Add docker_volumes_remove_anonymous: remove leftover unmounted anonymous volumes (issue 1796)

modules/docker/README.md

@@ -160,6 +160,7 @@ A failure is an error naming how it failed, never an empty answer.
 | `docker_disk_usage` | r | `docker system df -v`: total, active and reclaimable per kind, with the largest of each |
 | `docker_networks` | r | networks, subnets, and the containers on each |
 | `docker_volumes` | r | volumes, who mounts each, whether the mesh holds one of them, anonymous or not, and sizes if asked |
+| `docker_volumes_remove_anonymous` | a | leftover anonymous volumes no container mounts in any state (so none the mesh holds), optionally created before a time; each other volume answered with why it stays; none can be named. **A dry run unless `dry_run` is false, which needs `why`. Never forced** (issue 1796) |
 | `docker_events` | r | the runtime's events over a window ending now (default 60 min, at most 24 h), without exec noise unless asked; **an exec's command line is shown with any secret it carried as `[redacted: <what it was>]`** |
 | `docker_daemon_config` | r | `daemon.json` as on disk, `docker info`'s essentials, and keys the daemon has not taken yet |
 | `docker_unlabelled` | r | the containers the mesh does not hold: the cleanup list |

modules/docker/cmd/docker-tools/docker.go

@@ -1215,3 +1215,67 @@ func (c *Client) DaemonConfig(ctx context.Context) (map[string]any, error) {
 	answer["note"] = "keys read only at start take effect at the daemon's next restart; with live-restore on, a restart keeps every container running"
 	return answer, nil
 }
+
+// RemoveVolumesAsk is what docker_volumes_remove_anonymous is asked to take.
+type RemoveVolumesAsk struct {
+	DryRun        bool
+	Why           string
+	CreatedBefore *time.Time
+}
+
+// RemoveAnonymousVolumes removes the leftover anonymous volumes (novox/hq issue 1796): those docker
+// labels anonymous, which no container mounts in any state, so none a mesh-held container holds. The
+// classification is Volumes' own, not a copy. Every other volume is answered with why it stays. Each
+// is removed by its own `docker volume rm`, never forced and never `volume prune`, so one the daemon
+// refuses is reported and the rest still go.
+func (c *Client) RemoveAnonymousVolumes(ctx context.Context, a RemoveVolumesAsk) (map[string]any, error) {
+	if !a.DryRun && strings.TrimSpace(a.Why) == "" {
+		return nil, fmt.Errorf("why is required when dry_run is false")
+	}
+	all, err := c.Volumes(ctx, false, false)
+	if err != nil {
+		return nil, err
+	}
+	candidates := []string{}
+	skipped := []map[string]any{}
+	skip := func(name, why string) { skipped = append(skipped, map[string]any{"name": name, "why": why}) }
+	for _, v := range all["volumes"].([]map[string]any) {
+		name := fmt.Sprint(v["name"])
+		switch by := v["mounted_by"].([]map[string]any); {
+		case v["anonymous"] != true:
+			skip(name, "not anonymous: a named volume is data")
+		case v["mesh_held"] == true:
+			skip(name, "mounted by a container the mesh holds")
+		case len(by) > 0:
+			skip(name, fmt.Sprintf("mounted by %v (%v)", by[0]["container"], by[0]["state"]))
+		case a.CreatedBefore != nil && !volumeOlder(fmt.Sprint(v["created"]), *a.CreatedBefore):
+			skip(name, "not created before "+a.CreatedBefore.Format(time.RFC3339)+" (created "+fmt.Sprint(v["created"])+")")
+		default:
+			candidates = append(candidates, name)
+		}
+	}
+	answer := map[string]any{"dry_run": a.DryRun, "skipped": skipped,
+		"space_freed": "not reported: docker volume rm names what it removed; docker_disk_usage shows the space"}
+	if a.DryRun {
+		answer["would_remove"] = candidates
+		answer["note"] = "nothing was removed: call again with dry_run false and why to remove them"
+		return answer, nil
+	}
+	removed := []string{}
+	for _, name := range candidates {
+		if _, err := c.docker(ctx, "volume", "rm", name); err != nil {
+			skip(name, "docker refused: "+err.Error())
+			continue
+		}
+		removed = append(removed, name)
+	}
+	answer["skipped"] = skipped
+	answer["removed"], answer["count"], answer["why"] = removed, len(removed), a.Why
+	return answer, nil
+}
+
+// volumeOlder is whether a volume's CreatedAt is before the cutoff; one that cannot be read is not.
+func volumeOlder(created string, cutoff time.Time) bool {
+	t, err := time.Parse(time.RFC3339Nano, created)
+	return err == nil && t.Before(cutoff)
+}

