Write each module's have and the node's own facts beside the report, grouped per module and keyed by the module the controller names (issue 1132)

The node-engine reads a resource's module and a declaration's builds, says it does in every report (reads_modules), groups the apply's outcome per module with every failing resource named, and writes have.<node>.<module> and have.<node>.node to the bucket only when a value differs, never ahead of or in place of the report (novox/hq ADR 0429 section 4).

internal/apply/apply.go

@@ -179,6 +179,23 @@ type Error struct {
 	// (novox/hq ADR 0136) or a directory the engine refused (issue 495). Named, because "everything
 	// was attempted" is then untrue, and a report that says so after skipping a module lies.
 	Modules []string
+
+	// Failures is every resource that failed, the first among them, each with its error (issue 1132, novox/hq ADR
+	// 0429 §4): Others counts the rest and names none, and a module's state on the bus names what failed in it.
+	Failures []Failure
+}
+
+// Failure is one resource that failed in an apply, and why.
+type Failure struct {
+	Resource string
+	Err      error
+}
+
+// ModuleResult is how one module's part of an apply ended (issue 1132).
+type ModuleResult struct {
+	Failed bool
+	// Detail names each failing resource with its error, or why the module was not attempted.
+	Detail string
 }
 
 func (e *Error) Error() string {
@@ -747,6 +764,7 @@ func ApplyMindingWindows(
 				first := failures[0]
 				first.Done = report
 				first.Others = len(failures) - 1
+				first.Failures = failuresOf(failures)
 				first.Modules = gatedModules()
 				log("  kept " + guardPrefix + "*: the guard is not up, so what it replaces was left in force")
 				return report, known, first
@@ -758,7 +776,7 @@ func ApplyMindingWindows(
 		// **A module whose step did not complete is skipped from there on** (novox/hq ADR 0136).
 		// Reported rather than passed over in silence: "not attempted" and "nothing to do" are
 		// different answers, and only one of them is somebody's to fix.
-		if module, ours := moduleOf(resource.Identity()); ours && gated[module] {
+		if module, ours := d.ModuleOfID(resource.Identity()); ours && gated[module] {
 			report.Outcomes = append(report.Outcomes, Outcome{
 				ID: resource.Identity(), Type: string(resource.Kind()), Target: resource.Target(),
 				Action: "skipped", Detail: gatedWhy[module],
@@ -920,7 +938,7 @@ func ApplyMindingWindows(
 				in.refused[filepath.Clean(dir.Path)] = err
 			}
 			if dir, ok := resource.(*declaration.Directory); ok && in.refused[filepath.Clean(dir.Path)] != nil {
-				if module, ours := moduleOf(resource.Identity()); ours {
+				if module, ours := d.ModuleOfID(resource.Identity()); ours {
 					gated[module] = true
 					gatedWhy[module] = fmt.Sprintf("its directory %s was refused (novox/hq issue 495), so "+
 						"nothing more of this module was attempted", filepath.Clean(dir.Path))
@@ -969,7 +987,7 @@ func ApplyMindingWindows(
 				//
 				// An action still gates the machine: the bootstrap is a row of them, each making the
 				// next possible, and they belong to no module.
-				if module, ours := moduleOf(resource.Identity()); ours {
+				if module, ours := d.ModuleOfID(resource.Identity()); ours {
 					gated[module] = true
 					gatedWhy[module] = "a step this module declares did not complete"
 					log(fmt.Sprintf("  gated %s.*: a step it declares did not complete, so the rest "+
@@ -979,6 +997,7 @@ func ApplyMindingWindows(
 				failed.Stopped = true
 				failed.Done = report
 				failed.Others = len(failures) - 1
+				failed.Failures = failuresOf(failures)
 				failed.Modules = gatedModules()
 				return report, known, failed
 			}
@@ -1162,6 +1181,7 @@ func ApplyMindingWindows(
 		first := failures[0]
 		first.Done = report
 		first.Others = len(failures) - 1
+		first.Failures = failuresOf(failures)
 		first.Modules = gatedModules()
 		return report, known, first
 	}
@@ -3696,16 +3716,10 @@ func unitKey(scope, user, unit string) string {
 // False for what the mesh declares in its own right: the foundation's resources carry no dot at all,
 // and the adoption's are named for the mesh rather than for a module. Both belong to no module, and
 // their gate is therefore the machine's.
-func moduleOf(identity string) (string, bool) {
-	if strings.HasPrefix(identity, declaration.AdoptionPrefix) {
-		return "", false
-	}
-	at := strings.LastIndex(identity, ".")
-	if at <= 0 {
-		return "", false
-	}
-	return identity[:at], true
-}
+//
+// This is the guess from an id alone, for a caller with no declaration in hand; a caller with one asks
+// Declaration.ModuleOfID, which reads the module the controller said (issue 1132).
+func moduleOf(identity string) (string, bool) { return declaration.ModuleGuess(identity) }
 
