steve
f34773b505
Lands the protocol layer end-to-end: an agent can be enrolled through the operator UI, store credentials, dial back to the server over WS, complete the protocol_version handshake, and stay connected with periodic heartbeats. Server side: - P1-09 ws.Hub: one Conn per host_id, last-write-wins eviction, json envelope writer with a write mutex, reader, error envelopes. - P1-09 ws.AgentHandler: bearer-auth, accept upgrade, hello-stage (10s deadline, protocol_version checked against api.MinAgentProtocolVersion → ErrProtocolTooOld with help URL on reject), main read loop, defer hub register/unregister. - P1-10 POST /api/agents/enroll consumes a one-time token, mints a persistent agent bearer (sha-256 stored), creates a host row. - P1-10 POST /api/enrollment-tokens (operator, session-auth) issues a 1h one-time token. - P1-11 hello upserts agent_version + restic_version + protocol_version on the host row, flips status to online. - P1-12 heartbeat touches last_seen_at; background sweeper marks hosts offline after 90s without one. - store: hosts table accessors, host_schedule_version, enrollment_tokens FK on consumed_host dropped (audit-only field; the token gets burned before the host row exists). Agent side: - P1-13 internal/agent/config: yaml at /etc/restic-manager/agent.yaml, atomic Save (tmp+fsync+rename), Enrolled() helper. - P1-15 internal/agent/wsclient: dial with bearer + optional TLS cert pinning (sha-256 of leaf), exponential backoff with jitter (1s → 60s cap), heartbeat goroutine, fatal handling for ErrProtocolTooOld. - P1-15 wsclient.Enroll: HTTP POST /api/agents/enroll with sysinfo. - P1-17 internal/agent/sysinfo: hostname/OS/arch/restic-version collection. restic detected by `restic version` parse; absent restic doesn't block startup. - cmd/agent: -enroll-server / -enroll-token flags drive first-run enrollment then exit (so the install script can hand off to systemd to run the persistent service). End-to-end smoke verified: bootstrap → login → issue token → enroll → run agent → server logs `ws agent connected` with the right host_id and protocol_version 1. All tests still pass. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
79 lines
2.2 KiB
Go
79 lines
2.2 KiB
Go
// Package sysinfo collects host metadata at agent startup: OS, arch,
|
|
// hostname, restic version. The agent sends this in `hello` so the
|
|
// server's Host row stays current.
|
|
package sysinfo
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"os"
|
|
"os/exec"
|
|
"runtime"
|
|
"strings"
|
|
"time"
|
|
|
|
"gitea.dcglab.co.uk/steve/restic-manager/internal/api"
|
|
)
|
|
|
|
// Snapshot is the bundle of metadata reported in `hello`.
|
|
type Snapshot struct {
|
|
Hostname string
|
|
OS api.HostOS
|
|
Arch api.HostArch
|
|
ResticVersion string
|
|
ProtocolVersion int
|
|
BootTime time.Time
|
|
}
|
|
|
|
// Collect probes the running host. resticPath, if non-empty,
|
|
// overrides PATH lookup.
|
|
func Collect(ctx context.Context, resticPath string) (Snapshot, error) {
|
|
hn, err := os.Hostname()
|
|
if err != nil {
|
|
return Snapshot{}, fmt.Errorf("sysinfo: hostname: %w", err)
|
|
}
|
|
|
|
osTag := api.HostOS(runtime.GOOS)
|
|
archTag := api.HostArch(runtime.GOARCH)
|
|
|
|
resticVer, _ := detectResticVersion(ctx, resticPath) // empty on failure is fine
|
|
return Snapshot{
|
|
Hostname: hn,
|
|
OS: osTag,
|
|
Arch: archTag,
|
|
ResticVersion: resticVer,
|
|
ProtocolVersion: api.CurrentProtocolVersion,
|
|
}, nil
|
|
}
|
|
|
|
// detectResticVersion runs `restic version` and parses the first line.
|
|
// Output looks like:
|
|
// restic 0.17.1 compiled with go1.22.5 on linux/amd64
|
|
// Returns the version token (e.g. "0.17.1") or "" if restic isn't
|
|
// found. We never block startup on a missing restic — the operator
|
|
// might not have installed it yet, and the agent should still be
|
|
// able to connect and report.
|
|
func detectResticVersion(ctx context.Context, override string) (string, error) {
|
|
bin := override
|
|
if bin == "" {
|
|
var err error
|
|
bin, err = exec.LookPath("restic")
|
|
if err != nil {
|
|
return "", err
|
|
}
|
|
}
|
|
|
|
versionCtx, cancel := context.WithTimeout(ctx, 5*time.Second)
|
|
defer cancel()
|
|
out, err := exec.CommandContext(versionCtx, bin, "version").Output()
|
|
if err != nil {
|
|
return "", err
|
|
}
|
|
first := strings.SplitN(strings.TrimSpace(string(out)), "\n", 2)[0]
|
|
parts := strings.Fields(first)
|
|
if len(parts) >= 2 && parts[0] == "restic" {
|
|
return parts[1], nil
|
|
}
|
|
return "", fmt.Errorf("sysinfo: unrecognised restic version output: %q", first)
|
|
}
|