modules/docker/cmd/docker-tools/docker_test.go

@@ -431,3 +431,66 @@ func TestEventsCoveringTheWholeWindowSayItIsCompleteAndFilterTheTypeHere(t *test
 		t.Fatalf("a full buffer reaching past the window: %v", got)
 	}
 }
+
+// 1796/AC1: only anonymous volumes nothing mounts go, each answered; a named, a mounted and a too young one stay with why.
+func TestRemoveAnonymousVolumesTakesOnlyTheUnmountedAnonymousOnes(t *testing.T) {
+	f := machine().
+		on("docker volume ls --quiet", Ran{Stdout: "webdata\nanonmounted\nold\nyoung\nnamed\n"}).
+		on("docker volume inspect", Ran{Stdout: `[
+{"Name":"webdata","Driver":"local","CreatedAt":"2026-01-01T00:00:00Z","Labels":{"com.docker.volume.anonymous":""}},
+{"Name":"old","Driver":"local","CreatedAt":"2026-09-01T00:00:00Z","Labels":{"com.docker.volume.anonymous":""}},
+{"Name":"young","Driver":"local","CreatedAt":"2026-10-04T11:00:00Z","Labels":{"com.docker.volume.anonymous":""}},
+{"Name":"named","Driver":"local","CreatedAt":"2026-01-01T00:00:00Z"}]`}).
+		on("docker volume rm old", Ran{Stdout: "old\n"})
+	c := client(f, 1000)
+	before := time.Date(2026, 10, 3, 0, 0, 0, 0, time.UTC)
+	got, err := c.RemoveAnonymousVolumes(context.Background(), RemoveVolumesAsk{DryRun: true, CreatedBefore: &before})
+	if err != nil {
+		t.Fatal(err)
+	}
+	if f.ran("docker volume rm") || !reflect.DeepEqual(got["would_remove"], []string{"old"}) {
+		t.Fatalf("dry run: %v %+v", got, f.calls)
+	}
+	skipped := got["skipped"].([]map[string]any)
+	why := map[string]string{}
+	for _, s := range skipped {
+		why[s["name"].(string)] = s["why"].(string)
+	}
+	if len(why) != 3 || why["webdata"] == "" || why["young"] == "" || why["named"] == "" {
+		t.Fatalf("skipped: %v", skipped)
+	}
+	got, err = c.RemoveAnonymousVolumes(context.Background(), RemoveVolumesAsk{Why: "leftovers", CreatedBefore: &before})
+	if err != nil {
+		t.Fatal(err)
+	}
+	if !f.ran("docker volume rm old") || got["count"] != 1 || !reflect.DeepEqual(got["removed"], []string{"old"}) {
+		t.Fatalf("removed: %v %+v", got, f.calls)
+	}
+	for _, c := range f.calls {
+		if len(c.args) > 1 && c.args[0] == "volume" && c.args[1] == "rm" && (len(c.args) != 3 || c.args[2] != "old") {
+			t.Errorf("reached too far: %v", c.args)
+		}
+	}
+}
+
+// 1796/AC2: a volume that is mounted by a mesh-held container is never removed; the tool takes no name.
+func TestRemoveAnonymousVolumesRefusesANamedVolumeAndKeepsWhatTheMeshHolds(t *testing.T) {
+	for _, tool := range tools(client(&fake{}, 1000)) {
+		if tool.Name != "docker_volumes_remove_anonymous" {
+			continue
+		}
+		for _, k := range []string{"name", "names", "volume", "volumes"} {
+			if _, err := tool.Run(map[string]any{k: "x", "dry_run": false, "why": "w"}); err == nil {
+				t.Errorf("%s accepted", k)
+			}
+		}
+		if _, err := tool.Run(map[string]any{"dry_run": false}); err == nil {
+			t.Error("a removal without why was accepted")
+		}
+		if _, err := tool.Run(map[string]any{"created_before": "yesterday"}); err == nil {
+			t.Error("a bad time was accepted")
+		}
+		return
+	}
+	t.Fatal("tool not served")
+}

modules/docker/cmd/docker-tools/main.go

@@ -11,6 +11,7 @@ import (
 	"math"
 	"os"
 	"strings"
+	"time"
 
 	stdio "git.novox.be/novox/mesh-sdk/go"
 )
@@ -286,6 +287,34 @@ func tools(c *Client) []stdio.Tool {
 				return c.Volumes(ctx, flag(args, "unmounted", false), flag(args, "sizes", false))
 			},
 		},
+		{
+			Name: "docker_volumes_remove_anonymous",
+			Description: "Remove the leftover anonymous volumes (novox/hq issue 1796): only a volume docker labels anonymous (as docker_volumes says), which no container mounts in any state " +
+				"and so none the mesh holds, and with created_before only one created before it. Every other volume is answered with why it stays; a named volume is data and is never taken, " +
+				"and no volume can be named. Each is removed on its own, never forced; the answer has the count and names removed. Docker does not report the space a removed volume freed. " +
+				"A dry run by default; dry_run false needs why. Replaces docker volume rm and docker volume prune. (a)",
+			Input: map[string]any{
+				"dry_run":        map[string]any{"type": "boolean", "description": "list only (default true)"},
+				"why":            map[string]any{"type": "string", "description": "why: required when dry_run is false"},
+				"created_before": map[string]any{"type": "string", "description": "RFC 3339 time: only volumes created before it (default: any age)"},
+			},
+			Run: func(args map[string]any) (any, error) {
+				for _, k := range []string{"name", "names", "volume", "volumes"} {
+					if _, ok := args[k]; ok {
+						return nil, fmt.Errorf("%s: this tool takes no volume by name; it removes only unmounted anonymous volumes", k)
+					}
+				}
+				ask := RemoveVolumesAsk{DryRun: flag(args, "dry_run", true), Why: optional(args, "why")}
+				if s := optional(args, "created_before"); s != "" {
+					t, err := time.Parse(time.RFC3339, s)
+					if err != nil {
+						return nil, fmt.Errorf("created_before must be an RFC 3339 time such as 2026-10-01T00:00:00Z")
+					}
+					ask.CreatedBefore = &t
+				}
+				return c.RemoveAnonymousVolumes(ctx, ask)
+			},
+		},
 		{
 			Name: "docker_events",
 			Description: "What the runtime did in a window ending now (default the last 60 minutes, at most 24 hours): containers created, started, died, health changes, images pulled — with mesh_held. Exec events are left out unless asked; " +

modules/docker/module.json

@@ -33,6 +33,7 @@
     "docker_disk_usage",
     "docker_networks",
     "docker_volumes",
+    "docker_volumes_remove_anonymous",
     "docker_events",
     "docker_daemon_config",
     "docker_unlabelled",