Files
oikos/internal/httpapi/actuator.go
dtoro 7236c46e5c
Some checks failed
ci / build-test (push) Has been cancelled
ci / docker-build (push) Has been cancelled
ci / web (push) Has been cancelled
Desktop App / Build Linux (amd64) (push) Has been cancelled
Desktop App / Attach to Release (push) Has been cancelled
0.29.1 — review-fix round on E3: RunOutput, sshKeyPath fallback, RunStreaming consolidation, signer cache, stderr in errors
2026-08-08 23:01:10 +02:00

664 lines
27 KiB
Go

package httpapi
import (
"context"
"encoding/base64"
"encoding/json"
"fmt"
"log/slog"
"os"
"strconv"
"strings"
"time"
"github.com/dtoro/oikos/internal/actuator"
"github.com/dtoro/oikos/internal/db"
"github.com/dtoro/oikos/internal/db/sqlcgen"
"github.com/dtoro/oikos/internal/execlog"
"github.com/dtoro/oikos/internal/observability"
"github.com/google/uuid"
)
var (
_sshUser string
_sshKey []byte
)
// flexBool accepts a JSON bool, number (0/1), or string ("true"/"1"/"yes").
// LLMs routinely emit `"privileged": 0` instead of `false`; a strict `bool`
// field made the approved pct_create execution fail to parse *after* the
// operator had already approved it — the container was never created and the
// operator saw "queued" with no result. This type tolerates the common shapes.
type flexBool bool
func (b *flexBool) UnmarshalJSON(data []byte) error {
s := strings.TrimSpace(strings.Trim(string(data), `"`))
switch strings.ToLower(s) {
case "true", "1", "yes", "on":
*b = true
case "false", "0", "no", "off", "", "null":
*b = false
default:
return fmt.Errorf("cannot parse %q as bool", s)
}
return nil
}
func initSSH() {
if _sshUser == "" {
_sshUser = os.Getenv("OIKOS_SSH_USER")
if _sshUser == "" {
_sshUser = "root"
}
}
if len(_sshKey) == 0 {
keyPath := os.Getenv("OIKOS_SSH_KEY_PATH")
if keyPath == "" {
keyPath = "/etc/oikos/ssh_key"
}
var err error
_sshKey, err = os.ReadFile(keyPath)
if err != nil {
slog.Warn("httpapi ssh: cannot read key", "path", keyPath, "error", err)
}
}
}
// sshExecTimeout bounds how long a single remote command may run. Without
// this, a hung remote command (e.g. a piped install script stuck retrying
// DNS against a misconfigured gateway) blocks the executing goroutine
// forever: the execution never leaves 'approved'/'running', the operator
// sees an unkillable spinner, and get_execution_status has nothing new to
// report. Generous enough for a real apt/docker install; not infinite.
const sshExecTimeout = 10 * time.Minute
// streamWriter buffers everything it is given while forwarding each write to a
// sink. One on session.Stdout and another sharing the same buffer on
// session.Stderr reproduces CombinedOutput's interleaving in the order the
// remote end produced it. Shared implementation lives in internal/actuator
// (actuator.streamWriter / actuator.RunStreaming).
func sshExec(ctx context.Context, host, user, command string) (string, error) {
return sshExecStream(ctx, host, user, command, nil)
}
// sshExecStream runs a command and reports its combined output, forwarding
// each chunk to sink as it arrives. A nil sink behaves exactly as before.
