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/api/handler.go

@@ -15,13 +15,16 @@ import (
 	"github.com/mathiasbq/hyperguild/ingestion/internal/extract"
 	"github.com/mathiasbq/hyperguild/ingestion/internal/pipeline"
 	"github.com/mathiasbq/hyperguild/ingestion/internal/search"
+	"github.com/mathiasbq/hyperguild/ingestion/internal/vectorstore"
 )
 
 // Handler serves the ingestion HTTP API.
 type Handler struct {
-	brainDir string
-	logger   *slog.Logger
-	pipeline pipeline.Config
+	brainDir    string
+	logger      *slog.Logger
+	pipeline    pipeline.Config
+	embedStore  vectorstore.Store
+	embedClient vectorstore.Embedder
 }
 
 // NewHandler constructs a Handler. brainDir is the absolute path to brain/.
@@ -32,6 +35,14 @@ func NewHandler(brainDir string, logger *slog.Logger, pipelineCfg pipeline.Confi
 	return &Handler{brainDir: brainDir, logger: logger, pipeline: pipelineCfg}
 }
 
+// WithEmbedSync wires the optional vector store + embedder used by the
+// POST /backfill-embeddings endpoint. Calling with either nil is a no-op.
+func (h *Handler) WithEmbedSync(store vectorstore.Store, embedder vectorstore.Embedder) *Handler {
+	h.embedStore = store
+	h.embedClient = embedder
+	return h
+}
+
 type queryRequest struct {
 	Query string `json:"query"`
 	Limit int    `json:"limit,omitempty"`
@@ -230,6 +241,32 @@ func (h *Handler) Write(w http.ResponseWriter, r *http.Request) {
 	writeJSON(w, map[string]string{"path": relPath})
 }
 
+// BackfillEmbeddings handles POST /backfill-embeddings — synchronously
+// embeds every note under brain/wiki/ that's not yet in the vector
+// store, and deletes rows for files no longer on disk.
+func (h *Handler) BackfillEmbeddings(w http.ResponseWriter, r *http.Request) {
+	if h.embedStore == nil || h.embedClient == nil {
+		writeError(w, http.StatusServiceUnavailable,
+			"embeddings not configured (set BRAIN_PG_DSN and BRAIN_EMBED_URL)")
+		return
+	}
+	res, err := vectorstore.Sync(r.Context(), h.brainDir, h.embedStore, h.embedClient)
+	if err != nil {
+		h.logger.Error("backfill failed", "err", err)
+		writeError(w, http.StatusInternalServerError, "backfill error")
+		return
+	}
+	errStrs := make([]string, 0, len(res.Errors))
+	for _, e := range res.Errors {
+		errStrs = append(errStrs, e.Error())
+	}
+	writeJSON(w, map[string]any{
+		"added":   res.Added,
+		"deleted": res.Deleted,
+		"errors":  errStrs,
+	})
+}
+
 type indexRequest struct {
 	Wing string `json:"wing,omitempty"`
 }