felhom-agent/internal/proxmox/query.go

package proxmox

import (
	"context"
	"fmt"
	"net/url"
	"strings"
)

// Read-only query operations. All API-backed (Datastore.Audit / VM.Audit /
// Sys.Audit). These are what `felhom-agent --selftest` exercises against a live
// host — they mutate nothing.

// Version returns GET /version.
func (c *Client) Version(ctx context.Context) (Version, error) {
	var v Version
	return v, c.get(ctx, "/version", &v)
}

// Nodes returns GET /nodes. Use this to confirm the node name and read each
// node's ssl_fingerprint (which is what to pin in TLSConfig).
func (c *Client) Nodes(ctx context.Context) ([]Node, error) {
	var ns []Node
	return ns, c.get(ctx, "/nodes", &ns)
}

// NodeStatus returns GET /nodes/{node}/status (host metrics; needs Sys.Audit).
func (c *Client) NodeStatus(ctx context.Context) (NodeStatus, error) {
	var s NodeStatus
	return s, c.get(ctx, "/nodes/"+c.node+"/status", &s)
}

// ListLXC returns GET /nodes/{node}/lxc (the guests on this node).
func (c *Client) ListLXC(ctx context.Context) ([]Guest, error) {
	var gs []Guest
	return gs, c.get(ctx, "/nodes/"+c.node+"/lxc", &gs)
}

// Pool returns GET /pools/{name} (the pool's membership — the stale-lock reaper's ownership
// registry, audit A1). Requires `Pool.Audit` at `/pool/{name}` — NOTE: `Pool.Allocate` does NOT
// satisfy the read (spike SPIKE-a1-pool-membership-read T2: the live 403 named Pool.Audit with
// Allocate already granted). Host-install v1.9.0+ grants it in the FelhomAgentGuest role.
func (c *Client) Pool(ctx context.Context, name string) (PoolInfo, error) {
	var p PoolInfo
	return p, c.get(ctx, "/pools/"+url.PathEscape(name), &p)
}

// GuestStatus returns GET /nodes/{node}/lxc/{vmid}/status/current. The API body
// has no vmid field (it is in the path), so it is set from the argument.
func (c *Client) GuestStatus(ctx context.Context, vmid int) (Guest, error) {
	var g Guest
	path := fmt.Sprintf("/nodes/%s/lxc/%d/status/current", c.node, vmid)
	if err := c.get(ctx, path, &g); err != nil {
		return Guest{}, err
	}
	g.VMID = vmid
	return g, nil
}

// GuestConfig returns GET /nodes/{node}/lxc/{vmid}/config.
func (c *Client) GuestConfig(ctx context.Context, vmid int) (GuestConfig, error) {
	var cfg GuestConfig
	path := fmt.Sprintf("/nodes/%s/lxc/%d/config", c.node, vmid)
	return cfg, c.get(ctx, path, &cfg)
}

// ExtractArchiveConfig returns GET /nodes/{node}/vzdump/extractconfig — the guest config embedded
// in a backup archive, as raw pct-conf text. Token-covered (verified live under the scoped agent
// token on PVE 9.2.2, GL-5); for a PBS archive the storage-configured encryption key stays
// SERVER-side — the agent never touches key material (the DR spike's candidate-1 rejection holds).
// The DR bring-up reads ONLY the rootfs size from it: PVE refuses a restore that carries mpN
// params without an explicit rootfs, and the lost guest has no live config to size it from.
func (c *Client) ExtractArchiveConfig(ctx context.Context, volume string) (string, error) {
	var out string
	path := "/nodes/" + c.node + "/vzdump/extractconfig?volume=" + url.QueryEscape(volume)
	return out, c.get(ctx, path, &out)
}

// ListSnapshots returns GET /nodes/{node}/lxc/{vmid}/snapshot (the guest's snapshots, including the
// synthetic "current"). The startup stale-lock recovery uses it to find a dangling "vzdump" snapshot
// left by an interrupted snapshot-mode backup.
func (c *Client) ListSnapshots(ctx context.Context, vmid int) ([]Snapshot, error) {
	var ss []Snapshot
	path := fmt.Sprintf("/nodes/%s/lxc/%d/snapshot", c.node, vmid)
	return ss, c.get(ctx, path, &ss)
}

