feat(brain): hybrid BM25 + pgvector retrieval (opt-in)

Wires nomic-embed-text (iguana ollama) + pgvector on the shared
postgres18 into brain_query / brain_answer via Reciprocal Rank Fusion.
Pure BM25 stays the default; setting BRAIN_PG_DSN and BRAIN_EMBED_URL
together opts in. Setting one without the other is misconfiguration →
exit 1.

New packages:

- internal/embed
  Client.Embed(ctx, text) → []float32 via POST {URL}/api/embed.
  Defaults to nomic-embed-text:latest (768 dim). nil-on-empty-URL so
  callers gate on a single nil check.

- internal/vectorstore
  PGStore wraps a pgxpool against postgres18. Init creates
  brain_embeddings(path PK, vector(768), updated_at) + HNSW cosine
  index idempotently. Upsert / Delete / Search / KnownPaths.
  Sync(brainDir, store, embedder) diffs brain/wiki/ against the store
  and upserts new files / deletes removed ones; StartSync runs it on
  a ticker (default 300s). Integration tests gated by BRAIN_PG_TEST_DSN.

- scripts/brain-embeddings-init.sql
  One-time DBA setup: brain DB, brain_app role, vector extension,
  GRANTs. Idempotent.

Search layer:

- search.QueryOptions gains Vector + Embedder fields.
- QueryContext is the cancellable variant; Query stays for callers.
- When both are set, BM25 (top-N) and pgvector (top-4N) candidates
  merge via Reciprocal Rank Fusion (k=60, Cormack et al. 2009 — no
  tuning knob, robust to scale differences between rankers).
- Vector-only hits are hydrated from disk so callers see uniform
  Result records (path, title, excerpt, wing, hall, score).
- Wing/hall filters still apply to vector candidates via path-prefix.
- On embedder/vector errors the search falls back to BM25 — embedding
  outage degrades quality but doesn't take the brain offline.

MCP wiring:

- mcp.Server.WithHybridRetrieval(v, e) opt-in setter, same shape as
  WithReranker.
- brainQuery and brainAnswer pass the wired vector/embedder through
  to search.QueryContext.

REST:

- POST /backfill-embeddings drives Sync synchronously. Returns
  {added, deleted, errors[]}. 503 when feature is unconfigured.

cmd/server/main.go:

- BRAIN_PG_DSN + BRAIN_EMBED_URL together enable hybrid; one alone
  → exit 1.
- vectorAdapter bridges *PGStore (returns []Hit) to
  search.VectorSearcher (which takes []VectorHit) without either
  package importing the other.
- BRAIN_EMBED_SYNC_INTERVAL (default 300s) controls the background
  Sync ticker.

Backend pivot from Qdrant to pgvector recorded in DECISIONS.md
2026-05-18 (supersedes 2026-04-08): postgres18 already runs in
databases/ ns, Qdrant was never deployed, one engine beats two.

Dependency: github.com/jackc/pgx/v5 — modern, native pgvector via
parametric vector literals.

Tests:
- embed.Client: empty-URL nil, request shape, dimension, upstream
  error propagation, empty-text rejection.
- vectorstore.PGStore: dimension validation (unit); upsert/search/
  KnownPaths (integration, BRAIN_PG_TEST_DSN-gated).
- vectorstore.Sync: adds new files, skips known, deletes
  disappeared, skips _index.md, no-op when nil, collects embedder
  errors.
- search.Query: hybrid promotes vector-only hits via RRF; falls
  back to BM25 on embedder error.

Closes hyperguild#8.

ingestion/internal/search/search_test.go

@@ -2,6 +2,7 @@
 package search_test
 
 import (
+	"context"
 	"fmt"
 	"os"
 	"path/filepath"
@@ -12,6 +13,69 @@ import (
 	"github.com/stretchr/testify/require"
 )
 
+type stubEmbedder struct{ vec []float32 }
+
+func (s stubEmbedder) Embed(_ context.Context, _ string) ([]float32, error) { return s.vec, nil }
+
+type stubVector struct{ hits []search.VectorHit }
+
+func (s stubVector) Search(_ context.Context, _ []float32, _ int) ([]search.VectorHit, error) {
+	return s.hits, nil
+}
+
+func TestSearch_HybridRRFPromotesVectorOnlyHit(t *testing.T) {
+	dir := t.TempDir()
+	for _, p := range []struct{ rel, body string }{
+		// BM25-keyword note (matches "lejpa" once)
+		{"wiki/jepa-fx/facts/foo.md", "---\ntitle: Foo\n---\nlejpa keyword\n"},
+		// Semantically related note that does NOT contain the keyword.
+		{"wiki/jepa-fx/facts/semantic.md", "---\ntitle: Semantic\n---\nNo keyword in body.\n"},
+	} {
+		full := filepath.Join(dir, p.rel)
+		require.NoError(t, os.MkdirAll(filepath.Dir(full), 0o755))
+		require.NoError(t, os.WriteFile(full, []byte(p.body), 0o644))
+	}
+
+	embedder := stubEmbedder{vec: []float32{0.1}}
+	vector := stubVector{hits: []search.VectorHit{
+		{Path: "wiki/jepa-fx/facts/semantic.md", Distance: 0.05}, // best vector match
+		{Path: "wiki/jepa-fx/facts/foo.md", Distance: 0.10},
+	}}
+
+	got, err := search.Query(dir, search.QueryOptions{
+		Query:    "lejpa",
+		Limit:    5,
+		Vector:   vector,
+		Embedder: embedder,
+	})
+	require.NoError(t, err)
+	require.Len(t, got, 2, "vector-only hit should be hydrated into results")
+	paths := []string{got[0].Path, got[1].Path}
+	assert.Contains(t, paths, "wiki/jepa-fx/facts/foo.md")
+	assert.Contains(t, paths, "wiki/jepa-fx/facts/semantic.md")
+}
+
+func TestSearch_HybridFallsBackOnEmbedderError(t *testing.T) {
+	dir := t.TempDir()
+	require.NoError(t, os.MkdirAll(filepath.Join(dir, "wiki"), 0o755))
+	require.NoError(t, os.WriteFile(filepath.Join(dir, "wiki", "x.md"), []byte("keyword foo"), 0o644))
+
+	embedder := errorEmbedder{}
+	vector := stubVector{}
+	got, err := search.Query(dir, search.QueryOptions{
+		Query: "keyword", Limit: 5, Vector: vector, Embedder: embedder,
+	})
+	require.NoError(t, err)
+	require.Len(t, got, 1, "BM25 result should still come back when embedder fails")
+	assert.Equal(t, "wiki/x.md", got[0].Path)
+}
+
+type errorEmbedder struct{}
+
+func (errorEmbedder) Embed(_ context.Context, _ string) ([]float32, error) {
+	return nil, assert.AnError
+}
+
 func TestSearch_ReturnsMatchingPages(t *testing.T) {
 	dir := t.TempDir()
 	require.NoError(t, os.MkdirAll(filepath.Join(dir, "knowledge"), 0o755))