admin/felhom.eu
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
61f4898d309cba2e24887282b6a6b9809c74e30a
felhom.eu/scripts/felhom-host-install.sh
T
admin ccb378060d feat(install): --enable-oob installs felhom-sshd + static belt (H1 Part 5) 
install_oob: /etc/felhom-sshd tree + dedicated host key + felhom-op user + scoped
sudoers + RuntimeDirectory-guarded felhom-sshd.service (enable-not-start; agent
renders config) + static felhom_oob nft table + boot loader. Uninstall removes all.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PSK5g6qYLknKj8u3QAFEr6
2026-07-05 22:34:06 +02:00

1824 lines
105 KiB
Bash
Raw Blame History

#!/bin/bash
#===============================================================================
# felhom-host-install.sh v1.9.1
# Day-0 host-bootstrap for a Felhom Proxmox host (operator-deploy model).
#
# Run by the operator on a FRESHLY-PVE-INSTALLED box (after a manual PVE install
# + SSH in). Given a customer-id + retrieval passphrase, it fully automates
# Day-0: Proxmox API token -> hub host enrollment -> AGENT INSTALL (fetch from
# Gitea + verify sha256 + install) -> agent config -> golden -> guest provision
# -> verify. It composes already-proven mechanisms (the pveum role/token
# sequence, hub POST /host-enroll [option C], felhom-agent --selftest=provision).
# The agent renders bootstrap.json and the controller pulls its own
# controller.yaml in-guest; this script does NOT fetch that.
#
# v1.1.0 (BUNDLE slice): the agent binary + golden are now fetched from Gitea
# generic packages and VERIFIED against the hub-vouched artifact manifest
# (GET /api/v1/artifacts/{id}) before install/use. The fetch credential is the
# git token already inside the customer's controller.yaml (config-retrieve) — NO
# new credential. The checksum trust root is the HUB, not Gitea. This removes the
# old prerequisite "install the agent binary + unit manually".
#
# Grounding: documentation/audits/SPIKE-day0-firstboot-handshake-2026-06-26.md
#
# Usage:
# sudo ./felhom-host-install.sh --customer-id ID [options]
#
# Required:
# --customer-id ID Customer (must already exist in the hub)
#
# Options:
# --mode provision|dr provision (Day-0, default) | dr (10D stub — not impl.)
# --hub-url URL default https://hub.felhom.eu
# --vmid N guest VMID to provision. Default 9201; if omitted and 9201 is already
# in use, the script auto-picks the next free id (pct+qm) and asks to
# confirm. An EXPLICIT --vmid stays deterministic (dies unless --force).
# --golden VOLID golden archive volid (default: newest vzdump of the
# golden build VMID on the archive storage; else fetched
# from Gitea per the hub artifact manifest)
# --golden-vmid N golden build guest vmid for auto-discovery (default 9100)
# --archive-storage NAME storage holding the golden vzdump (default local)
# --force-gitea-golden ignore any local golden; fetch+verify the golden from
# Gitea (proves the fetch path; used by the live test)
# --node NAME PVE node name (default: pvesh /nodes, else hostname)
# --bridge-ip IP[:PORT] local-api listen addr (default: vmbr0 IP : 8443)
# --rootfs-grow N grow OS rootfs by N GiB (default: auto-compute)
# --datavol-grow N grow Docker-data vol by N GiB (default: auto-compute)
# --sysdata-grow N grow user-data vol by N GiB (default: auto-compute)
#
# Appliance cap (optional — protect a SHARED host's other guests; needs agent >= v0.52.0):
# --cores N cap the guest to N CPU cores (0/unset = golden default)
# --memory M cap the guest RAM to M MiB (0/unset = golden default)
#
# --passphrase-file PATH read the retrieval passphrase from a 0600 file
# (default: secure no-echo prompt)
# --preserve-from PATH merge non-Day-0 sections (privileged/storage/backup/
# local_api/authz/lan_resolver) from an existing config
# --preserve-state-from PATH carry the prior agent leaf+key+token-store (local-api.crt/key,
# local-tokens.log) over so the pinned fingerprint STAYS STABLE across a
# reinstall (no controller re-bootstrap). Use an aside copy of the old
# /var/lib/felhom-agent.
# --allow-new-leaf opt in to REGENERATE the agent leaf on a host that already has guests
# (the populated-host guard otherwise refuses; every guest must then be
# re-bootstrapped — only use intentionally).
# --force allow provisioning over an EXISTING vmid (destructive)
# --skip-provision install + configure + verify the agent, but do NOT
# provision a guest (re-install/upgrade an agent on a host
# that already has live guests; also the agent-only path)
# --dry-run print every mutating command without executing
# --resume skip steps already recorded in the state file
# -h, --help this help
#
# Uninstall (local host teardown — no hub contact, no passphrase):
# --uninstall cleanly revert an install: destroy the Felhom guest, remove the agent
# (unit/sudoers/binary/state/config/user + runtime artifacts: shared-parent
# unit, mkfs wrapper, hook snippet, dnsmasq snippets), the pveum
# role/user/token/ACL, and the install state file. Refuses a non-Felhom guest (no
# /etc/felhom-bootstrap mount) and skips host-level removal if OTHER Felhom
# guests remain (both overridable with --force). Typed vmid confirmation
# required. Reuses --vmid (else the recorded provisioned_vmid), --force,
# --archive-storage, --golden-vmid, --dry-run.
# --remove-golden with --uninstall, also delete the golden vzdump from the archive storage
#
# Retrofit (local, non-destructive — no hub contact, no passphrase):
# --adopt-pool add an EXISTING Felhom guest to the `felhom` pool (creates the pool if
# needed). Resolves the guest from --vmid else the recorded provisioned_vmid;
# refuses a non-Felhom guest unless --force. Touches ONLY pool membership —
# never reconfigures/restarts the guest. (A fresh provision joins the pool
# automatically; this retrofits already-installed boxes.)
# --rescope-acl migrate an existing install from the pre-3b broad-`/` token grant to the
# pool-scoped ACL (Guest@/pool/felhom + Store@each storage + Sys.Audit/SDN.Use@/).
# ACL-only (no data touched). SUPERVISED: run with felhom-agent STOPPED, then
# deploy agent >= v0.53.0, then start (the scoped ACL + pool-param agent are
# mutually dependent).
# --acl-storages "a b c" override the storages the scoped ACL grants Datastore.* on
# (default: "local local-lvm felhom-pbs"). Used by fresh install + --rescope-acl.
#
# State (idempotent/resumable): /var/lib/felhom-install/state.json
# Agent config written 0600 to the systemd unit's -config path
# (auto-detected; else /etc/felhom-agent/agent.json).
#
# SECURITY: the passphrase is read no-echo or from a 0600 file — never a CLI arg,
# never echoed, never written to the state file or logs. The minted pve-token
# secret + per-host hub api_key live ONLY in the agent config (0600, root).
#===============================================================================
set -euo pipefail
SCRIPT_VERSION="1.9.1" # keep in sync with the header line at the top of this file
