refactor(server): move the metadata-enrichment subsystem into lib/enrichment.py (R3) (#861)

* refactor(server): move the metadata-enrichment subsystem into lib/enrichment.py (R3)

MusicBrainz / Cover-Art-Archive / AcoustID transport, the match-scorer glue, and
the background enrichment worker (~930 lines, 61 defs) leave server.py as one
cohesive unit. Bodies are verbatim; the only changes are seam reads:

  meta_db / config_dir / sloppak_cache_dir / art_cache_dir -> appstate.<slot>
  _song_pack_art_exists / _art_override_paths (stay in server.py for the art +
    delete routes) -> appstate.<callable> (new seam slots, injected by reference)
  _env_flag -> env_compat.env_flag_compat (the existing identical helper)
  _artist_title_from_filename -> imported from metadata_db (its home)
  the User-Agent VERSION lookup: Path(__file__).parent ->
    Path(__file__).resolve().parents[1] (lib/enrichment.py -> app root)

server.py drives the worker through the module (import enrichment; the routes +
scan lifecycle call enrichment.X). Tests that faked the network on `server`
(_mb_http_get, _enrich_network_enabled, _caa_http_get, ...) now patch the same
names on `enrichment` — the module attribute is resolved at call time, so one
setattr reaches both the routes and the worker's internal callers. Acyclic:
enrichment imports appstate/appconfig/dlc_paths/metadata_db/mb_match/
acoustid_match/sloppak/loosefolder, never server.

server.py: 6,917 -> 5,988 (-929).

Verified: pyflakes clean (bar the pre-existing File/safe_join/tuning_name/ET);
route table IDENTICAL (143); full pytest 2400 passed (140 enrichment/art cases
incl the offline-safety + transport-error-pauses-pass contracts that fake the
network); test_packaging 44 passed (enrichment.py resolves under lib/); eslint 0.
Boot smoke: /api/enrichment/status + POST /kick serve from the new module.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test: reset enrichment worker state between tests (CodeRabbit)

lib/enrichment.py now owns the worker, and it stays imported for the whole
session while the `server` fixtures pop-and-reimport `server` — so the cancel
Event / status dict / caches would leak across tests, and a stale `_enrich_cancel`
could short-circuit a later direct `_background_enrich()`. An autouse conftest
fixture clears that process-global state before each test.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test: tighten the enrichment-reset fixture (CodeRabbit)

Narrow the import guard to ImportError (not blind Exception, BLE001), and stop
clearing _caa_index_locks — it's guarded by _caa_index_locks_guard, so an
unlocked clear() would race a still-alive worker, and its per-release mutexes
carry no test state.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

tests/test_scraper_options.py

@@ -8,6 +8,7 @@ flag is only force-enabled where a test needs the pipeline to run.
 """
 
 import importlib
+import enrichment
 import io as _io
 import sys
 
@@ -57,8 +58,8 @@ class FakeMB:
 @pytest.fixture()
 def mb(server, monkeypatch):
     fake = FakeMB()
-    monkeypatch.setattr(server, "_mb_http_get", fake)
-    monkeypatch.setattr(server, "_enrich_network_enabled", lambda: True)
+    monkeypatch.setattr(enrichment, "_mb_http_get", fake)
+    monkeypatch.setattr(enrichment, "_enrich_network_enabled", lambda: True)
     return fake
 
 
@@ -116,13 +117,13 @@ def test_musicbrainz_source_off_stamps_without_matching(server, mb, client):
     client.post("/api/settings", json={"enrich_src_musicbrainz": False})
     _put(server, "a.sloppak")
     mb.search_response = {"recordings": [mb_doc()]}
-    server._background_enrich()
+    enrichment._background_enrich()
     assert mb.calls == []
     row = server.meta_db.get_enrichment("a.sloppak")
     assert row["match_state"] == "unscanned"       # hash stamped, no match
     # Re-enabling picks the same row up on the next pass.
     client.post("/api/settings", json={"enrich_src_musicbrainz": True})
-    server._background_enrich()
+    enrichment._background_enrich()
     assert server.meta_db.get_enrichment("a.sloppak")["match_state"] == "matched"
 