func sshExecStream(ctx context.Context, host, user, command string, sink execlog.Sink) (string, error) {
initSSH()
if len(_sshKey) == 0 {
return "", fmt.Errorf("no SSH key available")
}
if user == "" {
user = _sshUser
}
signer, err := actuator.LoadSignerFromBytes(_sshKey)
if err != nil {
return "", fmt.Errorf("parse key: %w", err)
}
client, err := actuator.Dial(ctx, actuator.DialOptions{Host: host, User: user, Signer: signer})
if err != nil {
return "", err
}
defer client.Close()
return actuator.RunStreaming(ctx, client, command, sink, sshExecTimeout)
}
func resolveHostSSH(ctx context.Context, pool *db.Pool, entitySlug string) (string, string, error) {
var attrs string
err := pool.QueryRow(ctx, "SELECT attributes::text FROM entities WHERE slug = $1", entitySlug).Scan(&attrs)
if err != nil {
return "", "", fmt.Errorf("entity not found: %s", entitySlug)
}
var m map[string]interface{}
if err := json.Unmarshal([]byte(attrs), &m); err != nil {
return "", "", fmt.Errorf("parse attributes: %w", err)
}
sshUser := _sshUser
if sshUser == "" {
sshUser = "root"
}
if ip, ok := m["lan_ip"].(string); ok && ip != "" {
return ip, sshUser, nil
}
if mesh, ok := m["mesh"].(map[string]interface{}); ok {
for _, proto := range []string{"netbird", "tailscale"} {
if p, ok := mesh[proto].(map[string]interface{}); ok {
if ip, ok := p["ip"].(string); ok && ip != "" {
return ip, sshUser, nil
}
}
}
}
return "", "", fmt.Errorf("no IP found for %s", entitySlug)
}
// resolveRunTarget mirrors internal/mcp.resolveExecTarget for the approved-
// execution side: any target slug (host: or lxc:) resolves to the SSH
// endpoint that runs the command plus a wrap function that turns a plain
// shell command into what actually needs to be sent — identity for a host,
// `pct exec <pve_id>` for an LXC. Kept as a small duplicate rather than a
// cross-package import to avoid coupling httpapi to mcp for one helper.
func resolveRunTarget(ctx context.Context, pool *db.Pool, targetSlug string) (host, user string, wrap func(string) string, err error) {
if strings.HasPrefix(targetSlug, "host:") {
host, user, err = resolveHostSSH(ctx, pool, targetSlug)
return host, user, func(cmd string) string { return cmd }, err
}
if strings.HasPrefix(targetSlug, "lxc:") {
var pveID, hostAttr string
// COALESCE the host column: many older LXC entities (seeded from
// inventory, not provisioned by pct_create) have pve_id but no host
// attribute at all. Scanning a SQL NULL into a plain string errors
// the whole row, wrongly reporting "missing pve_id" even when it was
// present — COALESCE avoids the NULL, "" is handled below.
if qerr := pool.QueryRow(ctx, "SELECT attributes->>'pve_id', COALESCE(attributes->>'host', '') FROM entities WHERE slug = $1", targetSlug).Scan(&pveID, &hostAttr); qerr != nil || pveID == "" {
return "", "", nil, fmt.Errorf("LXC not found or missing pve_id: %s", targetSlug)
}
hostSlug := hostAttr
if hostSlug == "" {
hostSlug = "hubris"
}
if !strings.HasPrefix(hostSlug, "host:") {
hostSlug = "host:" + hostSlug
}
host, user, err = resolveHostSSH(ctx, pool, hostSlug)
id := pveID
return host, user, func(cmd string) string {
b64 := base64.StdEncoding.EncodeToString([]byte(cmd))
return fmt.Sprintf("pct exec %s -- bash -c 'echo %s | base64 -d | bash'", id, b64)
}, err
}
return "", "", nil, fmt.Errorf("unsupported target %q: must be host:<slug> or lxc:<slug>", targetSlug)
}
// executeApprovedAction runs a gated action after operator approval.
// Runs in a background goroutine to not block the HTTP response.
// emitExecutionEvent records an execution lifecycle event for SSE fan-out so
// the control room can watch approved actions run to completion live.
func emitExecutionEvent(ctx context.Context, pool *db.Pool, execID uuid.UUID, status string, detail map[string]any) {
severity := "info"
if status == "failed" {
severity = "warning"
}
// The correlation id was hardcoded to "", so execution events could not be
// tied back to the session that caused them — the one join you want when
// asking "what did this agent turn actually do?". It is already on the
// execution row; read it rather than threading it through eleven callers.
var correlationID string
if err := pool.QueryRow(ctx,
`SELECT correlation_id FROM executions WHERE entity_id = $1`, execID).Scan(&correlationID); err != nil {
correlationID = ""
}
_ = observability.Event(ctx, sqlcgen.New(pool), "execution."+status, &execID, severity, "actuator", correlationID, detail)
if status == "completed" || status == "failed" || status == "cancelled" {
closePlanStepForExecution(ctx, pool, execID, status)
}
}
// closePlanStepForExecution auto-closes a task plan step whose linked execution
// just reached a terminal state, so the task board advances even if the agent
// doesn't call update_plan_step itself (belt and suspenders — the agent links
// the step to the execution when it starts it; the api finishes it here). Emits
// plan.step.finished correlated to the step's session. No-op for the vast
// majority of executions, which aren't plan steps.