#-------------------------------------------------------------------------------
# Logging (mirrors felhom-controller/scripts/docker-setup.sh)
#-------------------------------------------------------------------------------
RED='\033[0;31m'; GREEN='\033[0;32m'; YELLOW='\033[1;33m'
BLUE='\033[0;34m'; CYAN='\033[0;36m'; NC='\033[0m'
log_info() { echo -e "${GREEN}[INFO]${NC} $1"; }
log_warn() { echo -e "${YELLOW}[WARN]${NC} $1"; }
log_error() { echo -e "${RED}[ERROR]${NC} $1" >&2; }
log_step() { echo -e "${BLUE}[STEP]${NC} $1"; }
log_success() { echo -e "${GREEN}[OK]${NC} $1"; }
log_skip() { echo -e "${CYAN}[SKIP]${NC} $1"; }
log_dry() { echo -e "${CYAN}[DRY-RUN]${NC} $1"; }
die() { log_error "$1"; exit 1; }
#-------------------------------------------------------------------------------
# Defaults
#-------------------------------------------------------------------------------
CUSTOMER_ID=""
MODE="provision"
HUB_URL="https://hub.felhom.eu"
VMID="9201"
VMID_EXPLICIT=false # set true when --vmid is given; gates the auto-pick-a-free-vmid behavior
GOLDEN_VOLID=""
GOLDEN_VMID="9100"
ARCHIVE_STORAGE="local"
NODE=""
NODE_EXPLICIT=false # set true when --node is given; gates the multi-node wrong-node guard
BRIDGE_ADDR=""
ROOTFS_GROW=""
DATAVOL_GROW=""
SYSDATA_GROW=""
CPU_CORES="" # --cores: optional appliance CPU-core cap (empty/unset = golden default)
MEM_MIB="" # --memory: optional appliance RAM cap in MiB (empty/unset = golden default)
PASSPHRASE_FILE=""
PRESERVE_FROM=""
PRESERVE_STATE_FROM="" # dir holding a prior local-api.{crt,key} + local-tokens.log to carry over (keeps the pin stable across a reinstall)
ALLOW_NEW_LEAF=false # opt-in to intentionally regenerate the agent leaf on a populated host (else the guard refuses)
FORCE=false
FORCE_GITEA_GOLDEN=false
SKIP_PROVISION=false
DRY_RUN=false
RESUME=false
UNINSTALL=false # --uninstall: local host teardown (destroy guest + remove agent/pveum/state)
REMOVE_GOLDEN=false # --remove-golden: also delete the golden vzdump during --uninstall
ADOPT_POOL=false # --adopt-pool: retrofit an EXISTING Felhom guest into the felhom pool (non-destructive)
RESCOPE_ACL=false # --rescope-acl: migrate an existing install from the broad-/ token to the scoped ACL
ROTATE_RECOVERY=false # --rotate-recovery: regenerate + re-vault the break-glass root@pam password (TASK G1)
ENABLE_OOB=false # --enable-oob: install the dedicated felhom-sshd OOB instance + belt (TASK H1)
# --- Gitea (artifact source) + agent install model (BUNDLE slice) ---
GITEA_BASE="https://gitea.dooplex.hu"
GITEA_OWNER="admin"
AGENT_REPO="felhom-agent" # for the raw unit/sudoers fetch (config text, canonical source)
AGENT_USER="felhom-agent" # the non-root service user the unit + sudoers name
AGENT_BIN="/usr/local/bin/felhom-agent"
AGENT_SUDOERS="/etc/sudoers.d/felhom-agent"
AGENT_UNIT="/etc/systemd/system/felhom-agent.service"
AGENT_STATE_DIR="/var/lib/felhom-agent"
PVE_USER="felhom-agent@pve"
PVE_TOKENID="agent"
PVE_POOL="felhom" # dedicated pool every Felhom-managed guest joins (fleet uniformity + ACL scope)
PVE_ROLE="FelhomAgent" # the PRE-3b single broad role (removed on rescope/uninstall if present — legacy)
# Pool-scoped ACL (3b, validated by SPIKE-pool-scoped-acl-2026-07-01): the agent's privileges are split
# across THREE roles applied at scoped paths so the token can only touch Felhom's own guests + storages
# (blast-radius containment). `pveum acl` grants a whole role per path, hence 3 roles not 1. Each role is
# granted to BOTH the user AND the token (privsep intersection). Guest privs (incl. Pool.Allocate so the
# agent restores INTO the pool) live at /pool/felhom; Datastore WRITE privs at each agent-touched storage.
# `Datastore.Audit` is box-wide in Base (3b-fix v1.7.0): the agent must ENUMERATE every storage incl. the
# dynamically-enrolled removable drives (felhom-usb/felhom-flash) it observes but never registers — a
# per-storage Audit grant hid them → false "drive detached" alerts. Audit is read-only, so box-wide Audit
# keeps WRITE containment (Allocate/AllocateSpace stay per-storage). Only Sys.Audit/SDN.Use/Datastore.Audit box-wide.
# `Pool.Audit` (v1.9.0, audit A1): the agent's stale-lock reaper reads GET /pools/felhom as its
# ownership registry (agent v0.62.0+); without it the reaper fail-safes (skips) and reports the
# `pve:pool-read` capability degraded. NOTE: Pool.Allocate does NOT satisfy the read — the spike
# (SPIKE-a1-pool-membership-read-2026-07-03 T2) 403'd with Allocate granted; Audit is required.
PVE_ROLE_GUEST="FelhomAgentGuest"
PVE_ROLE_STORE="FelhomAgentStore"
PVE_ROLE_BASE="FelhomAgentBase"
PVE_PRIVS_GUEST="VM.Allocate VM.Audit VM.Config.Disk VM.Config.CPU VM.Config.Memory VM.Config.Network VM.Config.Options VM.PowerMgmt VM.Snapshot VM.Snapshot.Rollback VM.Backup Pool.Allocate Pool.Audit"
PVE_PRIVS_STORE="Datastore.Allocate Datastore.AllocateSpace"
PVE_PRIVS_BASE="Sys.Audit SDN.Use Datastore.Audit"
# Storages the agent reads/writes (archive+dump=local, restore=local-lvm, offsite DR=felhom-pbs). The
# offsite felhom-pbs MUST be included or the agent's DR backup 403s (SPIKE residual #1). --acl-storages overrides.
PVE_STORAGES=(local local-lvm felhom-pbs)
STATE_DIR="/var/lib/felhom-install"
STATE_FILE="${STATE_DIR}/state.json"
AGENT_CONFIG="" # resolved in preflight
HARD_MIN_LVM_GIB=120 # a useful appliance won't fit below this on local-lvm
# Runtime carriers (never logged)
PASSPHRASE=""
PVE_TOKEN="" # felhom-agent@pve!agent=<secret>
HOST_ID=""
HOST_API_KEY=""
GIT_USER="" # from controller.yaml (config-retrieve) — Gitea fetch credential
GIT_TOKEN="" # from controller.yaml — NEVER logged
ART_AGENT_VER="" # hub artifact manifest: agent version + sha256
ART_AGENT_SHA=""
ART_GOLDEN_VER="" # hub artifact manifest: golden version + sha256
ART_GOLDEN_SHA=""
#-------------------------------------------------------------------------------
# Helpers
#-------------------------------------------------------------------------------
usage() { sed -n '2,95p' "$0" | sed 's/^# \{0,1\}//'; exit 0; }
run() { # simple (no pipes/redirects) mutating command
if $DRY_RUN; then log_dry "$*"; else "$@"; fi
}
# used_vmids — every in-use guest id on this host. LXC (pct) and VMs (qm) SHARE the id space,
# so both are consulted; headers (non-numeric first column) are filtered out.
used_vmids() {
{ pct list 2>/dev/null; qm list 2>/dev/null; } | awk '{print $1}' | grep -E '^[0-9]+$'
}
# _vmid_in_use ID — true if ID is present in the pct+qm used-set (more complete than `pct status`,
# which only knows LXC).
_vmid_in_use() {
local target="$1" used
used=" $(used_vmids | tr '\n' ' ') "
[[ "$used" == *" $target "* ]]
}
# next_free_vmid BASE — the first id >= BASE not in the used-set, scanning upward.
next_free_vmid() {
local base="$1" used id
used=" $(used_vmids | tr '\n' ' ') "
id="$base"
while [[ "$used" == *" $id "* ]]; do id=$((id + 1)); done
echo "$id"
