cmd/mavend/modelseam_test.go

@@ -0,0 +1,91 @@
+package main
+
+import (
+	"net/http"
+	"net/http/httptest"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/kami/maven/internal/config"
+	"github.com/kami/maven/internal/llm"
+)
+
+// No `workstation` block is the shipping deploy. The seam must then be the
+// resident client itself, with nothing probing anything.
+func TestModelSeamUnconfiguredIsResidentOnly(t *testing.T) {
+	resident := llm.New("http://127.0.0.1:1", time.Second)
+	hot, pair := modelSeam(&config.Config{}, resident)
+	if pair != nil {
+		t.Error("built a pair with no workstation configured")
+	}
+	if hot == nil {
+		t.Fatal("no seam at all, so the cascade would route with the classifier")
+	}
+}
+
+// A workstation with no resident model behind it has no floor, and a Pair with
+// no floor is a configuration mistake rather than a degraded mode.
+func TestModelSeamWithoutResidentIsNil(t *testing.T) {
+	cfg := &config.Config{Workstation: &config.WorkstationConfig{URL: "http://127.0.0.1:1"}}
+	cfg.Workstation.Health = strings.TrimRight(cfg.Workstation.URL, "/") + "/health"
+	hot, pair := modelSeam(cfg, nil)
+	if hot != nil || pair != nil {
+		t.Errorf("built a seam with no floor: hot=%v pair=%v", hot, pair)
+	}
+}
+
+// The configured case: the seam is the pair, and the pair notices a workstation
+// that answers /health.
+func TestModelSeamPrefersAnAnsweringWorkstation(t *testing.T) {
+	up := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(http.StatusOK)
+	}))
+	defer up.Close()
+
+	cfg := &config.Config{Workstation: &config.WorkstationConfig{
+		URL:   up.URL,
+		Probe: config.Duration(10 * time.Millisecond),
+	}}
+	cfg.Workstation.Health = strings.TrimRight(cfg.Workstation.URL, "/") + "/health"
+
+	hot, pair := modelSeam(cfg, llm.New("http://127.0.0.1:1", time.Second))
+	if pair == nil || hot == nil {
+		t.Fatal("no pair built for a configured workstation")
+	}
+	defer pair.Stop()
+
+	deadline := time.Now().Add(2 * time.Second)
+	for !pair.Available() && time.Now().Before(deadline) {
+		time.Sleep(5 * time.Millisecond)
+	}
+	if !pair.Available() {
+		t.Fatal("the pair never saw a workstation that answers /health")
+	}
+}
+
+// A card held by a CPT run answers 503, and that must read as unavailable
+// rather than as an error a turn has to handle.
+func TestModelSeamHeldCardIsUnavailable(t *testing.T) {
+	busy := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		http.Error(w, "model not loaded", http.StatusServiceUnavailable)
+	}))
+	defer busy.Close()
+
+	cfg := &config.Config{Workstation: &config.WorkstationConfig{
+		URL:   busy.URL,
+		Probe: config.Duration(10 * time.Millisecond),
+	}}
+	cfg.Workstation.Health = strings.TrimRight(cfg.Workstation.URL, "/") + "/health"
+
+	_, pair := modelSeam(cfg, llm.New("http://127.0.0.1:1", time.Second))
+	if pair == nil {
+		t.Fatal("no pair built for a configured workstation")
+	}
+	defer pair.Stop()
+
+	time.Sleep(50 * time.Millisecond)
+	if pair.Available() {
+		t.Error("a 503 from the supervisor read as available")
+	}
+}

cmd/mavend/voicewire.go

@@ -48,7 +48,11 @@ type voiceWiring struct {
 	// mcp — the MCP client, nil unless the `mcp` block configures an enabled
 	// server (Vikunja #251). Its tools land in the same allowlist as every
 	// other act, so nothing else here has to know about it.
-	mcp *mcpWiring
+	// pair — the workstation model with the resident one as the floor, nil
+	// unless a `workstation` block names an address. Held here only so the
+	// prober is stopped on shutdown; callers were handed it at build time.
+	pair *llm.Pair
+	mcp  *mcpWiring
 	// home — the Home Assistant client, nil unless the `smarthome` block is
 	// enabled (Vikunja #256). Its devices land in the same allowlist as every
 	// other act, so nothing else here has to know about it.
@@ -76,6 +80,9 @@ func (w *voiceWiring) close() {
 	if w.ttsClient != nil {
 		_ = w.ttsClient.Close()
 	}
+	if w.pair != nil {
+		w.pair.Stop()
+	}
 	w.mcp.close()
 }
 
