From 0838d1d7355712c5c78e4d8186e2d3edc6b8f980 Mon Sep 17 00:00:00 2001
From: mrhid6 <mrhid6@gmail.com>
Date: Fri, 7 Aug 2026 08:45:00 +0100
Subject: [PATCH] feat: models and indexes for the workload registry

---
 server/cmd/main.go                          |  4 ++
 server/internal/models/workloads.go         | 70 +++++++++++++++++++++
 server/internal/services/workloadindexes.go | 34 ++++++++++
 3 files changed, 108 insertions(+)
 create mode 100644 server/internal/models/workloads.go
 create mode 100644 server/internal/services/workloadindexes.go

diff --git a/server/cmd/main.go b/server/cmd/main.go
index 92a174a..6c8a9b9 100644
--- a/server/cmd/main.go
+++ b/server/cmd/main.go
@@ -136,6 +136,10 @@ func runSchemaSetup() {
 		log.Printf("warning: failed to ensure vuln indexes: %v", err)
 	}
 
+	if err := services.EnsureWorkloadIndexes(); err != nil {
+		log.Printf("warning: failed to ensure workload indexes: %v", err)
+	}
+
 	if instanceIDs, err := services.ListInstanceIDs(); err != nil {
 		log.Printf("warning: failed to list instances for default step seeding: %v", err)
 	} else {
diff --git a/server/internal/models/workloads.go b/server/internal/models/workloads.go
new file mode 100644
index 0000000..60bbe4b
--- /dev/null
+++ b/server/internal/models/workloads.go
@@ -0,0 +1,70 @@
+package models
+
+import (
+	"time"
+
+	"go.mongodb.org/mongo-driver/v2/bson"
+)
+
+// Workload kinds.
+const (
+	WorkloadContainer = "container"
+	WorkloadUnit      = "unit"
+)
+
+// Control actions.
+const (
+	WorkloadStart   = "start"
+	WorkloadStop    = "stop"
+	WorkloadRestart = "restart"
+)
+
+// Workload is one container or one systemd unit.
+type Workload struct {
+	Kind string `bson:"kind" json:"kind"` // container | unit
+	ID   string `bson:"id" json:"id"`     // container id, or unit name
+	Name string `bson:"name" json:"name"`
+
+	// State is deliberately NOT collapsed into a shared vocabulary across the
+	// two kinds. Containers report running/exited/paused/restarting/created;
+	// units report active/inactive/failed/activating. A failed unit and an
+	// exited container mean different things, and flattening them loses the
+	// distinction the operator needs.
+	State  string `bson:"state" json:"state"`
+	Health string `bson:"health,omitempty" json:"health,omitempty"`
+
+	Image string   `bson:"image,omitempty" json:"image,omitempty"`
+	Stack string   `bson:"stack,omitempty" json:"stack,omitempty"` // compose project label
+	Ports []string `bson:"ports,omitempty" json:"ports,omitempty"`
+
+	Restarts  int       `bson:"restarts,omitempty" json:"restarts,omitempty"`
+	StartedAt time.Time `bson:"started_at,omitempty" json:"started_at,omitempty"`
+
+	// Protected is computed agent-side and reported so the UI can render the
+	// action disabled with a reason rather than offering a button whose refusal
+	// is already known. The field is the courtesy; the agent's own check is the
+	// boundary.
+	Protected bool `bson:"protected" json:"protected"`
+}
+
+// ServerWorkloads holds one server's whole workload list in ONE document.
+type ServerWorkloads struct {
+	ID          bson.ObjectID `bson:"_id,omitempty" json:"-"`
+	InstanceID  string        `bson:"instance_id" json:"-"`
+	ServerID    string        `bson:"server_id" json:"server_id"`
+	Hash        string        `bson:"hash" json:"hash"`
+	Workloads   []Workload    `bson:"workloads" json:"workloads"`
+	CollectedAt time.Time     `bson:"collected_at" json:"collected_at"`
+
+	// A host with no Docker and a host with Docker running nothing both produce
+	// an empty list. One should read "not in use here", the other "nothing
+	// running", and only the second deserves any alarm.
+	//
+	// The error strings separate a third case the booleans cannot: installed
+	// with the daemon down. "Not installed" and "installed but not responding"
+	// are different problems with different fixes.
+	DockerOK     bool   `bson:"docker_ok" json:"docker_ok"`
+	DockerError  string `bson:"docker_error,omitempty" json:"docker_error,omitempty"`
+	SystemdOK    bool   `bson:"systemd_ok" json:"systemd_ok"`
+	SystemdError string `bson:"systemd_error,omitempty" json:"systemd_error,omitempty"`
+}
diff --git a/server/internal/services/workloadindexes.go b/server/internal/services/workloadindexes.go
new file mode 100644
index 0000000..6a5872a
--- /dev/null
+++ b/server/internal/services/workloadindexes.go
@@ -0,0 +1,34 @@
+package services
+
+import (
+	"context"
+	"log"
+
+	"gitea.hostxtra.co.uk/mrhid6/vantage/server/internal/db"
+	"go.mongodb.org/mongo-driver/v2/bson"
+	"go.mongodb.org/mongo-driver/v2/mongo"
+	"go.mongodb.org/mongo-driver/v2/mongo/options"
+)
+
+// EnsureWorkloadIndexes declares the indexes for the workload registry.
+//
+// It warns rather than being fatal, matching EnsureSecretIndexes and
+// EnsureVulnIndexes: a missing index degrades these queries to a collection
+// scan, which is no reason to refuse to serve the fleet.
+func EnsureWorkloadIndexes() error {
+	ctx := context.Background()
+
+	idx := []mongo.IndexModel{
+		{
+			Keys:    bson.D{{Key: "instance_id", Value: 1}, {Key: "server_id", Value: 1}},
+			Options: options.Index().SetUnique(true),
+		},
+		// Multikey, for the fleet-wide "which servers run image X" query, which
+		// is the reason the snapshot is stored rather than fetched and discarded.
+		{Keys: bson.D{{Key: "instance_id", Value: 1}, {Key: "workloads.image", Value: 1}}},
+	}
+	if _, err := db.Col("server_workloads").Indexes().CreateMany(ctx, idx); err != nil {
+		log.Printf("warning: server_workloads indexes: %v", err)
+	}
+	return nil
+}