mesh-host/internal/profile/profile.go

// Package profile answers one question: what can this machine be asked to do?
//
// A capability is DETECTED, never assumed. That distinction is the whole point of this
// package and it is not pedantry — novox/hq 04-ISSUES/007 records the fault it exists to
// prevent: an installed package was treated as a capability, and a node was assigned work it
// could not perform because the package was present and the thing was not running.
//
// So a capability here is not "is it installed". It is "does it work", and every detector
// says how it knows.
package profile

import (
	"context"
	"errors"
	"fmt"
	"os/exec"
	"runtime"
	"sort"
	"strings"
	"time"
)

// Verdict is what a detector concluded, and why.
//
// Why is not decoration. A capability reported absent with no reason is the same problem in a
// new place: something that cannot be acted on. The reason is what a person reads when a node
// will not take work they expected it to take.
type Verdict struct {
	Name string `json:"name"`
	// Present is true only when the capability is usable, not merely installed.
	Present bool `json:"present"`
	// Detail says what was observed — a version, a path, or why it is absent.
	Detail string `json:"detail"`
	// How names the check that produced this, so a wrong answer can be found.
	How string `json:"how"`
}

// Detector decides one capability. It is given a context so a hung probe cannot hang the host.
type Detector interface {
	Name() string
	Detect(ctx context.Context) Verdict
}

// Runner executes a command. Replaceable in tests for the pure-logic layer ONLY — every
// detector in this package is exercised against the real machine as well, because a test that
// fakes the system under detection asserts that the fake behaves as expected
// (novox/hq ADR 0017).
type Runner func(ctx context.Context, name string, args ...string) (stdout string, err error)

// ExecRunner runs a real command, with output captured and stdin closed.
func ExecRunner(ctx context.Context, name string, args ...string) (string, error) {
	cmd := exec.CommandContext(ctx, name, args...)
	cmd.Stdin = nil
	out, err := cmd.Output()
	if err != nil {
		var exit *exec.ExitError
		if errors.As(err, &exit) {
			return string(out), fmt.Errorf("%s exited %d: %s",
				name, exit.ExitCode(), strings.TrimSpace(string(exit.Stderr)))
		}
		return string(out), fmt.Errorf("%s: %w", name, err)
	}
	return string(out), nil
}

// Profile is every verdict, in a stable order.
type Profile struct {
	Architecture string    `json:"architecture"`
	Kernel       string    `json:"kernel"`
	Capabilities []Verdict `json:"capabilities"`
	// Machine is what it is made of (novox/hq issue 160), said with every profile: at enrolment, after
	// every apply, and by the reconcile once a day when nothing else made it speak.
	Machine *Machine `json:"machine,omitempty"`
}

// Has reports whether a named capability is present. Unknown names are absent, not an error:
// asking about a capability nothing detects is a question with a true answer.
func (p Profile) Has(name string) bool {
	for _, v := range p.Capabilities {
		if v.Name == name {
			return v.Present
		}
	}
	return false
}

// Missing lists the names that are not present, in order. What a node cannot do is the half
// that decides whether work may be placed on it.
func (p Profile) Missing() []string {
	var out []string
	for _, v := range p.Capabilities {
		if !v.Present {
			out = append(out, v.Name)
		}
	}
	sort.Strings(out)
	return out
}

// Detect runs every detector and collects the verdicts.
//
// A detector that fails does not fail the profile. This is deliberately NOT the rule in
// novox/hq ADR 0010: that rule governs applying state, where a failed step means the machine
// is not what was asked for. Detection is the opposite — a failed probe is a finding, and the
// finding is "absent, because the probe failed", which is exactly what a caller needs to know.
// Aborting would replace one legible absence with total ignorance.
func Detect(ctx context.Context, detectors []Detector, timeout time.Duration) Profile {
	p := Profile{
		Architecture: runtime.GOARCH,
		Kernel:       runtime.GOOS,
	}
	for _, d := range detectors {
		probeCtx, cancel := context.WithTimeout(ctx, timeout)
		p.Capabilities = append(p.Capabilities, d.Detect(probeCtx))
		cancel()
	}
	sort.Slice(p.Capabilities, func(i, j int) bool {
		return p.Capabilities[i].Name < p.Capabilities[j].Name
	})
	describeCtx, cancel := context.WithTimeout(ctx, timeout)
	m := DescribeMachine(describeCtx, RealSources())
	cancel()
	p.Machine = &m
	return p
}