func closePlanStepForExecution(ctx context.Context, pool *db.Pool, execID uuid.UUID, execStatus string) {
stepStatus := "done"
if execStatus == "failed" || execStatus == "cancelled" {
stepStatus = "failed"
}
var stepID, sessionID string
var seq int
if err := pool.QueryRow(ctx, `
UPDATE session_plan_steps SET status = $2, finished_at = now()
WHERE execution_id = $1 AND status NOT IN ('done', 'failed', 'skipped')
RETURNING id::text, session_id::text, seq`, execID, stepStatus).Scan(&stepID, &sessionID, &seq); err != nil {
return // no matching open step
}
_ = observability.Event(ctx, sqlcgen.New(pool), "plan.step.finished", &execID, "info", "actuator", sessionID,
map[string]any{"step_id": stepID, "seq": seq, "status": stepStatus, "execution_id": execID.String()})
}
func executeApprovedAction(ctx context.Context, pool *db.Pool, execID uuid.UUID, targetSlug string, actionStr string) {
slog.Info("httpapi: executing approved action", "execution_id", execID, "target", targetSlug, "action", actionStr)
host, user, wrap, err := resolveRunTarget(ctx, pool, targetSlug)
if err != nil {
slog.Error("httpapi: resolve host for approved execution", "error", err, "target", targetSlug)
pool.Exec(ctx, `UPDATE executions SET status='failed', result=$2::jsonb WHERE entity_id=$1`,
execID, jsonErr("%s", err.Error()))
emitExecutionEvent(ctx, pool, execID, "failed", map[string]any{"target": targetSlug, "error": err.Error()})
return
}
idx := strings.Index(actionStr, ":")
if idx < 0 {
slog.Error("httpapi: malformed action string (no colon)", "action", actionStr)
return
}
action, params := actionStr[:idx], actionStr[idx+1:]
startedAt := time.Now()
// Persist started_at now, not at the end. It was captured here but only
// written in the terminal UPDATE, so a running execution reported
// started_at = NULL for its entire life — the UI could not show how long
// anything had been going, which is exactly when you want to know.
if _, err := pool.Exec(ctx,
`UPDATE executions SET status = 'running', started_at = $2 WHERE entity_id = $1`,
execID, startedAt); err != nil {
slog.Error("httpapi: mark execution running", "error", err, "execution_id", execID)
}
// Stream output for the actions whose output an operator actually watches:
// a long apt upgrade, a pct create, an arbitrary approved `run`. The small
// internal lookups further down (listing template cache, pvesh nextid) stay
// unstreamed — they are plumbing, and logging them would bury the command
// the operator approved.
var correlationID string
if qerr := pool.QueryRow(ctx,
`SELECT correlation_id FROM executions WHERE entity_id = $1`, execID).Scan(&correlationID); qerr != nil {
correlationID = ""
}
sink, flushLogs := execlog.New(ctx, pool, execID, correlationID)
defer flushLogs()
var output, cmd string
switch action {
case "systemctl":
svc := strings.TrimPrefix(targetSlug, "lxc:")
switch {
case strings.HasPrefix(params, "enable:"):
svc = strings.TrimPrefix(params, "enable:")
cmd = fmt.Sprintf("systemctl enable %s --now 2>&1; sleep 1; systemctl is-active %s", svc, svc)
case strings.HasPrefix(params, "disable:"):
svc = strings.TrimPrefix(params, "disable:")
cmd = fmt.Sprintf("systemctl disable %s --now 2>&1; sleep 1; systemctl is-active %s", svc, svc)
default:
cmd = fmt.Sprintf("systemctl %s %s 2>&1", params, svc)
}
output, err = sshExecStream(ctx, host, user, cmd, sink)
case "apt_upgrade":
svc := strings.TrimPrefix(targetSlug, "lxc:")
cmd = fmt.Sprintf("apt update -qq 2>&1 >/dev/null && apt upgrade -y -qq 2>&1; echo '---'; systemctl is-active %s || true", svc)
output, err = sshExecStream(ctx, host, user, cmd, sink)
case "pct_create":
var cfg struct {
VMID int `json:"vmid"`
Hostname string `json:"hostname"`
Cores int `json:"cores"`
Memory int `json:"memory"`
DiskGB int `json:"disk_gb"`
IP string `json:"ip"`
GW string `json:"gw"`
Bridge string `json:"bridge"` // e.g. vmbr0/vmbr1 — which bridge actually reaches the target subnet on this host varies per host, don't assume vmbr0
Storage string `json:"storage"`
Template string `json:"template"`
Privileged flexBool `json:"privileged"`
Nesting flexBool `json:"nesting"`
Mounts []string `json:"mounts"`
Nameserver string `json:"nameserver"`
Searchdomain string `json:"searchdomain"`
// No services/post_install here anymore — pct_create is atomic
// (create + start + register only). Installing packages and
// running setup scripts is the agent's job via follow-up `run`
// calls against lxc:<hostname>, so each step is individually
// observable and recoverable instead of one opaque multi-minute
// black box. See the comment above the removed post-create block.
