mesh-controller/internal/catalogue/resolve.go

package catalogue

import (
	"errors"
	"fmt"
	"sort"
	"strings"
)

// Resolving is turning "these modules are assigned here" into "this is what the node runs".
//
// It refuses rather than guesses, everywhere. novox/hq ADR 0009: a requirement with several
// answers is refused and named, because counting candidates has no surprising behaviour and a
// solver that picks has to be understood before its answer can be trusted.

// Node is what resolution needs to know about the machine.
type Node struct {
	Name string
	Site string
	// Capabilities the machine actually has, as its profile reported them. Only the present ones
	// — a capability that was looked for and not found is the same as one nobody looked for, as
	// far as deciding what may run here goes.
	Capabilities map[string]bool
}

// Held is a claim somebody already has, used for the scopes wider than one node.
type Held struct {
	Claim  string
	Scope  string
	Node   string
	Module string
	Site   string
}

// Resolution is what a node should run, and why.
type Resolution struct {
	// Node is which machine this was resolved for, so a generator can be asked about it.
	Node string

	// Modules in the order they were resolved: assigned first, then what they pulled in.
	Modules []Manifest
	// Because says why each module is here — assigned, or required by something.
	Because map[string]string
	// Claims is what this node's set holds, so wider scopes can be checked against it.
	Claims []Held
}

// Refusal is why a set of assignments cannot become a declaration.
//
// Every reason at once rather than the first, and each says what to do about it. A person
// resolving these fixes them in one pass or in four.
type Refusal struct{ Problems []string }

func (r *Refusal) Error() string {
	return "these assignments cannot be applied:\n  - " + strings.Join(r.Problems, "\n  - ")
}

// ErrAmbiguous is returned inside a Refusal when a requirement has more than one answer.
var ErrAmbiguous = errors.New("more than one module provides that")

// Resolve works out everything a node runs, from what was assigned to it.
//
// The catalogue is every module the mesh knows about; assigned is what a person put on this node.
// What comes back is the closure — assigned modules plus everything they require — or a refusal
// naming every reason it could not be closed.
func Resolve(catalogue map[string]Manifest, assigned []string, node Node, elsewhere []Held) (Resolution, error) {
	var problems []string

	// What each name can be satisfied by. Built once from the whole catalogue, because "how many
	// modules provide this" is the question the whole rule turns on.
	offers := map[string][]string{}
	for _, m := range catalogue {
		for _, o := range m.Offers() {
			offers[o] = append(offers[o], m.Module)
		}
	}
	for k := range offers {
		sort.Strings(offers[k])
	}

	chosen := map[string]bool{}
	because := map[string]string{}
	var order []string

	// What the set already offers, which is the first thing a requirement is checked against.
	//
	// Without this, assigning zsh does not satisfy something that requires a shell: the
	// requirement is counted against the catalogue, three modules provide it, and the answer is
	// still "choose one" after somebody has chosen one. That makes the remedy useless, and it is
	// how this read when first used.
	satisfied := map[string]bool{}

	// Everything a person assigned goes in first. Those are choices already made, and a
	// requirement one of them answers is not a choice to put back to anybody.
	queue := append([]string{}, assigned...)
	for _, a := range assigned {
		because[a] = "assigned"
		if m, known := catalogue[a]; known {
			for _, o := range m.Offers() {
				satisfied[o] = true
			}
		}
	}

	// What has already been complained about. A requirement can be wanted by several modules at
	// once, and saying the same thing twice makes a person hunt for the difference between two
	// identical lines before realising there is none.
	reported := map[string]bool{}

	for len(queue) > 0 {
		want := queue[0]
		queue = queue[1:]
		if chosen[want] || reported[want] {
			continue
		}
		// Already answered by something in the set. This is the case that makes assigning zsh do
		// what a person meant by it.
		if satisfied[want] && !isModule(catalogue, want) {
			continue
		}

		candidates := offers[want]
		switch len(candidates) {
		case 0:
			reported[want] = true
			problems = append(problems, fmt.Sprintf(
				"nothing provides %q, wanted by %s", want, because[want]))
			continue
		case 1:
			// No choice to make, so none is made. This is the case that lets `install i3` bring
			// in xorg without anybody being asked anything.
		default:
			reported[want] = true
			problems = append(problems, fmt.Sprintf(
				"%q is wanted by %s and %d modules provide it — choose one and assign it: %s",
				want, because[want], len(candidates), strings.Join(candidates, ", ")))
			continue
		}

		m := catalogue[candidates[0]]
		if chosen[m.Module] {
			continue
		}
		chosen[m.Module] = true
		order = append(order, m.Module)
		for _, o := range m.Offers() {
			satisfied[o] = true
		}
		if _, ok := because[m.Module]; !ok {
			because[m.Module] = fmt.Sprintf("required by %s", because[want])
		}

		for _, r := range m.Requires {
			if _, ok := because[r]; !ok {
				because[r] = m.Module
			}
			queue = append(queue, r)
		}
	}

	resolution := Resolution{Node: node.Name, Because: because}
	for _, n := range order {
		resolution.Modules = append(resolution.Modules, catalogue[n])
	}

	problems = append(problems, checkCapabilities(resolution.Modules, node)...)
	claims, claimProblems := checkClaims(resolution.Modules, node, elsewhere)
	problems = append(problems, claimProblems...)
	problems = append(problems, checkResources(resolution.Modules)...)
	resolution.Claims = claims

	if len(problems) > 0 {
		sort.Strings(problems)
		return Resolution{}, &Refusal{Problems: problems}
	}
	return resolution, nil
}