 // handOver removes what a process replaces, once the process is running and still is a moment later
 // (novox/hq issue 213, ADR 0184). A replacement that is not up keeps what it replaces in place

internal/apply/module_results.go

@@ -0,0 +1,99 @@
+package apply
+
+import (
+	"errors"
+	"fmt"
+	"sort"
+	"strings"
+
+	"github.com/novox/mesh-host/internal/declaration"
+)
+
+// failuresOf is every failure of an apply as the error carries it: the first among them, then the rest, so a module
+// whose resource failed second is still named (issue 1132, and issue 500, which counted the rest and named none).
+func failuresOf(failures []*Error) []Failure {
+	out := make([]Failure, 0, len(failures))
+	for _, f := range failures {
+		out = append(out, Failure{Resource: f.Resource, Err: f.Err})
+	}
+	return out
+}
+
+// ModuleResults groups an apply's outcome per module the declaration names (novox/hq ADR 0429 §4, issue 1132): the
+// module's resources all applied, or it failed and Detail says which resource failed with its error, which resources
+// were skipped behind a step that did not complete, or that its resources were not attempted because a step of no
+// module stopped the apply. A module is named by what the declaration says of each resource (ModuleOfID), so one
+// whose id would guess another is still its own.
+//
+// A failure that is no resource's (an error that is not an Error, or a resource of no module) belongs to no module and
+// changes none: the node says it in its report. The report is the outcome of an apply that did not fail; an apply that
+// failed carries its own account in the Error, and that is read in its place.
+func ModuleResults(d *declaration.Declaration, report Report, err error) map[string]ModuleResult {
+	if d == nil {
+		return nil
+	}
+	out := map[string]ModuleResult{}
+	attempted := map[string]bool{}
+	var failed *Error
+	errors.As(err, &failed)
+	outcomes := report.Outcomes
+	if failed != nil {
+		outcomes = append(append([]Outcome(nil), outcomes...), failed.Done.Outcomes...)
+	}
+	skipped := map[string]string{}
+	for _, o := range outcomes {
+		module, ok := d.ModuleOfID(o.ID)
+		if !ok {
+			continue
+		}
+		if o.Action == "skipped" {
+			skipped[module] = o.Detail
+			continue
+		}
+		attempted[o.ID] = true
+	}
+	var reasons = map[string][]string{}
+	for _, r := range d.Resources {
+		if module, ok := d.ModuleOfID(r.Identity()); ok {
+			out[module] = ModuleResult{}
+			if failed != nil && failed.Stopped && !attempted[r.Identity()] {
+				reasons[module] = append(reasons[module], fmt.Sprintf("%s was not attempted: %s stopped the apply", r.Identity(), failed.Resource))
+			}
+		}
+	}
+	if failed != nil {
+		for _, f := range failed.Failures {
+			if module, ok := d.ModuleOfID(f.Resource); ok {
+				if _, named := out[module]; named {
+					reasons[module] = append(reasons[module], fmt.Sprintf("%s failed: %v", f.Resource, f.Err))
+				}
+			}
+		}
+		if len(failed.Failures) == 0 {
+			if module, ok := d.ModuleOfID(failed.Resource); ok {
+				if _, named := out[module]; named {
+					reasons[module] = append(reasons[module], fmt.Sprintf("%s failed: %v", failed.Resource, failed.Err))
+				}
+			}
+		}
+		for _, module := range failed.Modules {
+			if _, named := out[module]; named {
+				why := skipped[module]
+				if why == "" {
+					why = "a step it declares did not complete"
+				}
+				reasons[module] = append(reasons[module], "gated: "+why)
+			}
+		}
+	}
+	for module, why := range skipped {
+		if _, named := out[module]; named && len(reasons[module]) == 0 {
+			reasons[module] = append(reasons[module], "gated: "+why)
+		}
+	}
+	for module, why := range reasons {
+		sort.Strings(why)
+		out[module] = ModuleResult{Failed: true, Detail: strings.Join(why, "; ")}
+	}
+	return out
+}

