A release was a git tag. Installing llmgw on a node meant having a Go toolchain, and the onboarding script copied a binary from wherever it was run — which works and quietly makes whoever runs it the build server, with the fleet ending up on whatever was in their working tree. Tags now build static linux/amd64, linux/arm64 and darwin binaries and attach them. CGO_ENABLED=0 is the point: it has to run on a node whose libc is older than the builder's, and llmgw has no C dependency because modernc.org/sqlite is pure Go precisely so this stays true. Verified: "not a dynamic executable", runs on a node, reports its version. `ctl engine-check` closes the other half of the phase 4 gap. llmgw's launch arguments are read from each engine's documentation, and engines rename flags between versions; when that happens the failure arrives minutes into a model load, in the engine's own error message, on a node nobody was watching. It builds the widest command llmgw would ever produce — multi-node, since a flag that only appears there is the one nobody notices has gone — and checks each flag against the engine's own --help. No GPU: a CLI prints its help anywhere. Verified against llama.cpp b10991, all seven flags accepted. Flags are matched on a word boundary, so --port is not satisfied by --port-range. Without that, a renamed flag would sail through the check that exists to catch renamed flags. It also warns when the help text looks truncated, which is how the first run went: llama.cpp's help cut to 400 of its 725 lines reported five flags as missing that the running cluster uses. TestSidecarRunsBeforeEngine was flaky under a full run, and worse than flaky — its wait loop fell through on timeout, so a slow machine turned the ordering assertion into a no-op and the failure surfaced later as something else. It now asserts, with a deadline that suits a machine running every other package at the same time. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
188 lines
5.6 KiB
Go
188 lines
5.6 KiB
Go
package cli
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"os/exec"
|
|
"sort"
|
|
"strings"
|
|
"time"
|
|
|
|
"github.com/spf13/cobra"
|
|
|
|
"gitea.mynodes.xyz/ilker/llmgw/internal/agent/engines"
|
|
)
|
|
|
|
func newEngineCheckCmd() *cobra.Command {
|
|
var (
|
|
help string
|
|
nodes int
|
|
tp int
|
|
perNode int
|
|
)
|
|
|
|
cmd := &cobra.Command{
|
|
Use: "engine-check <engine>",
|
|
Short: "Check that an engine still accepts the flags llmgw builds for it",
|
|
Long: "llmgw's launch arguments are read from each engine's documentation, and\n" +
|
|
"engines rename and remove flags between versions. When that happens the\n" +
|
|
"failure arrives minutes into a model load, in an engine's own error\n" +
|
|
"message, on a node nobody was watching.\n\n" +
|
|
"This asks the engine itself. It runs the engine's --help and checks every\n" +
|
|
"flag llmgw would pass against it, which needs no GPU — a CLI prints its\n" +
|
|
"help on any machine. Run it after upgrading an engine.\n\n" +
|
|
"With --help-output it reads a saved --help instead of running anything,\n" +
|
|
"so the check works from a laptop against help captured on a node.",
|
|
Args: cobra.ExactArgs(1),
|
|
RunE: func(cmd *cobra.Command, args []string) error {
|
|
name := args[0]
|
|
reg := engines.NewRegistry(engines.Config{})
|
|
eng, err := reg.Get(name)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
spec := representativeShard(name, nodes, tp, perNode)
|
|
cmds, err := eng.Commands(spec)
|
|
if err != nil {
|
|
return fmt.Errorf("building a command for %s: %w", name, err)
|
|
}
|
|
|
|
text := help
|
|
if text == "" {
|
|
if text, err = runHelp(cmd.Context(), cmds); err != nil {
|
|
return err
|
|
}
|
|
}
|
|
|
|
// A truncated help produces confident nonsense: every flag below the
|
|
// cut looks missing. Real help text documents --help itself, which
|
|
// is the cheapest signal that we are looking at all of it.
|
|
if !mentions(text, "--help") {
|
|
cmd.PrintErrln("warning: this help text does not document --help, " +
|
|
"which usually means it was truncated. Flags below the cut will " +
|
|
"look missing.")