// isModule reports whether a name is a module in its own right rather than only something
// modules provide.
//
// A requirement naming a module is not satisfied by something else providing that name: `i3`
// requires `xorg` and means xorg, not "anything calling itself a display server".
func isModule(catalogue map[string]Manifest, want string) bool {
	_, ok := catalogue[want]
	return ok
}

// checkCapabilities refuses a module the machine cannot run.
//
// Said as a fact about the machine rather than about the module, because that is what it is and
// because nothing can be installed to change it.
func checkCapabilities(modules []Manifest, node Node) []string {
	var problems []string
	for _, m := range modules {
		for _, c := range m.Capabilities {
			if !node.Capabilities[c] {
				problems = append(problems, fmt.Sprintf(
					"%s needs the capability %q and %s does not have it — this is the wrong "+
						"machine, not a missing module", m.Module, c, node.Name))
			}
		}
	}
	return problems
}

// checkClaims refuses two modules holding one singular thing.
//
// Within this node's own set, and against what is already held elsewhere for the wider scopes. A
// claim at mesh scope is the same idea as the mesh's one hub, said once instead of hard-coded.
func checkClaims(modules []Manifest, node Node, elsewhere []Held) ([]Held, []string) {
	var problems []string
	var held []Held

	byScope := map[string]map[string]string{} // scope → claim → module
	for _, m := range modules {
		for _, c := range m.Claims {
			scope := c.At()
			if byScope[scope] == nil {
				byScope[scope] = map[string]string{}
			}
			if other, taken := byScope[scope][c.Name]; taken {
				problems = append(problems, fmt.Sprintf(
					"%s and %s both claim %q, and only one thing may hold it per %s",
					other, m.Module, c.Name, scope))
				continue
			}
			byScope[scope][c.Name] = m.Module
			held = append(held, Held{Claim: c.Name, Scope: scope, Node: node.Name,
				Module: m.Module, Site: node.Site})
		}
	}

	// And against the rest of the mesh, for the scopes that reach past this machine.
	for _, h := range held {
		for _, e := range elsewhere {
			if e.Node == node.Name || e.Claim != h.Claim || e.Scope != h.Scope {
				continue
			}
			switch h.Scope {
			case ScopeMesh:
				problems = append(problems, fmt.Sprintf(
					"%s on %s claims %q, which %s on %s already holds — one per mesh",
					h.Module, node.Name, h.Claim, e.Module, e.Node))
			case ScopeSite:
				if node.Site != "" && node.Site == e.Site {
					problems = append(problems, fmt.Sprintf(
						"%s on %s claims %q, which %s on %s already holds at %s — one per site",
						h.Module, node.Name, h.Claim, e.Module, e.Node, node.Site))
				}
			}
		}
	}
	return held, problems
}

// checkResources refuses two modules writing the same thing.
//
// This costs no manifest field: the mesh already holds every resource of every module, so two
// declaring one path or one unit are visible without either having to know about the other. A
// declared claim is only for the abstract conflicts nothing in the resources reveals.
func checkResources(modules []Manifest) []string {
	var problems []string
	owner := map[string]string{}

	for _, m := range modules {
		for _, r := range m.Resources {
			for _, field := range []string{"path", "unit", "name", "package"} {
				value, ok := r[field].(string)
				if !ok || value == "" {
					continue
				}
				key := field + " " + value
				if other, taken := owner[key]; taken && other != m.Module {
					problems = append(problems, fmt.Sprintf(
						"%s and %s both declare the %s %q", other, m.Module, field, value))
				}
				owner[key] = m.Module
			}
		}
	}
	return problems
}

// SettingsBy is the layers that apply to each module, keyed by module name.
type SettingsBy map[string][]Layer

// Generator works out a module's resources for one node, where they cannot be written in advance.
type Generator interface {
	// Resources for this node. Absent means the node is not part of whatever this generates,
	// which is an ordinary answer rather than a failure — a machine assigned the module before it
	// has an address on the network is in exactly that state.
	Resources(node string) ([]map[string]any, bool, error)
}

// Rendering is everything needed to turn a resolution into the declaration a node is sent.
type Rendering struct {
	Settings   SettingsBy
	Generators map[string]Generator
}

// Declaration is everything the resolved modules put on the node, with settings applied.
//
// Resource identities are prefixed with the module they came from. Two modules may reasonably
// both call something "config", and without this the second would silently replace the first —
// the node applying one of them and reporting success.
func (r Resolution) Declaration(with Rendering) ([]map[string]any, error) {
	var out []map[string]any
	for _, m := range r.Modules {
		resources := m.Resources
		if m.Computed != "" {
			generator, known := with.Generators[m.Computed]
			if !known {
				return nil, fmt.Errorf(
					"%s says its resources are computed by %q, and this control plane has no %q",
					m.Module, m.Computed, m.Computed)
			}
			generated, part, err := generator.Resources(r.Node)
			if err != nil {
				return nil, err
			}
			if !part {
				// Assigned, and not yet part of what this generates. Nothing to put on the
				// machine, which is different from an error: a node given the network module
				// before it has an address is in exactly that state, briefly.
				continue
			}
			resources = generated
		}
		for _, unsettled := range resources {
			resource, err := ApplySettings(unsettled, with.Settings[m.Module])
			if err != nil {
				return nil, err
			}
			copied := map[string]any{}
			for k, v := range resource {
				copied[k] = v
			}
			copied["id"] = m.Module + "." + fmt.Sprint(resource["id"])
			// A service saying what it reflects names resources within its own module, so those
			// are prefixed too or they would point at nothing.
			if reflects, ok := resource["restart-on"].([]any); ok {
				var renamed []any
				for _, id := range reflects {
					renamed = append(renamed, m.Module+"."+fmt.Sprint(id))
				}
				copied["restart-on"] = renamed
			}
			out = append(out, copied)
		}
	}
	return out, nil
}