v0.10.6

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

CHANGELOG.md

@@ -20,10 +20,17 @@ is only released once its **exit criterion** is met, not when its code lands.
 Until v1.0.0 the minor version is the breaking one: configuration formats and Go
 APIs change between minors without a deprecation period.
 
-## Unreleased
+## v0.10.6 — 2026-10-01
 
-Changes since v0.10.5, published as release candidates (v0.10.6-rc.N) until
-there are enough for v0.10.6.
+Published first as release candidates v0.10.6-rc.1 to rc.8; rc.5 failed its
+format check and has no binaries.
+
+Tried on the PoC cluster before release: LoRA adapters asked for by name
+through the gateway, two on one model, each answering as trained and the model
+itself unchanged; a saturated pool spilling to the next (8 of 12 concurrent
+requests on the preferred replica, 4 on the other); and a bronze request
+displaced from a full queue by a gold one, with 503 and Retry-After 5. Not tried
+live: a model served from an external provider, which needs a provider key.
 
 ### Capacity from the admin pages
 
@@ -46,7 +53,7 @@ What v0.10.5 made settable from the command line is now on the pages too:
 
 A llama.cpp model can carry `adapters`, each a name and a GGUF LoRA file. The
 nodes fetch them with the model's weights and llama.cpp loads them all at start,
-applied to nothing (`--lora-init-without-apply`); a request that names an
+applied to nothing (`--lora-scaled FILE:0`); a request that names an
 adapter goes to the model's replicas with `"lora": [{"id": i, "scale": s}]`,
 so one replica serves the model and all its adapters. Adapter names share the
 namespace of models, are listed in `/v1/models`, and follow key allowlists on

internal/agent/engines/llamacpp.go

@@ -146,12 +146,12 @@ func (l *LlamaCpp) Commands(s ShardSpec) ([]Command, error) {
 	}
 	// Loaded at start, applied per request: a request that names an adapter
 	// carries "lora": [{"id": i, "scale": s}], and one that names none is the
-	// base model, since every adapter starts at scale zero.
-	if len(p.Adapters) > 0 {
-		args = append(args, "--lora-init-without-apply")
-		for _, a := range p.Adapters {
-			args = append(args, "--lora", a.Path)
-		}
+	// base model. Each is loaded at scale zero, not with --lora and
+	// --lora-init-without-apply: that leaves an adapter's scale at 1, and
+	// llama-server applies it at that scale to every request with no "lora"
+	// of its own — every request for the model itself.
+	for _, a := range p.Adapters {
+		args = append(args, "--lora-scaled", a.Path+":0")
 	}
 	args = append(args, p.Args...)
 

internal/agent/engines/llamacpp_test.go

@@ -315,8 +315,8 @@ func TestAdaptersAreLoadedAtStartAndAppliedToNoneByDefault(t *testing.T) {
 		t.Fatal(err)
 	}
 	args := strings.Join(cmds[0].Args, " ")
-	if !strings.Contains(args, "--lora-init-without-apply --lora /w/sql.gguf --lora /w/docs.gguf") {
-		t.Errorf("args %s: both adapters, in order, loaded unapplied", args)
+	if !strings.Contains(args, "--lora-scaled /w/sql.gguf:0 --lora-scaled /w/docs.gguf:0") {
+		t.Errorf("args %s: both adapters, in order, loaded at scale zero", args)
 	}
 	plain, _ := (&LlamaCpp{}).Commands(llamaSpec(nil))
 	if strings.Contains(strings.Join(plain[0].Args, " "), "--lora") {

internal/router/handlers.go

@@ -1013,7 +1013,7 @@ func withModel(body []byte, name string) []byte {
 
 // withAdapter is body asking for model with a LoRA adapter applied, in
 // llama.cpp's form: "lora": [{"id": index, "scale": scale}]. Adapters not
-// listed are applied at zero, so the list is the whole of it.
+// listed stay at zero, the scale the engine loads each one at.
 func withAdapter(body []byte, model string, index int, scale float64) []byte {
 	var m map[string]json.RawMessage
 	if err := json.Unmarshal(body, &m); err != nil {