|
|
}
|
|
|
|
var unknown []string
|
|
seen := map[string]bool{}
|
|
for _, c := range cmds {
|
|
for _, a := range c.Args {
|
|
flag, _, _ := strings.Cut(a, "=")
|
|
if !strings.HasPrefix(flag, "--") || seen[flag] {
|
|
continue
|
|
}
|
|
seen[flag] = true
|
|
if !mentions(text, flag) {
|
|
unknown = append(unknown, flag)
|
|
}
|
|
}
|
|
}
|
|
sort.Strings(unknown)
|
|
|
|
out := cmd.OutOrStdout()
|
|
fmt.Fprintf(out, "%s: %d flags checked\n", name, len(seen))
|
|
for _, c := range cmds {
|
|
fmt.Fprintf(cmd.ErrOrStderr(), " %s %s\n", c.Path, strings.Join(c.Args, " "))
|
|
}
|
|
if len(unknown) == 0 {
|
|
fmt.Fprintln(out, "every flag llmgw builds is accepted by this engine")
|
|
return nil
|
|
}
|
|
fmt.Fprintf(out, "\n%d flags this engine does not mention:\n", len(unknown))
|
|
for _, f := range unknown {
|
|
fmt.Fprintf(out, " %s\n", f)
|
|
}
|
|
return fmt.Errorf("%s does not accept %d of the flags llmgw builds", name, len(unknown))
|
|
},
|
|
}
|
|
|
|
f := cmd.Flags()
|
|
f.StringVar(&help, "help-output", "", "a saved --help to check against, instead of running the engine")
|
|
f.IntVar(&nodes, "nodes", 2, "shape the command for a replica of this many nodes")
|
|
f.IntVar(&tp, "tp", 8, "tensor parallel degree")
|
|
f.IntVar(&perNode, "gpus-per-node", 4, "GPUs each node contributes")
|
|
return cmd
|
|
}
|
|
|
|
// representativeShard is the widest command llmgw would ever build, because a
|
|
// flag that only appears in the multi-node case is exactly the one nobody
|
|
// notices has been renamed.
|
|
func representativeShard(engine string, nodes, tp, perNode int) engines.ShardSpec {
|
|
if nodes < 1 {
|
|
nodes = 1
|
|
}
|
|
return engines.ShardSpec{
|
|
ReplicaID: "check", ShardID: "check-r0", Rank: 0, NNodes: nodes,
|
|
LeaderAddr: "10.0.0.1", LeaderPort: 20001,
|
|
GPUIndices: seq(perNode), HCAs: []string{"mlx5_0"},
|
|
MgmtInterface: "eth0", HTTPPort: 20000,
|
|
Profile: engines.Profile{
|
|
Name: "check", Engine: engine, TP: tp, Nodes: nodes, GPUsPerNode: perNode,
|
|
ModelPath: "/models/x", ServedModelName: "x",
|
|
},
|
|
}
|
|
}
|
|
|
|
func seq(n int) []int {
|
|
out := make([]int, n)
|
|
for i := range out {
|
|
out[i] = i
|
|
}
|
|
return out
|
|
}
|
|
|
|
// runHelp asks the engine to describe itself.
|
|
//
|
|
// The last command is the one that serves; the sidecars before it are a
|
|
// different program with a different vocabulary, so its help would be the wrong
|
|
// help to check against.
|
|
func runHelp(ctx context.Context, cmds []engines.Command) (string, error) {
|
|
c := cmds[len(cmds)-1]
|
|
|
|
// Everything up to the first flag, plus --help. Passing the real arguments
|
|
// would start the engine.
|
|
var args []string
|
|
for _, a := range c.Args {
|
|
if strings.HasPrefix(a, "-") {
|
|
break
|
|
}
|
|
args = append(args, a)
|
|
}
|
|
args = append(args, "--help")
|
|
|
|
ctx, cancel := context.WithTimeout(ctx, 2*time.Minute)
|
|
defer cancel()
|
|
|
|
out, err := exec.CommandContext(ctx, c.Path, args...).CombinedOutput()
|
|
if err != nil && len(out) == 0 {
|
|
return "", fmt.Errorf("running %s %s: %w\n"+
|
|
"(is the engine installed here? use --help-output to check against a saved one)",
|
|
c.Path, strings.Join(args, " "), err)
|
|
}
|
|
return string(out), nil
|
|
}
|
|
|
|
// mentions reports whether the help text documents a flag.
|
|
//
|
|
// Matched on a word boundary, so --port does not satisfy --port-range and a
|
|
// missing flag cannot hide behind a longer one that happens to contain it.
|
|
func mentions(help, flag string) bool {
|
|
for i := 0; ; {
|
|
j := strings.Index(help[i:], flag)
|
|
if j < 0 {
|
|
return false
|
|
}
|
|
end := i + j + len(flag)
|
|
if end == len(help) || !isFlagChar(help[end]) {
|
|
return true
|
|
}
|
|
i = end
|
|
}
|
|
}
|
|
|
|
func isFlagChar(b byte) bool {
|
|
return b == '-' || b == '_' || (b >= 'a' && b <= 'z') ||
|
|
(b >= 'A' && b <= 'Z') || (b >= '0' && b <= '9')
|
|
}
|