llama-sidecar v0.1.0: daemon + benchmarks + eval suite

Go daemon (cmd/llama-sidecar): per-agent llama-server process pool with
LRU eviction, OpenAI-compatible proxy, flag validation (Unsloth port),
deterministic hash-keyed sidecar reuse. Windows service support via
schtasks/NSSM with DETACHED_PROCESS, stdout pipe drain, and request-ctx
decoupled child lifetime.

Bug fixes (3b.1–3b5): -c flag drop from StripShadowingFlags, UTF-8 BOM
in JSON config, -fa → --flash-attn on default, child process exit after
one request (stdin devnull, stdout pipe, CREATE_NO_WINDOW → DETACHED,
context.Background for child lifetime, background reaper goroutine).

bench/: MTP on/off throughput sweep across 8 GGUFs via SSH+schtasks
automation to sam-desktop. Per-GGUF production flags from llama-swap
config with --ctx-size 32768 override.

eval/: accuracy benchmarks (MMLU 100q, GSM8K 50q, HumanEval 164) +
A/B model comparison (14 agent-typed prompts × 8 models). All scripts
resumable at individual question level.

94 Go tests, race detector clean.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

internal/winsvc/winsvc_unix.go

@@ -0,0 +1,26 @@
+//go:build !windows
+
+package winsvc
+
+import (
+	"context"
+	"log/slog"
+	"os"
+	"os/signal"
+	"syscall"
+	"time"
+)
+
+func RegisterShutdownHandler(ctx context.Context, shutdownFunc func(context.Context) error) {
+	sigCh := make(chan os.Signal, 1)
+	signal.Notify(sigCh, syscall.SIGTERM, syscall.SIGINT)
+	<-sigCh
+	slog.Info("shutdown signal received")
+	shutdownCtx, cancel := context.WithTimeout(ctx, 30*time.Second)
+	defer cancel()
+	if err := shutdownFunc(shutdownCtx); err != nil {
+		slog.Error("shutdown error", "err", err)
+		os.Exit(1)
+	}
+	os.Exit(0)
+}

internal/winsvc/winsvc_windows.go

@@ -0,0 +1,25 @@
+//go:build windows
+
+package winsvc
+
+import (
+	"context"
+	"log/slog"
+	"os"
+	"os/signal"
+	"time"
+)
+
+func RegisterShutdownHandler(ctx context.Context, shutdownFunc func(context.Context) error) {
+	sigCh := make(chan os.Signal, 1)
+	signal.Notify(sigCh, os.Interrupt)
+	<-sigCh
+	slog.Info("shutdown signal received")
+	shutdownCtx, cancel := context.WithTimeout(ctx, 30*time.Second)
+	defer cancel()
+	if err := shutdownFunc(shutdownCtx); err != nil {
+		slog.Error("shutdown error", "err", err)
+		os.Exit(1)
+	}
+	os.Exit(0)
+}