}
# State helpers (robust JSON via python3).
_state_has() {
[[ -f "$STATE_FILE" ]] || return 1
STATE_FILE="$STATE_FILE" python3 -c "import json,os,sys;f=os.environ['STATE_FILE'];d=json.load(open(f));sys.exit(0 if sys.argv[1] in d.get('completed',[]) else 1)" "$1" 2>/dev/null
}
_state_mark() {
$DRY_RUN && return 0
mkdir -p "$STATE_DIR"
STATE_FILE="$STATE_FILE" python3 -c "import json,os,sys;f=os.environ['STATE_FILE'];d=json.load(open(f)) if os.path.exists(f) else {'completed':[]};c=d.setdefault('completed',[]);(c.append(sys.argv[1]) if sys.argv[1] not in c else None);json.dump(d,open(f,'w'),indent=2)" "$1"
}
should_skip() { # returns 0 (skip) if --resume AND step already done
if $RESUME && _state_has "$1"; then log_skip "step '$1' already completed"; return 0; fi
return 1
}
# _state_put KEY VALUE — set a top-level string key in state.json (creates the file if absent).
# Mirrors _state_mark: dry-run no-ops (writes nothing), robust JSON via python3.
_state_put() {
$DRY_RUN && return 0
mkdir -p "$STATE_DIR"
STATE_FILE="$STATE_FILE" python3 -c "import json,os,sys;f=os.environ['STATE_FILE'];d=json.load(open(f)) if os.path.exists(f) else {'completed':[]};d[sys.argv[1]]=sys.argv[2];json.dump(d,open(f,'w'),indent=2)" "$1" "$2"
}
# _state_get KEY — print the top-level string value for KEY (empty if the file/key is absent).
_state_get() {
[[ -f "$STATE_FILE" ]] || return 0
STATE_FILE="$STATE_FILE" python3 -c "import json,os,sys;d=json.load(open(os.environ['STATE_FILE']));print(d.get(sys.argv[1],''))" "$1" 2>/dev/null
}
http_code() { # GET, prints status code only (read-only preflight)
curl -fsS -o /dev/null -w '%{http_code}' "$@" 2>/dev/null || curl -sS -o /dev/null -w '%{http_code}' "$@" 2>/dev/null
}
#-------------------------------------------------------------------------------
# Artifact + Gitea helpers (BUNDLE slice)
#-------------------------------------------------------------------------------
# Resolve the hub-vouched artifact manifest (agent + golden version+sha256). Passphrase-authed,
# same trust root as config-retrieve. Sets ART_* globals. Empty fields are valid (caller falls back).
resolve_artifacts() {
local resp code body
resp=$(curl -sS -w $'\n%{http_code}' "$HUB_URL/api/v1/artifacts/$CUSTOMER_ID" \
-H "X-Retrieval-Password: $PASSPHRASE")
code=$(tail -n1 <<<"$resp"); body=$(sed '$d' <<<"$resp")
[[ "$code" == "200" ]] || die "artifact manifest fetch failed: HTTP $code"
ART_AGENT_VER=$(python3 -c "import json,sys;print(json.loads(sys.argv[1])['agent']['version'])" "$body" 2>/dev/null || echo "")
ART_AGENT_SHA=$(python3 -c "import json,sys;print(json.loads(sys.argv[1])['agent']['sha256'])" "$body" 2>/dev/null || echo "")
ART_GOLDEN_VER=$(python3 -c "import json,sys;print(json.loads(sys.argv[1])['golden']['version'])" "$body" 2>/dev/null || echo "")
ART_GOLDEN_SHA=$(python3 -c "import json,sys;print(json.loads(sys.argv[1])['golden']['sha256'])" "$body" 2>/dev/null || echo "")
}
# Resolve the Gitea fetch credential (git username + token) from the customer's controller.yaml —
# the SAME secret config-retrieve already hands out (NO new credential). Sets GIT_USER / GIT_TOKEN.
# Parses the git: block without a YAML lib (fresh PVE has no PyYAML).
resolve_git_creds() {
local yaml
yaml=$(curl -fsS "$HUB_URL/api/v1/config/$CUSTOMER_ID" -H "X-Retrieval-Password: $PASSPHRASE") \
|| die "controller.yaml fetch failed (for the git fetch token)"
GIT_USER=$(awk '/^[^[:space:]#]/{ingit=($1=="git:")} ingit&&$1=="username:"{print $2}' <<<"$yaml" | head -1)
GIT_TOKEN=$(awk '/^[^[:space:]#]/{ingit=($1=="git:")} ingit&&$1=="token:"{print $2}' <<<"$yaml" | head -1)
# strip any surrounding quotes
GIT_USER="${GIT_USER%\"}"; GIT_USER="${GIT_USER#\"}"
GIT_TOKEN="${GIT_TOKEN%\"}"; GIT_TOKEN="${GIT_TOKEN#\"}"
[[ -n "$GIT_TOKEN" ]] || die "no git token in controller.yaml — cannot fetch artifacts from Gitea"
}
# Fetch a Gitea generic-package URL to a dest with the git token, then VERIFY its sha256 against the
# expected (hub-vouched) value. Aborts on any mismatch — verify-before-use. $1=url $2=dest $3=expected_sha
fetch_verify() {
local url="$1" dest="$2" want="$3"
[[ -n "$want" ]] || die "refusing to install an artifact with no expected sha256 (manifest incomplete): $url"
curl -fsS -u "${GIT_USER}:${GIT_TOKEN}" -o "$dest" "$url" || die "fetch failed: $url"
local got; got=$(sha256sum "$dest" | awk '{print $1}')
if [[ "$got" != "$want" ]]; then
rm -f "$dest"
die "sha256 MISMATCH for $url — expected $want got $got. Refusing to install (verify-before-use)."
fi
log_success " verified sha256 ${got:0:16}… matches the hub manifest"
}
# Fetch a raw config file (the canonical unit/sudoers) from the agent repo with the git token. These
# are non-executable text (not the integrity-checked binary); the sudoers is `visudo -cf`-validated
# before install, which catches corruption/tampering that would matter. $1=repo-path $2=dest
fetch_raw() {
local path="$1" dest="$2"
curl -fsS -u "${GIT_USER}:${GIT_TOKEN}" -o "$dest" \
"$GITEA_BASE/$GITEA_OWNER/$AGENT_REPO/raw/branch/main/$path" \
|| die "raw fetch failed: $path"
[[ -s "$dest" ]] || die "raw fetch empty: $path"
}
#-------------------------------------------------------------------------------
# Uninstall (local host teardown) — reverse of install; no hub contact, no passphrase
#-------------------------------------------------------------------------------
# felhom_guests — every vmid on this host that carries the /etc/felhom-bootstrap bind mount (the
# read-only bootstrap mount an agent-provisioned guest always has). Matched by the CONSTANT guest
# PATH, not a hardcoded mpN slot (the slot drifts; on the demo host it's mp9).
felhom_guests() {
local id
for id in $(used_vmids); do
pct config "$id" 2>/dev/null | grep -q 'mp=/etc/felhom-bootstrap' && echo "$id"