@@ -188,6 +195,11 @@ func wireVoice(cfg *config.Config, coreAPI ipc.CoreAPI, phr phraser.Phraser, mem
 		// the new llama-server when the resident model is swapped (Vikunja #250).
 		llmClient = llmClientFor(lp, 60*time.Second)
 	}
+	// The workstation model sits above that one when it is configured and its
+	// card is free. hot is what the router and the replier complete through:
+	// either the pair, or the resident client alone, or nothing at all.
+	hot, pair := modelSeam(cfg, llmClient)
+	w.pair = pair
 	// ----- router (the cascade; floor examples seed the classifier) -----
 	// The act matcher's allowlist is exactly the enabled tool names — the
 	// router only matches acts the executor can run (one source of truth).
@@ -199,7 +211,7 @@ func wireVoice(cfg *config.Config, coreAPI ipc.CoreAPI, phr phraser.Phraser, mem
 	// against the classifier's 50.0%, at about 1s a turn instead of 30ms (see
 	// config.VoiceConfig.LLMRouter). The classifier always stays wired as the
 	// fallback, so a model error never breaks a turn.
-	rtr := buildRouter(emb, matcher, threshold, pickLLMRouter(cfg.Voice.UseLLMRouter(), llmClient))
+	rtr := buildRouter(emb, matcher, threshold, pickLLMRouter(cfg.Voice.UseLLMRouter(), hot))
 
 	// ----- sessions registry (shared with voicesink) -----
 	sessions := voice.NewSessions()
@@ -233,8 +245,8 @@ func wireVoice(cfg *config.Config, coreAPI ipc.CoreAPI, phr phraser.Phraser, mem
 
 	// ----- replier (LLM-backed when the engine is on, Stub floor otherwise) -----
 	replier := voice.Replier(voice.NewStubReplier())
-	if llmClient != nil {
-		replier = newLLMReplier(llmClient, contextBlockFn(cfg, time.Now))
+	if hot != nil {
+		replier = newLLMReplier(hot, contextBlockFn(cfg, time.Now))
 	}
 
 	// ----- the handler (the reactive path; closes over stt / tts / router / coreAPI / memory) -----
@@ -291,7 +303,42 @@ func wireVoice(cfg *config.Config, coreAPI ipc.CoreAPI, phr phraser.Phraser, mem
 // pickLLMRouter returns the LLM router when the operator asked for it and there
 // is a llama-server to talk to, and nil otherwise. nil is safe: the cascade then
 // routes with the classifier, so an unusable setting costs accuracy, not turns.
-func pickLLMRouter(enabled bool, c *llm.Client) *router.LLMRouter {
+// modelSeam builds the completion seam the hot paths use: routing and replies.
+//
+// With no `workstation` block it is the resident client and nothing probes
+// anything, which is today's deploy exactly. With one, it is an llm.Pair that
+// prefers the workstation and falls back to the resident model silently — the
+// silent half of the degradation rule (docs/offload.md), because the big model
+// is only better here and the 1.7B is today's shipping quality. He is never
+// told which of the two phrased his reply.
+//
+// A nil resident client means the phraser is not an LLM phraser. There is then
+// no floor, and a Pair with no floor is a configuration mistake rather than a
+// degraded mode, so the seam is nil and the cascade routes with the classifier.
+func modelSeam(cfg *config.Config, resident *llm.Client) (router.Completer, *llm.Pair) {
+	if resident == nil {
+		if cfg.Workstation != nil {
+			log.Printf("voice: a workstation is configured but there is no resident model to floor it with — ignoring the block")
+		}
+		return nil, nil
+	}
+	if cfg.Workstation == nil {
+		return resident, nil
+	}
+	ws := cfg.Workstation
+	pair := llm.NewPair(
+		llm.New(ws.URL, time.Duration(ws.Timeout)),
+		resident,
+		ws.Health,
+		time.Duration(ws.Probe),
+	)
+	pair.Start(context.Background())
+	log.Printf("voice: workstation model at %s, probed every %s, resident model as the floor",
+		ws.URL, time.Duration(ws.Probe))
+	return pair, pair
+}
+
+func pickLLMRouter(enabled bool, c router.Completer) *router.LLMRouter {
 	if !enabled {
 		return nil
 	}