G2: embedd — text → vector via Ollama · 2 scrum fixes

Bridges the missing piece for the staffing co-pilot: text inputs to
vectord-shaped vectors. Standalone cmd/embedd on :3216 fronted by
gateway at /v1/embed. Pluggable embed.Provider interface (G2 ships
Ollama; OpenAI/Voyage swap in via the same interface in G3+).

Wire format:
  POST /v1/embed {"texts":[...], "model":"..."}  // model optional
  → 200 {"model","dimension","vectors":[[...]]}

Default model: nomic-embed-text (768-d). Ollama returns float64;
provider converts to float32 at the boundary so vectors flow through
vectord/HNSW without re-conversion.

Acceptance smoke 5/5 PASS — including the architectural payoff:
end-to-end embed → vectord add → search by re-embedded text returns
recall=1 at distance 5.96e-8 (float32 precision noise on identical
unit vectors). The staffing co-pilot pipeline (text → vector →
similarity search) is now functional end-to-end.

All 9 smokes (D1-D6 + G1 + G1P + G2) PASS deterministically.

Cross-lineage scrum on shipped code:
  - Opus 4.7 (opencode):                    0 BLOCK + 4 WARN + 3 INFO
  - Kimi K2-0905 (openrouter):              0 BLOCK + 2 WARN + 1 INFO
  - Qwen3-coder (openrouter):               "No BLOCKs" (3 tokens)

Fixed (2 — 1 convergent + 1 single-reviewer):
  C1 (Opus + Kimi convergent WARN): per-text 60s timeout × N-text
    batch was up to N×60s with no batch-level cap. One stuck Ollama
    call would stall the whole handler indefinitely. Fix:
    context.WithTimeout(r.Context(), 60s) wraps the entire batch.
  O-W3 (Opus WARN): empty strings in texts went to Ollama unchecked,
    producing version-dependent garbage. Fix: reject "" with 400 at
    the handler boundary so callers get a deterministic answer
    instead of an upstream-conditional 502.

Deferred (4): drainAndClose 64KiB cap (matches G0 pattern), no
concurrency limit on /embed (single-tenant G2), missing Accept
header (exotic-proxy concern), MaxBytesError string-match
redundancy (paranoia layer kept consistent across codebase).

Zero false positives this round — Qwen returned 3 tokens "No BLOCKs"
and the other two reviewers' findings were all real.

Setup confirmed: Ollama 0.21.0 on :11434 with nomic-embed-text loaded.
Per-text /api/embeddings used (forward-compat with 0.21+); newer
0.4+ /api/embed batch endpoint can swap in via the Provider interface.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

cmd/gateway/main.go

@@ -43,6 +43,7 @@ func main() {
 		"ingestd_url":  cfg.Gateway.IngestdURL,
 		"queryd_url":   cfg.Gateway.QuerydURL,
 		"vectord_url":  cfg.Gateway.VectordURL,
+		"embedd_url":   cfg.Gateway.EmbeddURL,
 	}
 	for k, v := range upstreams {
 		if v == "" {
@@ -61,12 +62,14 @@ func main() {
 	ingestdURL := mustParseUpstream("ingestd_url", cfg.Gateway.IngestdURL)
 	querydURL := mustParseUpstream("queryd_url", cfg.Gateway.QuerydURL)
 	vectordURL := mustParseUpstream("vectord_url", cfg.Gateway.VectordURL)
+	embeddURL := mustParseUpstream("embedd_url", cfg.Gateway.EmbeddURL)
 
 	storagedProxy := gateway.NewProxyHandler(storagedURL)
 	catalogdProxy := gateway.NewProxyHandler(catalogdURL)
 	ingestdProxy := gateway.NewProxyHandler(ingestdURL)
 	querydProxy := gateway.NewProxyHandler(querydURL)
 	vectordProxy := gateway.NewProxyHandler(vectordURL)
+	embeddProxy := gateway.NewProxyHandler(embeddURL)
 
 	if err := shared.Run("gateway", cfg.Gateway.Bind, func(r chi.Router) {
 		// Storage / catalog have multi-segment paths under their
@@ -82,6 +85,8 @@ func main() {
 		r.Handle("/v1/sql", querydProxy)
 		// Vector search routes — /v1/vectors/index, /v1/vectors/index/{name}/...
 		r.Handle("/v1/vectors/*", vectordProxy)
+		// Embedding service — /v1/embed
+		r.Handle("/v1/embed", embeddProxy)
 	}); err != nil {
 		slog.Error("server", "err", err)
 		os.Exit(1)