From 7c28eddd47b17b16e7958c7e381b46bbb3bc0ae1 Mon Sep 17 00:00:00 2001
From: Jonathan <claude.cs@jger.nl>
Date: Fri, 10 Jul 2026 18:54:15 +0200
Subject: [PATCH] fix: persist all found candidates and guard duplicate adapter
 names

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---
 worker/lyra_worker/pipeline.py | 17 ++++++++++++-----
 worker/tests/test_pipeline.py  | 29 +++++++++++++++++++++++++++++
 2 files changed, 41 insertions(+), 5 deletions(-)

diff --git a/worker/lyra_worker/pipeline.py b/worker/lyra_worker/pipeline.py
index eb966bb..ee63857 100644
--- a/worker/lyra_worker/pipeline.py
+++ b/worker/lyra_worker/pipeline.py
@@ -1,8 +1,10 @@
+from dataclasses import replace
 from typing import Sequence
 
 import psycopg
 
 from lyra_worker.adapters.base import SourceAdapter
+from lyra_worker.confidence import score_confidence
 from lyra_worker.quality import quality_class
 from lyra_worker.ranker import rank_candidates
 from lyra_worker.types import Candidate, MBTarget
@@ -103,6 +105,10 @@ def run_pipeline(
     dest_root: str = "/music",
 ) -> None:
     """Real staged acquisition using source-agnostic adapters. Fakes in this plan."""
+    names = [a.name for a in adapters]
+    if len(names) != len(set(names)):
+        raise ValueError(f"adapter names must be unique, got {names}")
+
     # 1. intake
     _set_state(conn, job_id, "matching", "intake")
     target = _load_target(conn, job_id)
@@ -116,16 +122,17 @@ def run_pipeline(
         conn.commit()
         return
 
-    # 2. match
+    # 2. match — search all adapters; score + persist EVERY candidate found
     _set_state(conn, job_id, "matching", "match")
-    candidates: list[Candidate] = []
+    found: list[Candidate] = []
     for adapter in adapters:
-        candidates.extend(adapter.search(target))
+        for c in adapter.search(target):
+            found.append(replace(c, confidence=score_confidence(target, c)))
+    _persist_candidates(conn, job_id, found)
 
     # 3. rank
     _set_state(conn, job_id, "matched", "rank")
-    ranked = rank_candidates(target, candidates, min_confidence)
-    _persist_candidates(conn, job_id, ranked)
+    ranked = rank_candidates(target, found, min_confidence)
     if not ranked:
         _fail(conn, job_id, "no candidate above confidence threshold")
         return
diff --git a/worker/tests/test_pipeline.py b/worker/tests/test_pipeline.py
index 7252d3d..4ef265d 100644
--- a/worker/tests/test_pipeline.py
+++ b/worker/tests/test_pipeline.py
@@ -99,3 +99,32 @@ def test_dedupe_skips_already_in_library(conn):
         cur.execute('SELECT count(*) FROM "LibraryItem" WHERE artist = %s AND album = %s',
                     ("Radiohead", "In Rainbows"))
         assert cur.fetchone()[0] == 1  # not duplicated
+
+
+def test_below_threshold_candidates_are_persisted_for_diagnosis(conn):
+    from lyra_worker.adapters.fakes import FakeQobuz
+    from lyra_worker.types import MBTarget
+
+    class WrongAlbumQobuz(FakeQobuz):
+        def search(self, target):
+            # returns a candidate for a different album -> scores below the gate
+            return super().search(MBTarget(artist=target.artist, album="Some Completely Unrelated Title"))
+
+    job_id = insert_request(conn, artist="Radiohead", album="In Rainbows")
+    claim_next(conn)
+    run_pipeline(conn, job_id, [WrongAlbumQobuz()], dest_root="/tmp/lib")
+
+    assert _job_state(conn, job_id)[0] == "needs_attention"
+    with conn.cursor() as cur:
+        cur.execute('SELECT count(*) FROM "Candidate" WHERE "jobId" = %s', (job_id,))
+        assert cur.fetchone()[0] >= 1  # found-but-rejected candidate retained for diagnosis
+
+
+def test_duplicate_adapter_names_raise(conn):
+    import pytest
+    from lyra_worker.adapters.fakes import FakeQobuz
+
+    job_id = insert_request(conn, artist="Radiohead", album="In Rainbows")
+    claim_next(conn)
+    with pytest.raises(ValueError):
+        run_pipeline(conn, job_id, [FakeQobuz(), FakeQobuz()], dest_root="/tmp/lib")