done
}
#-------------------------------------------------------------------------------
# felhom pool (fleet uniformity) — every managed guest joins the `felhom` pool. All pool ops run as
# root@pam from the installer, so NO agent/token/ACL change is involved (that is the separate 3b spike).
# API shapes confirmed on PVE 9: `pvesh get /pools` → [{poolid,comment}]; `pvesh get /pools/<id>` →
# {poolid,comment,members:[{vmid,...}]}. Pool ops: `pveum pool add|delete <id>`, `pveum pool modify
# <id> --vms <ids>` (additive).
#-------------------------------------------------------------------------------
# pool_exists — true if the felhom pool is present.
pool_exists() {
pvesh get /pools --output-format json 2>/dev/null \
| python3 -c "import json,sys;sys.exit(0 if any(p.get('poolid')=='$PVE_POOL' for p in json.load(sys.stdin)) else 1)" 2>/dev/null
}
# pool_members — space-separated vmids currently in the felhom pool (empty if none / pool absent).
pool_members() {
pvesh get "/pools/$PVE_POOL" --output-format json 2>/dev/null \
| python3 -c "import json,sys
try: d=json.load(sys.stdin)
except Exception: sys.exit(0)
print(' '.join(str(m.get('vmid')) for m in d.get('members',[]) if m.get('vmid') is not None))" 2>/dev/null
}
# ensure_felhom_pool — create the pool if absent (idempotent no-op otherwise). Via run() (dry-run-aware).
ensure_felhom_pool() {
if pool_exists; then
log_skip " pool $PVE_POOL already exists"
else
run pveum pool add "$PVE_POOL" --comment "Felhom-managed guests"
fi
}
# pool_add_guest VMID — add a guest to the felhom pool unless it is already a member (idempotent).
pool_add_guest() {
local vmid="$1" members
members=" $(pool_members) "
if [[ "$members" == *" $vmid "* ]]; then
log_skip " guest $vmid already in pool $PVE_POOL"
else
run pveum pool modify "$PVE_POOL" -vms "$vmid"
log_success " guest $vmid added to pool $PVE_POOL"
fi
}
#-------------------------------------------------------------------------------
# Pool-scoped ACL helpers (3b). All ops run as root@pam (installer) — no privilege change to the agent.
#-------------------------------------------------------------------------------
# _role_exists NAME — true if a pveum role NAME exists.
_role_exists() {
pveum role list --output-format json 2>/dev/null \
| python3 -c "import json,sys;sys.exit(0 if any(r['roleid']==sys.argv[1] for r in json.load(sys.stdin)) else 1)" "$1" 2>/dev/null
}
# _ensure_role NAME "PRIVS" — create the role, or modify it to the exact priv set (idempotent).
_ensure_role() {
local name="$1" privs="$2"
if _role_exists "$name"; then
log_info " role $name exists — ensuring exact privileges"
run pveum role modify "$name" -privs "$privs"
else
run pveum role add "$name" -privs "$privs"
fi
}
# _grant PATH ROLE — grant ROLE at PATH to BOTH the user AND the token (privsep intersection). `acl
# modify` is idempotent so this is safe to repeat / re-apply after a token rotation.
_grant() {
local path="$1" role="$2"
run pveum acl modify "$path" -user "$PVE_USER" -role "$role"
run pveum acl modify "$path" -token "${PVE_USER}!${PVE_TOKENID}" -role "$role"
}
# apply_scoped_acl — create the 3 scoped roles and grant each at its path(s). Requires the pool to exist.
# ORDER (3b-fix): Base (which holds box-wide Datastore.Audit) is ensured + granted BEFORE Store, so a
# RE-APPLY on a live box adds Audit@/ before Store drops its per-storage Audit → the agent never loses
# storage-enumeration visibility mid-apply (gap-free).
apply_scoped_acl() {
_ensure_role "$PVE_ROLE_BASE" "$PVE_PRIVS_BASE"
_ensure_role "$PVE_ROLE_GUEST" "$PVE_PRIVS_GUEST"
_ensure_role "$PVE_ROLE_STORE" "$PVE_PRIVS_STORE"
_grant / "$PVE_ROLE_BASE"
_grant "/pool/$PVE_POOL" "$PVE_ROLE_GUEST"
local s
for s in "${PVE_STORAGES[@]}"; do
_grant "/storage/$s" "$PVE_ROLE_STORE"
done
log_success " scoped ACL applied (Base@/, Guest@/pool/$PVE_POOL, Store@[${PVE_STORAGES[*]}])"
}
# _acl_grant_present PATH TYPE UGID ROLE — true if that exact ACL grant exists.
_acl_grant_present() {
pveum acl list --output-format json 2>/dev/null | python3 -c "import json,sys
p,t,u,r=sys.argv[1:5]
sys.exit(0 if any(e.get('path')==p and e.get('type')==t and e.get('ugid')==u and e.get('roleid')==r for e in json.load(sys.stdin)) else 1)" "$1" "$2" "$3" "$4" 2>/dev/null
}
# remove_scoped_acl — delete the 3-role scoped grants (user+token at each path), then the 3 roles
# (roles last — PVE refuses to delete a referenced role). Presence-checked, tolerate-absent.
remove_scoped_acl() {
local s
if _acl_grant_present "/pool/$PVE_POOL" user "$PVE_USER" "$PVE_ROLE_GUEST"; then run pveum acl delete "/pool/$PVE_POOL" --users "$PVE_USER" --roles "$PVE_ROLE_GUEST"; fi
if _acl_grant_present "/pool/$PVE_POOL" token "${PVE_USER}!${PVE_TOKENID}" "$PVE_ROLE_GUEST"; then run pveum acl delete "/pool/$PVE_POOL" --tokens "${PVE_USER}!${PVE_TOKENID}" --roles "$PVE_ROLE_GUEST"; fi
for s in "${PVE_STORAGES[@]}"; do
if _acl_grant_present "/storage/$s" user "$PVE_USER" "$PVE_ROLE_STORE"; then run pveum acl delete "/storage/$s" --users "$PVE_USER" --roles "$PVE_ROLE_STORE"; fi
if _acl_grant_present "/storage/$s" token "${PVE_USER}!${PVE_TOKENID}" "$PVE_ROLE_STORE"; then run pveum acl delete "/storage/$s" --tokens "${PVE_USER}!${PVE_TOKENID}" --roles "$PVE_ROLE_STORE"; fi
done
if _acl_grant_present / user "$PVE_USER" "$PVE_ROLE_BASE"; then run pveum acl delete / --users "$PVE_USER" --roles "$PVE_ROLE_BASE"; fi
if _acl_grant_present / token "${PVE_USER}!${PVE_TOKENID}" "$PVE_ROLE_BASE"; then run pveum acl delete / --tokens "${PVE_USER}!${PVE_TOKENID}" --roles "$PVE_ROLE_BASE"; fi
local name
for name in "$PVE_ROLE_GUEST" "$PVE_ROLE_STORE" "$PVE_ROLE_BASE"; do
if _role_exists "$name"; then run pveum role delete "$name"; else log_skip " role $name already absent"; fi