internal/apply/module_results_test.go

@@ -0,0 +1,76 @@
+package apply
+
+import (
+	"errors"
+	"strings"
+	"testing"
+
+	"github.com/novox/mesh-host/internal/declaration"
+)
+
+func twoModules(t *testing.T) *declaration.Declaration {
+	t.Helper()
+	d, err := declaration.Parse([]byte(`{"declaration":1,"builds":{"a":"b-1","b":"b-2"},"resources":[
+		{"id":"a.dir","type":"directory","path":"/srv/a","module":"a"},
+		{"id":"b.dir","type":"directory","path":"/srv/b","module":"b"},
+		{"id":"b.conf","type":"file","path":"/srv/b/c","content":"x","module":"b"},
+		{"id":"c.dir","type":"directory","path":"/srv/c","module":"c"}]}`))
+	if err != nil {
+		t.Fatal(err)
+	}
+	return d
+}
+
+// 1132/AC3: every resource of module A applied and one of module B failed: A is a success, B failed with the failing
+// resource and its error named; a module gated by another's failure is failed too.
+func TestAnApplyIsGroupedPerModule(t *testing.T) {
+	d := twoModules(t)
+	done := Report{Outcomes: []Outcome{
+		{ID: "a.dir", Action: "created"},
+		{ID: "c.dir", Action: "skipped", Detail: "a step this module declares did not complete"},
+	}}
+	err := &Error{Resource: "b.dir", Err: errors.New("no space left"), Done: done, Others: 1,
+		Failures: []Failure{{Resource: "b.dir", Err: errors.New("no space left")}, {Resource: "b.conf", Err: errors.New("denied")}},
+		Modules:  []string{"c"}}
+	got := ModuleResults(d, Report{}, err)
+	if len(got) != 3 {
+		t.Fatalf("modules %v, want a, b and c", got)
+	}
+	if got["a"].Failed || got["a"].Detail != "" {
+		t.Errorf("a: %+v, want a clean success", got["a"])
+	}
+	b := got["b"]
+	if !b.Failed || !strings.Contains(b.Detail, "b.dir") || !strings.Contains(b.Detail, "no space left") ||
+		!strings.Contains(b.Detail, "b.conf") || !strings.Contains(b.Detail, "denied") {
+		t.Errorf("b: %+v, want both failing resources and their errors", b)
+	}
+	c := got["c"]
+	if !c.Failed || !strings.Contains(c.Detail, "did not complete") {
+		t.Errorf("c: %+v, want it failed as gated, with why", c)
+	}
+}
+
+// 1132/AC3: an apply that did not fail is a success for every module the declaration names.
+func TestACleanApplyIsASuccessForEveryModule(t *testing.T) {
+	got := ModuleResults(twoModules(t), Report{}, nil)
+	for _, m := range []string{"a", "b", "c"} {
+		if r, ok := got[m]; !ok || r.Failed {
+			t.Errorf("%s: %+v (%v), want a success", m, r, ok)
+		}
+	}
+}
+
+// 1132/AC3: a step that belongs to no module stops the apply there; a module with a resource not attempted is not a
+// success.
+func TestAModuleNotAttemptedIsNotASuccess(t *testing.T) {
+	d := twoModules(t)
+	err := &Error{Resource: "boot", Err: errors.New("boom"), Stopped: true, Failures: []Failure{{Resource: "boot", Err: errors.New("boom")}},
+		Done: Report{Outcomes: []Outcome{{ID: "a.dir", Action: "created"}}}}
+	got := ModuleResults(d, Report{}, err)
+	if got["a"].Failed {
+		t.Errorf("a was done: %+v", got["a"])
+	}
+	if !got["b"].Failed || !strings.Contains(got["b"].Detail, "boot") {
+		t.Errorf("b was not attempted: %+v", got["b"])
+	}
+}

internal/apply/move_out.go

@@ -350,7 +350,7 @@ func moveOutPass(d *declaration.Declaration, known store.State, applied map[stri
 		if unknown != declaration.UnknownMoveOut || !applied[r.Identity()] {
 			continue
 		}
-		module, _ := moduleOf(r.Identity())
+		module, _ := d.ModuleOfID(r.Identity())
 		if module == "" {
 			module = r.Identity()
 		}