/Boise"'
+    assert rows[("fires", "digest_max_chars")] == "200"
+
+
+# ===========================================================================
+# Digest renderer
+# ===========================================================================
+
+
+def test_render_digest_returns_no_fires_when_table_empty():
+    from meshai.notifications.scheduled.fire_digest import render_digest
+
+    async def _run():
+        return await render_digest(llm_backend=None, max_chars=200)
+    wire, source = asyncio.run(_run())
+    assert wire == ""
+    assert source == "no_fires"
+
+
+def test_render_digest_terse_fallback_when_no_llm():
+    _seed_fire(irwin_id="ID-A", name="Cache Peak",
+                 lat=42.0, lon=-114.0, acres=1847, contained=23)
+    _seed_fire(irwin_id="ID-B", name="Twin Peaks",
+                 lat=43.0, lon=-115.0, acres=320, contained=5)
+    from meshai.notifications.scheduled.fire_digest import render_digest
+
+    async def _run():
+        return await render_digest(llm_backend=None, max_chars=200)
+    wire, source = asyncio.run(_run())
+    assert source == "fallback_terse"
+    assert wire
+    assert "Cache Peak" in wire
+    assert len(wire) <= 200
+
+
+def test_render_digest_uses_llm_when_available():
+    """When the LLM backend returns a string, that string IS the wire."""
+    _seed_fire(irwin_id="ID-A", name="Cache Peak",
+                 lat=42.0, lon=-114.0, acres=1847)
+
+    class StubLLM:
+        async def generate(self, *, messages, system_prompt, max_tokens):
+            # The renderer must give us a single-line wire derived from
+            # the LLM output, with markdown stripped + cap applied.
+            return "Cache Peak 1847 ac stable; no spotting today."
+
+    from meshai.notifications.scheduled.fire_digest import render_digest
+
+    async def _run():
+        return await render_digest(llm_backend=StubLLM(), max_chars=200)
+    wire, source = asyncio.run(_run())
+    assert source == "llm"
+    assert wire == "Cache Peak 1847 ac stable; no spotting today."
+
+
+# ===========================================================================
+# Fuzzy fire lookup for ?status
+# ===========================================================================
+
+
+def test_status_lookup_exact_name():
+    from meshai.router import _lookup_fire_fuzzy
+    _seed_fire(irwin_id="ID-A", name="Cache Peak",
+                 lat=42.0, lon=-114.0, acres=1847)
+    f = _lookup_fire_fuzzy("Cache Peak")
+    assert f is not None
+    assert f["incident_name"] == "Cache Peak"
+
+
+def test_status_lookup_trims_trailing_fire_word():
+    from meshai.router import _lookup_fire_fuzzy
+    _seed_fire(irwin_id="ID-A", name="Cache Peak",
+                 lat=42.0, lon=-114.0, acres=1847)
+    f = _lookup_fire_fuzzy("cache peak fire")
+    assert f is not None
+    assert f["incident_name"] == "Cache Peak"
+
+
+def test_status_lookup_word_overlap_fallback():
+    from meshai.router import _lookup_fire_fuzzy
+    _seed_fire(irwin_id="ID-A", name="Cache Peak",
+                 lat=42.0, lon=-114.0, acres=1847)
+    f = _lookup_fire_fuzzy("how is peak doing")
+    assert f is not None
+    assert f["incident_name"] == "Cache Peak"
+
+
+def test_status_lookup_returns_none_on_no_match():
+    from meshai.router import _lookup_fire_fuzzy
+    _seed_fire(irwin_id="ID-A", name="Cache Peak",
+                 lat=42.0, lon=-114.0, acres=1847)
+    assert _lookup_fire_fuzzy("nonexistent ranger station") is None
+
+
+def test_status_query_rewrite_includes_fire_context():
+    from meshai.router import _maybe_rewrite_status_query
+    _seed_fire(irwin_id="ID-A", name="Cache Peak",
+                 lat=42.0, lon=-114.0, acres=1847, contained=23)
+    out = _maybe_rewrite_status_query("?status Cache Peak", router=None)
+    assert out is not None
+    assert "Cache Peak" in out
+    assert "1847" in out
+    # Must instruct the LLM to be terse mesh format.
+    assert "mesh" in out.lower()
+
+
+def test_status_query_rewrite_returns_none_when_not_status():
+    from meshai.router import _maybe_rewrite_status_query
+    out = _maybe_rewrite_status_query("how's the weather?", router=None)
+    assert out is None