done
}
# remove_old_broad_acl — remove the PRE-3b single FelhomAgent role granted at / (user+token) + the role.
# Tolerate-absent (fresh 3b installs have none). Used by --rescope-acl (migration) and step_token (so a
# re-install can't leave the old broad grant unioned with the new scoped one).
remove_old_broad_acl() {
if _acl_grant_present / user "$PVE_USER" "$PVE_ROLE"; then run pveum acl delete / --users "$PVE_USER" --roles "$PVE_ROLE"; fi
if _acl_grant_present / token "${PVE_USER}!${PVE_TOKENID}" "$PVE_ROLE"; then run pveum acl delete / --tokens "${PVE_USER}!${PVE_TOKENID}" --roles "$PVE_ROLE"; fi
if _role_exists "$PVE_ROLE"; then run pveum role delete "$PVE_ROLE"; else log_skip " old broad role $PVE_ROLE already absent"; fi
}
# run_uninstall — the full guarded teardown. Every mutation goes through run() so --dry-run prints it
# and executes nothing. Ordering is the reverse of install: guest -> agent -> pveum(ACL,token,user,
# role) -> golden(opt-in) -> state file. See the TASK spec §7/§8.
run_uninstall() {
log_step "UNINSTALL — local host teardown"
# 1. Resolve the target vmid: --vmid, else the recorded provisioned_vmid, else die.
local state_vmid vmid pool_removed=false
state_vmid=$(_state_get provisioned_vmid)
if $VMID_EXPLICIT; then
vmid="$VMID"
elif [[ -n "$state_vmid" ]]; then
vmid="$state_vmid"
log_info " no --vmid given; using recorded provisioned_vmid=$vmid from $STATE_FILE"
else
die "pass --vmid N (state has no recorded vmid)"
fi
# state-mismatch: an explicit --vmid that disagrees with the recorded one needs --force.
if $VMID_EXPLICIT && [[ -n "$state_vmid" && "$state_vmid" != "$vmid" ]]; then
if $FORCE; then
log_warn " --vmid $vmid differs from the recorded provisioned_vmid=$state_vmid — --force given, proceeding"
else
die "--vmid $vmid differs from the recorded provisioned_vmid=$state_vmid. Pass --force to override."
fi
fi
# 2. Guest teardown (guarded: ours-check + typed confirm).
if _vmid_in_use "$vmid"; then
# ours-check: a Felhom guest carries the /etc/felhom-bootstrap bind mount (constant guest path).
if pct config "$vmid" 2>/dev/null | grep -q 'mp=/etc/felhom-bootstrap'; then
log_info " vmid $vmid looks like a Felhom guest (has the /etc/felhom-bootstrap mount)"
elif $FORCE; then
log_warn " vmid $vmid has NO /etc/felhom-bootstrap mount — --force given, destroying anyway"
else
die "vmid $vmid does not look like a Felhom-provisioned guest (no /etc/felhom-bootstrap mount).
Refusing to destroy. Pass --force to override."
fi
# show the config so the operator can eyeball what is about to be destroyed
log_info " pct config $vmid:"
pct config "$vmid" 2>/dev/null | sed 's/^/ /'
# typed confirmation — mandatory, never skipped except in --dry-run (nothing is destroyed there).
if $DRY_RUN; then
log_dry "would prompt: Type the vmid ($vmid) to confirm PERMANENT destruction"
else
local ans
read -rp "Type the vmid ($vmid) to confirm PERMANENT destruction: " ans < /dev/tty
[[ "$ans" == "$vmid" ]] || die "confirmation mismatch (got '$ans', expected '$vmid') — aborting, nothing destroyed"
fi
# stop (tolerate already-stopped) then destroy
local gstat; gstat=$(pct status "$vmid" 2>/dev/null | awk '{print $2}')
if [[ "$gstat" == "running" ]]; then
run pct stop "$vmid"
else
log_skip " guest $vmid not running (status: ${gstat:-unknown}) — skip stop"
fi
run pct destroy "$vmid"
log_success " guest $vmid destroyed"
else
log_skip " guest $vmid already absent — skipping guest teardown"
# host-level removal is still ours-gated: allowed if state's provisioned_vmid matches; else --force.
if [[ -n "$state_vmid" && "$state_vmid" == "$vmid" ]]; then
log_info " recorded provisioned_vmid matches $vmid — host-level removal permitted"
elif ! $FORCE; then
die "guest $vmid is absent and is not the recorded provisioned_vmid ('${state_vmid:-none}') — refusing host-level removal without --force."
fi
fi
# 3. Other-Felhom-guests detector — the safe default. If any OTHER Felhom guest remains and no
# --force, stop after the guest teardown and leave every host-level component in place.
local others others_csv
others=$(felhom_guests | grep -vx "$vmid" || true)
if [[ -n "$others" ]] && ! $FORCE; then
others_csv=$(echo "$others" | tr '\n' ' ' | sed 's/ */ /g;s/^ //;s/ $//;s/ /, /g')
echo ""
log_warn "Other Felhom guests remain (${others_csv}); leaving the agent + PVE token + state in place."
log_warn "Re-run --uninstall --force to remove host-level components anyway (this orphans ${others_csv})."
log_success "UNINSTALL (guest-only) complete — removed guest $vmid; host-level components preserved."
log_info " NOTE: the host record still exists in the hub — remove it there if desired."
$DRY_RUN && log_warn " DRY-RUN: nothing above was actually executed."
return 0
fi
# ── host-level removal (reverse of install) ──────────────────────────────────────────────────
log_step "host-level removal"
# 4. Agent removal — service, unit(+.bak), sudoers, binary(+.bak), state dir, config, user.
# NEVER `sudo`. Resolve the agent config path BEFORE the unit is removed (mirrors preflight —
# the unit's -config arg is the truth, else the default); the config holds the per-host hub
# api_key and must not survive an uninstall (drill finding R1).
local agent_cfg=""
if systemctl cat felhom-agent >/dev/null 2>&1; then
agent_cfg=$(systemctl cat felhom-agent 2>/dev/null | grep -oP '(?<=-config )\S+' | head -1)
fi
[[ -n "$agent_cfg" ]] || agent_cfg="/etc/felhom-agent/agent.json"
if systemctl list-unit-files felhom-agent.service >/dev/null 2>&1; then
systemctl is-active --quiet felhom-agent 2>/dev/null && run systemctl stop felhom-agent
systemctl is-enabled --quiet felhom-agent 2>/dev/null && run systemctl disable felhom-agent
else
log_skip " felhom-agent unit not loaded — skip stop/disable"
fi
if [[ -f "$AGENT_UNIT" ]]; then run rm -f "$AGENT_UNIT"; else log_skip " $AGENT_UNIT already absent"; fi
local bak
for bak in "${AGENT_UNIT}".bak-*; do [[ -e "$bak" ]] && run rm -f "$bak"; done
run systemctl daemon-reload
if [[ -f "$AGENT_SUDOERS" ]]; then run rm -f "$AGENT_SUDOERS"; else log_skip " $AGENT_SUDOERS already absent"; fi
if [[ -f "$AGENT_BIN" ]]; then run rm -f "$AGENT_BIN"; else log_skip " $AGENT_BIN already absent"; fi
for bak in "${AGENT_BIN}".bak-*; do [[ -e "$bak" ]] && run rm -f "$bak"; done
if [[ -d "$AGENT_STATE_DIR" ]]; then run rm -rf "$AGENT_STATE_DIR"; else log_skip " $AGENT_STATE_DIR already absent"; fi
if id "$AGENT_USER" >/dev/null 2>&1; then run userdel "$AGENT_USER"; else log_skip " service user $AGENT_USER already absent"; fi
# 4b. Agent config (pve token + per-host hub api_key — secrets must not survive; drill R1).
if [[ -f "$agent_cfg" ]]; then run rm -f "$agent_cfg"; else log_skip " $agent_cfg already absent"; fi