}
if err := json.Unmarshal([]byte(params), &cfg); err != nil {
slog.Error("httpapi: pct_create parse params", "error", err, "params", params)
pool.Exec(ctx, `UPDATE executions SET status='failed', result=$2::jsonb WHERE entity_id=$1`,
execID, jsonErr("invalid pct_create params: %v", err))
emitExecutionEvent(ctx, pool, execID, "failed", map[string]any{"target": targetSlug, "error": err.Error()})
return
}
// Only hostname is required. vmid is optional — when 0 (or later found
// to collide) the VMID guard below assigns a free cluster id.
if cfg.Hostname == "" {
pool.Exec(ctx, `UPDATE executions SET status='failed', result=$2::jsonb WHERE entity_id=$1`,
execID, `{"error":"pct_create: hostname is required"}`)
emitExecutionEvent(ctx, pool, execID, "failed", map[string]any{"target": targetSlug, "error": "missing hostname"})
return
}
if cfg.Cores == 0 {
cfg.Cores = 1
}
if cfg.Memory == 0 {
cfg.Memory = 512
}
if cfg.DiskGB == 0 {
cfg.DiskGB = 8
}
if cfg.Storage == "" {
cfg.Storage = "local-lvm"
}
if cfg.GW == "" {
cfg.GW = "192.168.8.2"
}
if cfg.Nameserver == "" {
cfg.Nameserver = "192.168.8.2"
}
if cfg.Searchdomain == "" {
cfg.Searchdomain = "hubris.network"
}
// Template pre-flight: resolve against what the host actually has
// cached. A hardcoded name (e.g. debian-13) fails opaquely with a raw
// `pct` error when that exact file isn't present. List the cache, then
// either validate the requested template or auto-pick the newest
// debian one; on miss, fail early with the available list so the
// operator/agent can retry with a real name.
cacheList, tplErr := sshExec(ctx, host, user, "ls -1 /var/lib/vz/template/cache/ 2>/dev/null | grep -E '\\.tar\\.(zst|gz|xz)$' || true")
available := []string{}
for _, l := range strings.Split(strings.TrimSpace(cacheList), "\n") {
if l = strings.TrimSpace(l); l != "" {
available = append(available, l)
}
}
if tplErr != nil {
pool.Exec(ctx, `UPDATE executions SET status='failed', result=$2::jsonb WHERE entity_id=$1`,
execID, jsonErr("list templates on %s: %s", targetSlug, tplErr.Error()))
emitExecutionEvent(ctx, pool, execID, "failed", map[string]any{"target": targetSlug, "error": tplErr.Error()})
return
}
cfg.Template = resolveTemplate(cfg.Template, available)
if cfg.Template == "" {
msg := fmt.Sprintf("no usable LXC template on %s. Available: %v", targetSlug, available)
pool.Exec(ctx, `UPDATE executions SET status='failed', result=$2::jsonb WHERE entity_id=$1`,
execID, jsonErr("%s", msg))
emitExecutionEvent(ctx, pool, execID, "failed", map[string]any{"target": targetSlug, "error": msg})
return
}
// VMID collision guard. Proxmox VMIDs are cluster-wide, so the model's
// guess (e.g. 132) can collide with a container on another node — pct
// create then fails with "CT N already exists on node X". Fetch the set
// of in-use VMIDs across the cluster; if the requested id is taken (or
// absent), fall back to the cluster's next free id so provisioning
// still succeeds instead of dead-ending on the operator's approval.
