feat(poker): nameless-villain identity resolution engine

Phase 1 of the scouting desk (docs/SCOUTING_DESK.md). Villains keyed by physical
descriptor when there's no name — a fuzzy key matched by embedding, venue-scoped,
gated on distinctiveness so a generic description never resolves to a wrong guess.

- schema: poker_players gains descriptors/descriptor_embedding/distinctiveness/
  named (name stays populated with a descriptor label to avoid a NOT-NULL rebuild
  on the live DB); new tables player_distinct_pairs + identity_queue.
- resolve_villain(ref, venue) → band name|high|ambiguous|generic|none; exact name
  is deterministic, descriptors match by cosine, generic-only refuses to guess.
- create_descriptor_villain / add_descriptor / name_villain; merge_players
  (repoints obs/reads, prefers a real name, re-embeds the union); mark_distinct +
  are_distinct (rejected merges stay rejected); identity_queue file/list/resolve
  with pending-dedup; scan_merge_candidates for the dream cycle (skips distinct
  pairs and cross-venue).

11 tests. Full suite 141 green.

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

tests/test_villains.py

@@ -0,0 +1,116 @@
+"""Nameless-villain identity resolution: descriptor matching, merge, distinct, queue."""
+from __future__ import annotations
+
+import importlib
+
+import numpy as np
+import pytest
+
+
+def _fake_embed(texts):
+    """Overlap-sensitive bag-of-words vectors so cosine reflects shared tokens."""
+    out = []
+    for t in texts:
+        v = np.zeros(64, dtype=np.float32)
+        for w in t.lower().split():
+            v[hash(w) % 64] += 1.0
+        out.append((v if v.any() else np.full(64, 1e-6, dtype=np.float32)).tolist())
+    return out
+
+
+@pytest.fixture
+def poker(tmp_path, monkeypatch):
+    monkeypatch.setenv("LYRA_DB_PATH", str(tmp_path / "test.db"))
+    from lyra import llm
+    monkeypatch.setattr(llm, "embed", _fake_embed)
+    import lyra.memory as memory
+    importlib.reload(memory)
+    import lyra.poker as poker
+    importlib.reload(poker)
+    return poker
+
+
+def test_distinctiveness_distinctive_vs_generic(poker):
+    assert poker.distinctiveness("guy with a neck tattoo") > 0.6
+    assert poker.distinctiveness("mid-aged white dude with glasses") < 0.3
+
+
+def test_generic_descriptor_never_resolves_to_a_guess(poker):
+    poker.create_descriptor_villain("neck tattoo sleeve arm", venue="Meadows")
+    r = poker.resolve_villain("mid aged white guy with glasses", venue="Meadows")
+    assert r["band"] == "generic"
+    assert r["match_id"] is None
+
+
+def test_exact_name_match_is_deterministic(poker):
+    pid = poker.upsert_player("Sleepy John", venue="Meadows")
+    r = poker.resolve_villain("sleepy john")
+    assert r["band"] == "name" and r["match_id"] == pid
+
+
+def test_rephrased_descriptor_resolves_high(poker):
+    pid = poker.create_descriptor_villain("neck tattoo sleeve arm", venue="Meadows")
+    r = poker.resolve_villain("neck tattoo sleeve", venue="Meadows")
+    assert r["band"] == "high" and r["match_id"] == pid
+    assert r["confidence"] >= 0.80
+
+
+def test_partial_descriptor_is_ambiguous_not_high(poker):
+    poker.create_descriptor_villain("neck tattoo sleeve arm", venue="Meadows")
+    r = poker.resolve_villain("neck tattoo", venue="Meadows")
+    assert r["band"] == "ambiguous"  # plausible, but don't guess live
+
+
+def test_merge_repoints_observations_and_deletes_dup(poker):
+    keep = poker.create_descriptor_villain("neck tattoo", venue="Meadows")
+    dup = poker.create_descriptor_villain("neck ink tatted", venue="Meadows")
+    poker._c().execute(
+        "INSERT INTO player_observations (player_id, session_id, created_at) VALUES (?,1,?)",
+        (dup, poker._now()))
+    poker._c().commit()
+    assert poker.merge_players(keep, dup) is True
+    assert poker.get_villain_file() and all(p["id"] != dup for p in poker.get_villain_file())
+    obs = poker._c().execute(
+        "SELECT COUNT(*) n FROM player_observations WHERE player_id = ?", (keep,)).fetchone()["n"]
+    assert obs == 1
+
+
+def test_merge_prefers_a_real_name(poker):
+    named = poker.upsert_player("Danny", venue="Meadows")
+    desc = poker.create_descriptor_villain("neck tattoo", venue="Meadows")
+    poker.merge_players(desc, named)  # keep the descriptor id, but name should win
+    row = dict(poker._c().execute("SELECT name, named FROM poker_players WHERE id = ?", (desc,)).fetchone())
+    assert row["name"] == "Danny" and row["named"] == 1
+
+
+def test_mark_distinct_blocks_merge_scan(poker):
+    a = poker.create_descriptor_villain("neck tattoo sleeve", venue="Meadows")
+    b = poker.create_descriptor_villain("neck tattoo sleeve", venue="Meadows")
+    poker.mark_distinct(a, b, note="one's taller")
+    assert poker.are_distinct(a, b)
+    assert poker.scan_merge_candidates() == 0  # confirmed-distinct pair is skipped
+
+
+def test_scan_files_merge_candidate_for_near_duplicates(poker):
+    poker.create_descriptor_villain("neck tattoo sleeve", venue="Meadows")
+    poker.create_descriptor_villain("neck tattoo sleeve", venue="Meadows")
+    filed = poker.scan_merge_candidates()
+    assert filed == 1
+    q = poker.list_identity_queue()
+    assert q and q[0]["kind"] == "merge_candidate" and len(q[0]["players"]) == 2
+
+
+def test_queue_dedupes_identical_pending_task(poker):
+    a = poker.create_descriptor_villain("neck tattoo", venue="Meadows")
+    b = poker.create_descriptor_villain("neck ink", venue="Meadows")
+    t1 = poker.queue_identity_task("merge_candidate", [a, b])
+    t2 = poker.queue_identity_task("merge_candidate", [b, a])  # same pair, reversed
+    assert t1 == t2
+    assert len(poker.list_identity_queue()) == 1
+
+
+def test_name_villain_flips_named_flag(poker):
+    pid = poker.create_descriptor_villain("neck tattoo", venue="Meadows")
+    poker.name_villain(pid, "Danny")
+    r = poker.resolve_villain("Danny")
+    assert r["band"] == "name" and r["match_id"] == pid