run rmdir "$(dirname "$agent_cfg")" 2>/dev/null || true
# 4b2. Management-plane break-glass (TASK G1): timer+oneshot+script+tmpfiles. Stop/disable the
# timer, remove all four artifacts + the runtime heal-marker. We do NOT `rmdir /run/sshd` —
# the stock sshd needs it; leaving the (now unit-less) dir in place is correct (a bare kernel
# /run tmpfs recreates it empty on next boot anyway). Tolerate-absent throughout.
if systemctl list-unit-files felhom-mgmt-watchdog.timer >/dev/null 2>&1; then
systemctl is-active --quiet felhom-mgmt-watchdog.timer 2>/dev/null && run systemctl stop felhom-mgmt-watchdog.timer
systemctl is-enabled --quiet felhom-mgmt-watchdog.timer 2>/dev/null && run systemctl disable felhom-mgmt-watchdog.timer
else
log_skip " felhom-mgmt-watchdog.timer not loaded — skip stop/disable"
fi
run systemctl reset-failed felhom-mgmt-watchdog.service 2>/dev/null || true
local wda
for wda in /etc/systemd/system/felhom-mgmt-watchdog.service /etc/systemd/system/felhom-mgmt-watchdog.timer \
/usr/local/sbin/felhom-mgmt-watchdog /etc/tmpfiles.d/felhom-privsep.conf /run/felhom-mgmt-watchdog.healed; do
if [[ -e "$wda" ]]; then run rm -f "$wda"; fi
done
# 4b3. OOB felhom-sshd instance + belt (TASK H1). Stop/disable felhom-sshd + the belt loader,
# remove units + config tree + belt table + felhom-op user/sudoers. NEVER touch the stock
# sshd/:22/etc/ssh. Tolerate-absent throughout.
if systemctl list-unit-files felhom-sshd.service >/dev/null 2>&1; then
systemctl is-active --quiet felhom-sshd 2>/dev/null && run systemctl stop felhom-sshd
systemctl is-enabled --quiet felhom-sshd 2>/dev/null && run systemctl disable felhom-sshd
fi
if systemctl list-unit-files felhom-oob-nft.service >/dev/null 2>&1; then
systemctl is-active --quiet felhom-oob-nft 2>/dev/null && run systemctl stop felhom-oob-nft
systemctl is-enabled --quiet felhom-oob-nft 2>/dev/null && run systemctl disable felhom-oob-nft
fi
run systemctl reset-failed felhom-sshd felhom-oob-nft 2>/dev/null || true
nft list table inet felhom_oob >/dev/null 2>&1 && run nft delete table inet felhom_oob
local oa
for oa in /etc/systemd/system/felhom-sshd.service /etc/systemd/system/felhom-oob-nft.service \
/etc/felhom-oob.nft /etc/sudoers.d/felhom-op /run/felhom-sshd.pid /run/felhom-sshd.healed; do
if [[ -e "$oa" ]]; then run rm -f "$oa"; fi
done
if [[ -d /etc/felhom-sshd ]]; then run rm -rf /etc/felhom-sshd; fi
if id felhom-op >/dev/null 2>&1; then run userdel -r felhom-op 2>/dev/null || run userdel felhom-op; fi
# 4c. Shared-parent unit + wrapper + /mnt/felhom-drives (agent-installed at runtime; drill R2).
# Stop/disable, remove unit + script, unbind + remove the (empty) parent dir. Tolerate-absent.
if systemctl list-unit-files felhom-shared-parent.service 2>/dev/null | grep -q felhom-shared-parent; then
systemctl is-active --quiet felhom-shared-parent 2>/dev/null && run systemctl stop felhom-shared-parent
systemctl is-enabled --quiet felhom-shared-parent 2>/dev/null && run systemctl disable felhom-shared-parent
else
log_skip " felhom-shared-parent unit not loaded — skip stop/disable"
fi
if [[ -f /etc/systemd/system/felhom-shared-parent.service ]]; then run rm -f /etc/systemd/system/felhom-shared-parent.service; else log_skip " felhom-shared-parent.service already absent"; fi
if [[ -f /usr/local/sbin/felhom-shared-parent.sh ]]; then run rm -f /usr/local/sbin/felhom-shared-parent.sh; fi
run systemctl daemon-reload
if mountpoint -q /mnt/felhom-drives 2>/dev/null; then run umount /mnt/felhom-drives; fi
if [[ -d /mnt/felhom-drives ]]; then run rmdir /mnt/felhom-drives 2>/dev/null || true; fi
# 4d. Guarded-mkfs wrapper, guest-hook snippet, lan-resolver dnsmasq snippets (drill R3-R5).
if [[ -f /usr/local/sbin/felhom-mkfs-guarded ]]; then run rm -f /usr/local/sbin/felhom-mkfs-guarded; else log_skip " felhom-mkfs-guarded already absent"; fi
if [[ -f /var/lib/vz/snippets/felhom-guest-hook.sh ]]; then run rm -f /var/lib/vz/snippets/felhom-guest-hook.sh; fi
local dconf _dnsmasq_touched=false
for dconf in /etc/dnsmasq.d/felhom-*.conf; do
[[ -e "$dconf" ]] || continue
run rm -f "$dconf"; _dnsmasq_touched=true
done
if $_dnsmasq_touched && systemctl is-active --quiet dnsmasq 2>/dev/null; then
run systemctl restart dnsmasq || true
fi
# 5. pveum removal (presence-checked; tolerate-absent; roles deleted only after their grants).
# Remove the 3-role scoped grants+roles (3b) AND the pre-3b single-role broad grant if present —
# both tolerate-absent so --uninstall works on a box of either shape.
remove_scoped_acl
remove_old_broad_acl
# token then user (token-remove purges its ACL; user-delete purges anything else).
if pveum user token list "$PVE_USER" --output-format json 2>/dev/null | python3 -c "import json,sys;sys.exit(0 if any(t['tokenid']=='$PVE_TOKENID' for t in json.load(sys.stdin)) else 1)" 2>/dev/null; then
run pveum user token remove "$PVE_USER" "$PVE_TOKENID"
else
log_skip " token ${PVE_USER}!${PVE_TOKENID} already absent"
fi
if pveum user list --output-format json 2>/dev/null | python3 -c "import json,sys;sys.exit(0 if any(u['userid']=='$PVE_USER' for u in json.load(sys.stdin)) else 1)" 2>/dev/null; then
run pveum user delete "$PVE_USER"
else
log_skip " user $PVE_USER already absent"
fi
# 5b. felhom pool — delete ONLY if empty (a destroyed guest is auto-removed from its pool). Never
# delete a pool that still holds members (someone else's guests, or another Felhom guest kept
# under --force).
if pool_exists; then
local pool_left; pool_left=$(pool_members)
if [[ -z "$pool_left" ]]; then
run pveum pool delete "$PVE_POOL"
pool_removed=true
else
log_skip " pool $PVE_POOL not empty (members: $pool_left) — leaving it"
fi
else
log_skip " pool $PVE_POOL already absent"
fi
# 6. Golden vzdump (opt-in via --remove-golden; else left in place).
if $REMOVE_GOLDEN; then
local gvols gv
gvols=$(pvesm list "$ARCHIVE_STORAGE" --content backup 2>/dev/null | awk -v v="$GOLDEN_VMID" '$0 ~ ("vzdump-lxc-" v "-"){print $1}')
if [[ -n "$gvols" ]]; then
while IFS= read -r gv; do
[[ -n "$gv" ]] || continue
run pvesm free "$gv"
done <<<"$gvols"
log_success " removed golden vzdump(s) from $ARCHIVE_STORAGE"
else
log_skip " no golden vzdump (vzdump-lxc-${GOLDEN_VMID}-*) on $ARCHIVE_STORAGE"
fi
else
log_skip " golden vzdump left in place (pass --remove-golden to remove)"
fi
# 7. Install state file (only reached when host-level removal ran — safe-skip returned earlier).
if [[ -f "$STATE_FILE" ]]; then run rm -f "$STATE_FILE"; else log_skip " $STATE_FILE already absent"; fi
run rmdir "$STATE_DIR" 2>/dev/null || true
# 8. Summary.
echo ""
log_success "UNINSTALL complete — removed: guest $vmid, the felhom-agent (unit/sudoers/binary/state/config/user + shared-parent/mkfs-wrapper/hook-snippet/dnsmasq-snippets), the pveum role/user/token/ACL,$( $pool_removed && printf ' the %s pool,' "$PVE_POOL") and $STATE_FILE."
if $REMOVE_GOLDEN; then log_info " golden vzdump: removed."; else log_info " golden vzdump: left in place (--remove-golden to remove)."; fi
log_info " NOTE: the 'sudo' and 'dnsmasq' packages were left installed (system packages); the host record still exists in the hub — remove it there if desired."