usedRaw, _ := sshExec(ctx, host, user, `pvesh get /cluster/resources --type vm --output-format json 2>/dev/null | grep -o '"vmid":[0-9]*' | grep -o '[0-9]*' || true`)
used := map[int]bool{}
for _, l := range strings.Fields(usedRaw) {
if n, e := strconv.Atoi(strings.TrimSpace(l)); e == nil {
used[n] = true
}
}
if cfg.VMID == 0 || used[cfg.VMID] {
nextRaw, nerr := sshExec(ctx, host, user, `pvesh get /cluster/nextid 2>/dev/null`)
nextID, cerr := strconv.Atoi(strings.TrimSpace(nextRaw))
if nerr != nil || cerr != nil || nextID == 0 {
msg := fmt.Sprintf("VMID %d is already in use on the cluster and could not resolve a free id", cfg.VMID)
pool.Exec(ctx, `UPDATE executions SET status='failed', result=$2::jsonb WHERE entity_id=$1`,
execID, jsonErr("%s", msg))
emitExecutionEvent(ctx, pool, execID, "failed", map[string]any{"target": targetSlug, "error": msg})
return
}
slog.Info("httpapi: pct_create VMID reassigned", "requested", cfg.VMID, "assigned", nextID)
cfg.VMID = nextID
}
privFlag := "--unprivileged 1"
if cfg.Privileged {
privFlag = "--unprivileged 0"
}
nestingFlag := ""
features := []string{}
if cfg.Nesting {
features = append(features, "nesting=1")
}
if cfg.Privileged {
features = append(features, "keyctl=1")
}
if len(features) > 0 {
nestingFlag = fmt.Sprintf(" --features %s", strings.Join(features, ","))
}
if cfg.Bridge == "" {
cfg.Bridge = "vmbr0"
}
// net0: DHCP when no static IP is given (or ip=="dhcp"). Proxmox
// rejects a gateway alongside ip=dhcp, so only add gw for a static IP.
net0 := "name=eth0,bridge=" + cfg.Bridge + ","
isStatic := cfg.IP != "" && !strings.EqualFold(cfg.IP, "dhcp")
if !isStatic {
net0 += "ip=dhcp"
} else {
net0 += "ip=" + cfg.IP
if cfg.GW != "" {
net0 += ",gw=" + cfg.GW
}
}
// Pre-flight: for a static config, ping the gateway from the target
// HOST, on the SPECIFIC BRIDGE being requested, before spending 5+
// minutes creating the container. This is the check that would have
// caught the real TypeType failure immediately instead of after a
// full provision attempt.
//
// Binding to the bridge (`ping -I <bridge>`) matters and was found
// live: a plain unqualified `ping <gw>` from the host can succeed via
// the host's own routing table (multiple routes, possibly through an
// upstream router) even when the *container* — which only gets a
// naive on-link default route via its bridge's veth — can never ARP
// that gateway at all. Confirmed on `strong`: bare `ping 192.168.8.2`
// succeeded (via the host's default route), but a container actually
// attached to vmbr0 showed 100% packet loss trying to reach the same
// address, because vmbr0 doesn't carry that subnet's L2 segment.
// Binding to the bridge interface reproduces what the container will
// actually experience, not what the host's broader routing table can
// reach.
