mesh-controller/cmd/mesh-control/acts.go

package main

import (
	"context"
	"fmt"
	"sort"
	"strings"

	"github.com/novox/mesh-control/internal/catalogue"
)

// The things the mesh can be asked to do, separated from how it was asked.
//
// **A surface is an adapter with no decisions in it** (novox/hq ADR 0035). The command line and
// the command API call the same functions here, so an assignment refused at one is refused at the
// other for the same reason and in the same words. The moment a surface can accept something
// another would reject, the mesh has two answers to one question and people learn which to trust.
//
// Each returns what happened as text a person can read and a caller can pass on. Neither surface
// composes its own explanation, because two explanations of one refusal drift.

// assign puts a module on a node, and says at once what in the mesh no longer works out.
//
// The assignment is kept even when the node does not resolve: it is what a person meant, and
// assignment is not an ordering. A consumer assigned before its provider does not resolve for as
// long as it takes to assign the provider, and refusing the first half of a pair would make the
// order somebody types two commands in part of the mesh's rules.
//
// **What is checked is the mesh, not the one machine** — because that is what the assignment
// changes. novox/hq 04-ISSUES/017 names the shape: an action can succeed into a state its own
// verify rejects, and it happens when the action's test is not the test the verify uses. Here the
// action tested one node and the verify is resolution over all of them, so an assignment could be
// reported as fine while it took a provision away from every other machine — a module offering a
// mesh-scoped provision stops offering it the moment its own node stops resolving, and every
// consumer elsewhere is then told *nothing in this mesh provides it*, with a remedy that names a
// module already assigned. That was found on a four-node raise and read as a version bump breaking
// provider recognition; it was neither the version nor the provider.
//
// It costs a resolution per machine. Assignment is a person typing a command, and being told which
// machines this just blocked is worth more than the milliseconds.
func assign(ctx context.Context, open *stores, node, module string) (string, error) {
	if err := open.inventory.Assign(ctx, node, module); err != nil {
		return "", err
	}
	said := fmt.Sprintf("%s is assigned %s", node, module)
	plan, _, err := planFor(ctx, open, node)
	if err != nil {
		// Kept, and still refused. Both halves are the answer, and the rest of the mesh is still
		// worth reporting: this machine's refusal is rarely the only consequence.
		return said + blockedElsewhere(ctx, open, node), err
	}
	// Kept, and cannot be hosted here. Said at once rather than discovered at push: a module whose
	// capability the machine lacks is on the wrong machine, and the assignment records what a person
	// meant while this line says it will not run until it moves. The rest of the node still pushes.
	for _, u := range plan.Unhostable {
		if u.Module != module {
			continue
		}
		for _, c := range u.Missing {
			said += "\n  but " + catalogue.WrongMachine(u.Module, c, node)
		}
	}
	return said + fmt.Sprintf("\n  run `push %s` to send it", node) +
		blockedElsewhere(ctx, open, node), nil
}

// unassign takes a module off a node. What it leaves behind is the host's business: a directory
// holding anything the mesh did not put there is kept (novox/hq ADR 0030).
//
// It reports the rest of the mesh for the same reason assign does, and more sharply: taking a
// module off one machine is the ordinary way to stop providing something to another, and nothing
// about the command's own output would ever have said so.
func unassign(ctx context.Context, open *stores, node, module string) (string, error) {
	if err := open.inventory.Unassign(ctx, node, module); err != nil {
		return "", err
	}
	return fmt.Sprintf("%s no longer runs %s — run `push %s` to make it so",
		node, module, node) + blockedElsewhere(ctx, open, node), nil
}

// blockedElsewhere is every OTHER machine that cannot be worked out as things now stand.
//
// **The state, not the cause.** Saying "this assignment broke laptop" would mean resolving the
// whole mesh twice and would still be a guess about which of several changes did it; saying
// "laptop cannot be worked out, and here is what it says" is true, is what somebody has to fix,
// and cannot mislead. The machine that was just changed is left out because its own refusal is
// already the answer beside this one.
//
// Nothing here can fail the act it reports on. A mesh that cannot be read is worth saying and is
// not a reason to claim the assignment did not happen — it did.
func blockedElsewhere(ctx context.Context, open *stores, except string) string {
	nodes, err := open.inventory.Nodes(ctx)
	if err != nil {
		return "\n\nThe rest of the mesh could not be checked: " + err.Error()
	}
	blocked := map[string]string{}
	for _, n := range nodes {
		if n.Name == except {
			continue
		}
		if _, _, err := planFor(ctx, open, n.Name); err != nil {
			blocked[n.Name] = err.Error()
		}
	}
	if len(blocked) == 0 {
		return ""
	}
	names := make([]string, 0, len(blocked))
	for name := range blocked {
		names = append(names, name)
	}
	sort.Strings(names)

	var out strings.Builder
	fmt.Fprintf(&out, "\n\nAND %d other machine(s) cannot be worked out as things stand, so "+
		"nothing will be sent to them:\n", len(names))
	for _, name := range names {
		fmt.Fprintf(&out, "  %s\n", name)
		for _, line := range strings.Split(strings.TrimRight(blocked[name], "\n"), "\n") {
			fmt.Fprintf(&out, "    %s\n", strings.TrimSpace(line))
		}
	}
	out.WriteString("\nThis may or may not be what just changed — it is what is true now.")
	return out.String()
}