$DRY_RUN && log_warn " DRY-RUN: nothing above was actually executed."
return 0
}
# run_adopt_pool — retrofit an EXISTING Felhom guest into the felhom pool. Non-destructive: creates the
# pool if absent + adds the guest; never reconfigures/restarts the guest, never contacts the hub. Guest
# resolves from --vmid else the recorded provisioned_vmid (mirrors run_uninstall).
run_adopt_pool() {
log_step "ADOPT-POOL — add an existing Felhom guest to the $PVE_POOL pool"
local state_vmid vmid
state_vmid=$(_state_get provisioned_vmid)
if $VMID_EXPLICIT; then
vmid="$VMID"
elif [[ -n "$state_vmid" ]]; then
vmid="$state_vmid"
log_info " no --vmid given; using recorded provisioned_vmid=$vmid from $STATE_FILE"
else
die "pass --vmid N (state has no recorded vmid)"
fi
_vmid_in_use "$vmid" || die "guest $vmid not found on this host (nothing to adopt)"
# ours-check: only adopt a Felhom guest (has the /etc/felhom-bootstrap mount) unless --force.
if pct config "$vmid" 2>/dev/null | grep -q 'mp=/etc/felhom-bootstrap'; then
log_info " vmid $vmid looks like a Felhom guest (has the /etc/felhom-bootstrap mount)"
elif $FORCE; then
log_warn " vmid $vmid has NO /etc/felhom-bootstrap mount — --force given, adopting anyway"
else
die "vmid $vmid does not look like a Felhom-provisioned guest (no /etc/felhom-bootstrap mount).
Refusing to adopt. Pass --force to override."
fi
ensure_felhom_pool
pool_add_guest "$vmid"
echo ""
log_success "ADOPT-POOL complete — guest $vmid is in pool $PVE_POOL (guest not otherwise modified)."
$DRY_RUN && log_warn " DRY-RUN: nothing above was actually executed."
return 0
}
# run_rescope_acl — migrate an EXISTING install from the pre-3b broad-/ token to the pool-scoped ACL.
# Non-destructive to data (ACL-only): ensure the pool + the guest is a member, apply the 3-role scoped
# grants, THEN remove the old broad grant. Idempotent + dry-run-aware. Does NOT touch the guest or hub.
# ORDERING (see §13): run this with the agent STOPPED, then deploy agent >= v0.53.0, then start — the
# scoped ACL and the pool-param agent are mutually dependent.
run_rescope_acl() {
log_step "RESCOPE-ACL — migrate to the pool-scoped token ACL"
local state_vmid vmid
state_vmid=$(_state_get provisioned_vmid)
if $VMID_EXPLICIT; then
vmid="$VMID"
elif [[ -n "$state_vmid" ]]; then
vmid="$state_vmid"
log_info " no --vmid given; using recorded provisioned_vmid=$vmid from $STATE_FILE"
else
die "pass --vmid N (state has no recorded vmid)"
fi
_vmid_in_use "$vmid" || die "guest $vmid not found on this host"
if pct config "$vmid" 2>/dev/null | grep -q 'mp=/etc/felhom-bootstrap'; then
log_info " vmid $vmid looks like a Felhom guest (has the /etc/felhom-bootstrap mount)"
elif $FORCE; then
log_warn " vmid $vmid has NO /etc/felhom-bootstrap mount — --force given, rescoping anyway"
else
die "vmid $vmid does not look like a Felhom-provisioned guest (no /etc/felhom-bootstrap mount).
Refusing to rescope. Pass --force to override."
fi
# The guest MUST be a pool member before the scoped token can touch it — ensure it first.
ensure_felhom_pool
pool_add_guest "$vmid"
# Apply the scoped grants, THEN remove the old broad grant (add-before-remove: never leave the token
# with NO grant mid-migration).
apply_scoped_acl
remove_old_broad_acl
echo ""
log_success "RESCOPE-ACL complete — token scoped to /pool/$PVE_POOL + /storage/[${PVE_STORAGES[*]}] + Sys.Audit/SDN.Use@/."
log_warn " NOW deploy agent >= v0.53.0 (restore-into-pool) and (re)start felhom-agent — the scoped ACL needs it."
$DRY_RUN && log_warn " DRY-RUN: nothing above was actually executed."
return 0
}
#-------------------------------------------------------------------------------
# Arg parse
#-------------------------------------------------------------------------------
while [[ $# -gt 0 ]]; do
case "$1" in
--customer-id) CUSTOMER_ID="$2"; shift 2 ;;
--mode) MODE="$2"; shift 2 ;;
--hub-url) HUB_URL="$2"; shift 2 ;;
--vmid) VMID="$2"; VMID_EXPLICIT=true; shift 2 ;;
--golden) GOLDEN_VOLID="$2"; shift 2 ;;
--golden-vmid) GOLDEN_VMID="$2"; shift 2 ;;
--archive-storage) ARCHIVE_STORAGE="$2"; shift 2 ;;
--node) NODE="$2"; NODE_EXPLICIT=true; shift 2 ;;
--bridge-ip) BRIDGE_ADDR="$2"; shift 2 ;;
--rootfs-grow) ROOTFS_GROW="$2"; shift 2 ;;
--datavol-grow) DATAVOL_GROW="$2"; shift 2 ;;
--sysdata-grow) SYSDATA_GROW="$2"; shift 2 ;;
--cores) CPU_CORES="$2"; shift 2 ;;
--memory) MEM_MIB="$2"; shift 2 ;;
--passphrase-file) PASSPHRASE_FILE="$2"; shift 2 ;;
--preserve-from) PRESERVE_FROM="$2"; shift 2 ;;
--preserve-state-from) PRESERVE_STATE_FROM="$2"; shift 2 ;;
--allow-new-leaf) ALLOW_NEW_LEAF=true; shift ;;
--force) FORCE=true; shift ;;
--force-gitea-golden) FORCE_GITEA_GOLDEN=true; shift ;;
--skip-provision) SKIP_PROVISION=true; shift ;;
--uninstall) UNINSTALL=true; shift ;;
--remove-golden) REMOVE_GOLDEN=true; shift ;;
--adopt-pool) ADOPT_POOL=true; shift ;;
--rescope-acl) RESCOPE_ACL=true; shift ;;
--rotate-recovery) ROTATE_RECOVERY=true; shift ;;
--enable-oob) ENABLE_OOB=true; shift ;;
--acl-storages) read -ra PVE_STORAGES <<< "$2"; shift 2 ;;
--dry-run) DRY_RUN=true; shift ;;
--resume) RESUME=true; shift ;;
-h|--help) usage ;;
*) die "Unknown option: $1 (use -h)" ;;
esac
done
#===============================================================================
# UNINSTALL MODE — local host teardown (no hub contact, no passphrase). Dispatched early,
# before any provision/DR logic, and does not require --customer-id.
#===============================================================================
if $UNINSTALL; then
[[ $EUID -eq 0 ]] || die "must run as root"
echo ""
log_info "felhom-host-install v${SCRIPT_VERSION} — mode=uninstall"
$DRY_RUN && log_warn "DRY-RUN: no mutations will be performed"
echo ""