if isStatic && cfg.GW != "" {
pingOut, pingErr := sshExec(ctx, host, user, fmt.Sprintf("ping -I %s -c1 -W2 %s >/dev/null 2>&1 && echo PREFLIGHT_OK || echo PREFLIGHT_FAIL", cfg.Bridge, cfg.GW))
if pingErr != nil || !gatewayPreflightPassed(pingOut) {
msg := fmt.Sprintf(
"gateway %s is not reachable from %s on bridge %s — this almost always means the bridge doesn't carry that subnet on this host (each bridge only reaches the network it's physically wired to). "+
"Do not retry with a different gateway guess in the same subnet: find an existing LXC on this host with an IP in the same /28 and copy its exact bridge+gateway, or use DHCP instead.",
cfg.GW, targetSlug, cfg.Bridge)
pool.Exec(ctx, `UPDATE executions SET status='failed', result=$2::jsonb WHERE entity_id=$1`,
execID, jsonErr("%s", msg))
emitExecutionEvent(ctx, pool, execID, "failed", map[string]any{"target": targetSlug, "error": msg})
return
}
}
templatePath := fmt.Sprintf("/var/lib/vz/template/cache/%s", cfg.Template)
createCmd := fmt.Sprintf(
"pct create %d %s --hostname %s --cores %d --memory %d --rootfs %s:%d %s --net0 %s%s --start 1",
cfg.VMID, templatePath, cfg.Hostname, cfg.Cores, cfg.Memory,
cfg.Storage, cfg.DiskGB, privFlag, net0, nestingFlag)
if cfg.Nameserver != "" {
createCmd += fmt.Sprintf(" --nameserver %s", cfg.Nameserver)
}
if cfg.Searchdomain != "" {
createCmd += fmt.Sprintf(" --searchdomain %s", cfg.Searchdomain)
}
// Add mount points
for i, mp := range cfg.Mounts {
if i < 10 { // pct supports up to mp9
createCmd += fmt.Sprintf(" --mp%d %s", i, mp)
}
}
slog.Info("httpapi: pct_create running", "vmid", cfg.VMID, "hostname", cfg.Hostname, "cmd", createCmd)
output, err = sshExecStream(ctx, host, user, createCmd, sink)
// pct_create is now DELIBERATELY ATOMIC: create + start + register,
// nothing else. It used to also run apt installs and a post_install
// script inline as one black-box multi-minute SSH call — the agent
// got back a single opaque success/fail for the whole thing with no
// way to see (or fix) which step actually broke. That's the opposite
// of what makes an agent able to recover from errors.
//
// Installing packages, running post_install, and verifying the
// service now happen as the agent's OWN follow-up `run` calls against
// the new lxc:<hostname> target — each one is synchronous (in an
// active assent window) or individually gated, so the agent observes
// every step's real output and can diagnose + retry the exact thing
// that failed instead of re-doing the whole container. See SOUL.md
// "After pct_create: you drive the install" and provisionScript's
// surviving role (DNS self-heal) is now something the agent invokes
// itself via `run`, not something baked into this handler.
//
// cfg.Services/cfg.PostInstall are intentionally no longer read here.
// On success, register the entity in the DB with proper relationships
if err == nil {
slug := "lxc:" + cfg.Hostname
var lxcID uuid.UUID
lxcID, _ = uuid.NewV7()
attrs := map[string]any{
"pve_id": fmt.Sprintf("%d", cfg.VMID),
"host": strings.TrimPrefix(targetSlug, "host:"),
"ip": cfg.IP,
}
attrsJSON, _ := json.Marshal(attrs)
_, insErr := pool.Exec(ctx, `INSERT INTO entities (id, slug, type, name, state, attributes, enrolled_at)
VALUES ($1, $2, 'lxc', $3, 'provisioning', $4, now()) ON CONFLICT (slug) DO NOTHING`, lxcID, slug, cfg.Hostname, attrsJSON)
if insErr != nil {
slog.Error("httpapi: pct_create entity insert", "error", insErr, "slug", slug)
}
// Create hosts relationship: Proxmox host → LXC
var hostID uuid.UUID
if err := pool.QueryRow(ctx, "SELECT id FROM entities WHERE slug = $1", targetSlug).Scan(&hostID); err == nil {
_, relErr := pool.Exec(ctx, `INSERT INTO relationships (source_id, target_id, type, attributes, valid_from)
VALUES ($1, $2, 'hosts', '{"provisioned_by":"nomos"}'::jsonb, now())`, hostID, lxcID)
if relErr != nil {
slog.Error("httpapi: pct_create relationship insert", "error", relErr, "host", targetSlug, "lxc", slug)
}
}
// Create entity_status row for health tracking
pool.Exec(ctx, `INSERT INTO entity_status (entity_id, health, last_check_at)
VALUES ($1, 'unknown', now()) ON CONFLICT (entity_id) DO NOTHING`, lxcID)
emitExecutionEvent(ctx, pool, execID, "executing", map[string]any{
"lxc_slug": slug, "vmid": cfg.VMID, "host": targetSlug,
})
slog.Info("httpapi: pct_create entity registered", "slug", slug, "vmid", cfg.VMID, "host", targetSlug)
}
case "run":
// The general gated primitive: arbitrary shell against any host or
// LXC, approved and classified by internal/policy.ClassifyCommand at
// request time (see mcp/server.go's "run" tool). No fixed action
// enum — new capability doesn't require new Go code here.