 
@@ -133,7 +134,7 @@ def test_field_toggles_strip_auto_applied_fields(server, mb, client):
                                        "enrich_apply_genres": False})
     _put(server, "a.sloppak")
     mb.search_response = {"recordings": [mb_doc()]}
-    server._background_enrich()
+    enrichment._background_enrich()
     row = server.meta_db.get_enrichment("a.sloppak")
     assert row["match_state"] == "matched"
     assert row["canon_artist"] == "AC/DC"
@@ -150,7 +151,7 @@ def test_names_toggle_keeps_ids_and_other_fields(server, mb, client):
     client.post("/api/settings", json={"enrich_apply_names": False})
     _put(server, "a.sloppak")
     mb.search_response = {"recordings": [mb_doc()]}
-    server._background_enrich()
+    enrichment._background_enrich()
     row = server.meta_db.get_enrichment("a.sloppak")
     assert row["match_state"] == "matched"
     assert row["canon_artist"] is None
@@ -170,7 +171,7 @@ def test_review_accept_applies_all_fields_despite_toggles(server, mb, client):
     # Partial artist agreement → review tier (candidates stored unfiltered).
     _put(server, "a.sloppak", artist="AC/DC ft Nobody")
     mb.search_response = {"recordings": [mb_doc()]}
-    server._background_enrich()
+    enrichment._background_enrich()
     assert server.meta_db.get_enrichment("a.sloppak")["match_state"] == "review"
     r = client.post("/api/enrichment/review/a.sloppak/accept",
                     json={"recording_id": "rec-1"})
@@ -192,21 +193,21 @@ def test_reenabling_field_backfills_matched_row(server, mb, client):
     client.post("/api/settings", json={"enrich_apply_year": False})
     _put(server, "a.sloppak")
     mb.search_response = {"recordings": [mb_doc()]}
-    server._background_enrich()
+    enrichment._background_enrich()
     row = server.meta_db.get_enrichment("a.sloppak")
     assert row["match_state"] == "matched"
     assert row["canon_year"] is None                    # suppressed
     assert row["apply_mask"] == "enrich_apply_year"     # …and remembered
     # Re-enable → next pass re-queues and backfills the year (hash unchanged).
     client.post("/api/settings", json={"enrich_apply_year": True})
-    server._background_enrich()
+    enrichment._background_enrich()
     row = server.meta_db.get_enrichment("a.sloppak")
     assert row["match_state"] == "matched"
     assert row["canon_year"] == "1990"                  # backfilled
     assert row["apply_mask"] in (None, "")              # fully applied now
     # Converged: a fully-applied row is not re-queued again.
     assert server.meta_db.enrichment_pending(
-        allowed_keys=frozenset(server._ENRICH_APPLY_FIELDS)) == []
+        allowed_keys=frozenset(enrichment._ENRICH_APPLY_FIELDS)) == []
 
 
 def test_partial_match_is_not_a_cache_donor(server):
@@ -271,8 +272,8 @@ def caa(server, monkeypatch):
         calls.append(release_id)
         return art.get(release_id)
     fake.calls = calls
-    monkeypatch.setattr(server, "_caa_http_get", fake)
-    monkeypatch.setattr(server, "_enrich_network_enabled", lambda: True)
+    monkeypatch.setattr(enrichment, "_caa_http_get", fake)
+    monkeypatch.setattr(enrichment, "_enrich_network_enabled", lambda: True)
     return fake
 
 
@@ -280,13 +281,13 @@ def test_caa_source_toggle_gates_art_fetch(server, client, caa):
     make_sloppak(server, "a.sloppak")
     _match_row(server, "a.sloppak")
     client.post("/api/settings", json={"enrich_src_caa": False})
-    server._background_enrich()
+    enrichment._background_enrich()
     assert caa.calls == []
     row = server.meta_db.get_enrichment("a.sloppak")
     assert row["art_state"] is None                # not forfeited, just skipped
     # Re-enable → the same row is picked up.
     client.post("/api/settings", json={"enrich_src_caa": True})
-    server._background_enrich()
+    enrichment._background_enrich()
     assert server.meta_db.get_enrichment("a.sloppak")["art_state"] == "caa"
 
 
@@ -294,7 +295,7 @@ def test_apply_art_toggle_gates_art_fetch(server, client, caa):
     make_sloppak(server, "a.sloppak")
     _match_row(server, "a.sloppak")
     client.post("/api/settings", json={"enrich_apply_art": False})
-    server._background_enrich()
+    enrichment._background_enrich()
     assert caa.calls == []
     assert server.meta_db.get_enrichment("a.sloppak")["art_state"] is None