// ListRunningTasks returns the node's currently-active tasks (GET /nodes/{node}/tasks?source=active).
// The startup stale-lock recovery uses it as the load-bearing safety guard: a backup lock is cleared
// ONLY when no vzdump task is genuinely in-flight for the guest (an agent restart while a real backup
// runs must never clear the live lock). NOTE: PVE 9.x rejects `?running=1` ("property not defined in
// schema") — `source=active` is the supported filter (it returns the RUNNING tasks); confirmed live on
// felhom-pve (PVE 9.2.2). active-source entries carry status "RUNNING"; we match on type+id, so the
// case difference vs the by-UPID status endpoint ("running") is moot.
func (c *Client) ListRunningTasks(ctx context.Context) ([]TaskStatus, error) {
	var ts []TaskStatus
	return ts, c.get(ctx, "/nodes/"+c.node+"/tasks?source=active", &ts)
}

// ListStorage returns GET /storage (cluster-wide storage definitions).
func (c *Client) ListStorage(ctx context.Context) ([]Storage, error) {
	var ss []Storage
	return ss, c.get(ctx, "/storage", &ss)
}

// NodeStorage returns GET /nodes/{node}/storage (storage with live usage).
func (c *Client) NodeStorage(ctx context.Context) ([]Storage, error) {
	var ss []Storage
	return ss, c.get(ctx, "/nodes/"+c.node+"/storage", &ss)
}

// StorageEntryConfig is the storage-entry CONFIG as served by GET /storage/{id} (PBS DR slice 2
// adoption probe — the pbs-type fields the bridge compares against the descriptor). All fields
// non-secret; the token secret lives in /etc/pve/priv/storage/<id>.pw, never in this response.
type StorageEntryConfig struct {
	Storage       string `json:"storage"`
	Type          string `json:"type"`
	Server        string `json:"server,omitempty"`
	Datastore     string `json:"datastore,omitempty"`
	Namespace     string `json:"namespace,omitempty"`
	Username      string `json:"username,omitempty"`
	Fingerprint   string `json:"fingerprint,omitempty"`
	EncryptionKey string `json:"encryption-key,omitempty"` // K's OWN fingerprint (not the key)
}

// StorageEntry returns GET /storage/{id} — the entry's configuration, or found=false when the id
// does not exist (PVE answers HTTP 500 "does not exist" — mapped here so the adoption probe can
// branch without string-matching upstream).
func (c *Client) StorageEntry(ctx context.Context, id string) (*StorageEntryConfig, bool, error) {
	var e StorageEntryConfig
	err := c.get(ctx, "/storage/"+url.PathEscape(id), &e)
	if err != nil {
		if strings.Contains(err.Error(), "does not exist") {
			return nil, false, nil
		}
		return nil, false, err
	}
	return &e, true, nil
}

// StorageActive returns whether GET /nodes/{node}/storage/{id}/status reports the entry active —
// for a pbs entry that means PVE connected to the PBS with the stored credentials (the
// post-apply/adoption health probe).
func (c *Client) StorageActive(ctx context.Context, id string) (bool, error) {
	var st struct {
		Active  int `json:"active"`
		Enabled int `json:"enabled"`
	}
	path := fmt.Sprintf("/nodes/%s/storage/%s/status", c.node, url.PathEscape(id))
	if err := c.get(ctx, path, &st); err != nil {
		return false, err
	}
	return st.Active == 1, nil
}

// StorageContent returns GET /nodes/{node}/storage/{store}/content (e.g. vzdump
// archives + CT templates available for a restore).
func (c *Client) StorageContent(ctx context.Context, store string) ([]StorageContent, error) {
	var cs []StorageContent
	path := fmt.Sprintf("/nodes/%s/storage/%s/content", c.node, url.PathEscape(store))
	return cs, c.get(ctx, path, &cs)
}

// LatestBackupVolID resolves the most recent vzdump archive for vmid on a backup storage.
// It lists the store's content, keeps only backup archives for that vmid, and returns the
// one with the greatest CTime. This is how a backup's produced archive is resolved after
// Vzdump+WaitTask (the task status carries no result volid), and how the restore-test picks
// a backup to restore. Returns ("", nil) when the guest has no archive on that store.
func (c *Client) LatestBackupVolID(ctx context.Context, store string, vmid int) (string, error) {
	contents, err := c.StorageContent(ctx, store)
	if err != nil {
		return "", err
	}
	var bestVol string
	var bestCTime int64 = -1
	for _, e := range contents {
		if e.Content != "backup" || e.VMID != vmid {
			continue
		}
		if e.CTime > bestCTime {
			bestCTime, bestVol = e.CTime, e.VolID
		}
	}
	return bestVol, nil
}

// urlEscape escapes a path segment (a UPID contains ':' and '@').
func urlEscape(s string) string { return url.PathEscape(s) }