var cfg struct {
Command string `json:"command"`
Purpose string `json:"purpose"`
}
if perr := json.Unmarshal([]byte(params), &cfg); perr != nil {
pool.Exec(ctx, `UPDATE executions SET status='failed', result=$2::jsonb WHERE entity_id=$1`,
execID, jsonErr("invalid run params: %v", perr))
emitExecutionEvent(ctx, pool, execID, "failed", map[string]any{"target": targetSlug, "error": perr.Error()})
return
}
cmd = wrap(cfg.Command)
output, err = sshExecStream(ctx, host, user, cmd, sink)
default:
slog.Error("httpapi: unknown gated action for approved execution", "action", action, "execution_id", execID)
pool.Exec(ctx, `UPDATE executions SET status='failed', result=$2::jsonb WHERE entity_id=$1`,
execID, jsonErr("unknown action: %s", action))
return
}
durationMs := int(time.Since(startedAt).Milliseconds())
status := "completed"
verified := true
// Build result via json.Marshal, not string interpolation. Command output
// (apt/pct) contains quotes, backslashes and control chars; the old
// fmt.Sprintf only escaped "\n", producing invalid JSON that failed the
// ::jsonb cast — so this UPDATE was silently discarded and the execution
// was stuck at "approved" forever even though provisioning succeeded.
resMap := map[string]any{"output": output}
if err != nil {
resMap["error"] = err.Error()
status = "failed"
verified = false
}
resultJSON, _ := json.Marshal(resMap)
if _, uerr := pool.Exec(ctx, `UPDATE executions SET status=$2, result=$3::jsonb, duration_ms=$4, verified=$5, started_at=$6, completed_at=$7 WHERE entity_id=$1`,
execID, status, resultJSON, durationMs, verified, startedAt, time.Now()); uerr != nil {
slog.Error("httpapi: finalize execution status", "error", uerr, "execution_id", execID, "intended_status", status)
}
emitExecutionEvent(ctx, pool, execID, status, map[string]any{
"action": action, "target": targetSlug, "duration_ms": durationMs,
})
slog.Info("httpapi: approved action executed",
"execution_id", execID, "action", action, "status", status, "duration_ms", durationMs)
}
// jsonErr builds a valid {"error": "..."} JSON payload for an execution's
// result column. Always use this instead of fmt.Sprintf'ing JSON by hand —
// error text and command output routinely contain quotes/backslashes that
// break a hand-built string and fail the ::jsonb cast.
func jsonErr(format string, args ...any) []byte {
b, _ := json.Marshal(map[string]any{"error": fmt.Sprintf(format, args...)})
return b
}
// resolveTemplate maps a requested template name to one actually present in
// the host's template cache. Exact match wins; a bare distro hint (e.g.
// "debian-13" or "debian") matches by prefix; empty picks the newest debian
// (falling back to any) template available. Returns "" when nothing fits.
// gatewayPreflightPassed interprets the PREFLIGHT_OK/PREFLIGHT_FAIL markers
// from the pct_create gateway pre-flight check. Pulled out as its own
// function (rather than an inline strings.Contains at the call site) so it's
// unit-testable: a prior version checked for "REACHABLE", which is a
// substring of "UNREACHABLE" — the check could never actually fail, and it
// took a live deployment to notice. Exact-match markers plus a test make
// that specific bug class structurally unable to recur silently.
func gatewayPreflightPassed(out string) bool {
return strings.TrimSpace(out) == "PREFLIGHT_OK"
}
func resolveTemplate(requested string, available []string) string {
if len(available) == 0 {
return ""
}
if requested != "" {
for _, a := range available {
if a == requested {
return a
}
}
for _, a := range available {
if strings.HasPrefix(a, requested) {
return a
}
}
}
// Auto-pick: prefer debian, then the lexically-greatest (newest version).
best := ""
for _, a := range available {
if strings.Contains(a, "debian") && a > best {
best = a
}
}
if best != "" {
return best
}
for _, a := range available {
if a > best {
best = a
}
}
return best
}