run_uninstall
exit 0
fi
#===============================================================================
# ADOPT-POOL MODE — retrofit an EXISTING Felhom guest into the felhom pool (non-destructive; no hub
# contact, no passphrase, no guest reconfigure beyond pool membership). Dispatched early.
#===============================================================================
if $ADOPT_POOL; then
[[ $EUID -eq 0 ]] || die "must run as root"
echo ""
log_info "felhom-host-install v${SCRIPT_VERSION} — mode=adopt-pool"
$DRY_RUN && log_warn "DRY-RUN: no mutations will be performed"
echo ""
run_adopt_pool
exit 0
fi
#===============================================================================
# RESCOPE-ACL MODE — migrate an existing install to the pool-scoped token ACL (ACL-only, no hub, no
# passphrase). Supervised: run with the agent stopped, then deploy agent >= v0.53.0 (see §13).
#===============================================================================
if $RESCOPE_ACL; then
[[ $EUID -eq 0 ]] || die "must run as root"
echo ""
log_info "felhom-host-install v${SCRIPT_VERSION} — mode=rescope-acl"
$DRY_RUN && log_warn "DRY-RUN: no mutations will be performed"
echo ""
run_rescope_acl
exit 0
fi
#===============================================================================
# DR MODE — documented seam only (10D). NOT implemented.
#===============================================================================
if [[ "$MODE" == "dr" ]]; then
log_error "DR mode not yet implemented (10D)."
cat >&2 <<'EOF'
The DR step skeleton (for the future implementer) mirrors provision EXCEPT
the restore source:
1. pre-flight (root, PVE, hub reachable, customer+passphrase valid)
2. pveum token (identical to provision)
3. host-enroll (mint-once-reuse — the lost host re-binds to its customer)
4. agent config write (identical)
5. RESTORE: instead of the golden, restore the customer's OWN whole-CT PBS
snapshot (continuity preserved) — agent --selftest=bring-up -mode dr
-archive <pbs-snapshot>. Identity/keys come from escrow + the hub recipe.
6. verify (identical)
EOF
exit 2
fi
[[ "$MODE" == "provision" ]] || die "Unknown --mode: $MODE (provision|dr)"
#===============================================================================
# PROVISION MODE
#===============================================================================
[[ -n "$CUSTOMER_ID" ]] || die "--customer-id is required (use -h)"
echo ""
log_info "felhom-host-install v${SCRIPT_VERSION} — mode=provision customer=${CUSTOMER_ID} vmid=${VMID}"
$DRY_RUN && log_warn "DRY-RUN: no mutations will be performed"
echo ""
#-------------------------------------------------------------------------------
# Read passphrase (no-echo prompt or 0600 file) — never on argv/logs
#-------------------------------------------------------------------------------
read_passphrase() {
if [[ -n "$PASSPHRASE_FILE" ]]; then
[[ -f "$PASSPHRASE_FILE" ]] || die "--passphrase-file not found: $PASSPHRASE_FILE"
local perm; perm=$(stat -c '%a' "$PASSPHRASE_FILE")
[[ "$perm" == "600" || "$perm" == "400" ]] || log_warn "passphrase file $PASSPHRASE_FILE is mode $perm (want 600)"
PASSPHRASE="$(< "$PASSPHRASE_FILE")"; PASSPHRASE="${PASSPHRASE%$'\n'}"
else
# Read from the terminal explicitly (not stdin), so the no-echo prompt works whether the
# script is run from a file OR piped to bash (curl … | sudo bash) — where stdin is the pipe.
read -rsp "Retrieval passphrase for customer '${CUSTOMER_ID}': " PASSPHRASE < /dev/tty; echo ""
fi
[[ -n "$PASSPHRASE" ]] || die "empty passphrase"
}
#-------------------------------------------------------------------------------
# STEP 1 — pre-flight (fail fast before any mutation)
#-------------------------------------------------------------------------------
step_preflight() {
log_step "1/8 pre-flight"
[[ $EUID -eq 0 ]] || die "must run as root"
command -v pveum >/dev/null || die "pveum not found — is this a Proxmox VE host?"
command -v pct >/dev/null || die "pct not found — is this a Proxmox VE host?"
command -v pvesh >/dev/null || die "pvesh not found"
command -v curl >/dev/null || die "curl not found"
command -v python3>/dev/null || die "python3 not found"
local pvever; pvever=$(pveversion | head -1)
[[ "$pvever" == *"/9."* ]] || log_warn "expected PVE 9.x, got: $pvever"
log_info " $pvever"
# node — on a MULTI-NODE cluster, auto-selecting nodes[0] is a wrong-node footgun. Require an
# explicit --node unless there is exactly one node (or no guest will be provisioned).
local nodes_json node_count node_names
nodes_json=$(pvesh get /nodes --output-format json 2>/dev/null || echo "[]")
node_count=$(python3 -c "import json,sys;print(len(json.loads(sys.argv[1])))" "$nodes_json" 2>/dev/null || echo 0)
if [[ "${node_count:-0}" -gt 1 ]] && ! $NODE_EXPLICIT && ! $SKIP_PROVISION; then
node_names=$(python3 -c "import json,sys;print(', '.join(n['node'] for n in json.loads(sys.argv[1])))" "$nodes_json" 2>/dev/null || echo "?")
die "this is a ${node_count}-node cluster (${node_names}); pass --node explicitly — auto-selecting nodes[0] risks provisioning on the wrong node."
fi
if [[ -z "$NODE" ]]; then
NODE=$(python3 -c "import json,sys;print(json.loads(sys.argv[1])[0]['node'])" "$nodes_json" 2>/dev/null || hostname)
fi
if $NODE_EXPLICIT; then log_info " node: $NODE (explicit)"; else log_info " node: $NODE (auto)"; fi
# agent config path: honor the existing systemd unit's -config, else default
if systemctl cat felhom-agent >/dev/null 2>&1; then
AGENT_CONFIG=$(systemctl cat felhom-agent 2>/dev/null | grep -oP '(?<=-config )\S+' | head -1)
fi
[[ -n "$AGENT_CONFIG" ]] || AGENT_CONFIG="/etc/felhom-agent/agent.json"
log_info " agent config: $AGENT_CONFIG"
# v1.1.0: the agent binary is no longer a prerequisite — the agent-install step (5/8) fetches it
# from Gitea + verifies it. Just report what's present (if anything).
if command -v felhom-agent >/dev/null 2>&1; then
log_info " agent (existing): $(felhom-agent --version 2>&1 | head -1)"
else
log_info " agent: not installed yet — will be fetched + installed in step 5/8"
fi
# local-lvm free space
local free_gib
free_gib=$(lvs --noheadings --units g -o lv_size,data_percent /dev/pve/data 2>/dev/null | awk '{gsub(/[^0-9.]/,"",$1); used=$2; print int($1*(100-used)/100)}' 2>/dev/null || echo 0)
if [[ "${free_gib:-0}" -gt 0 ]]; then
log_info " local-lvm free: ~${free_gib} GiB"
[[ "$free_gib" -ge "$HARD_MIN_LVM_GIB" ]] || log_warn "local-lvm free ~${free_gib} GiB < hard min ${HARD_MIN_LVM_GIB} GiB"
else
log_warn " could not read local-lvm free space (continuing)"
fi
# RAM floor (soft): a big appliance guest can pressure existing guests on a small box. WARN only.
local mem_avail_mib
mem_avail_mib=$(awk '/^MemAvailable:/{print int($2/1024)}' /proc/meminfo 2>/dev/null || echo 0)
if [[ "${mem_avail_mib:-0}" -gt 0 ]]; then
if [[ "$mem_avail_mib" -lt 2048 ]]; then
log_warn " low free RAM (~${mem_avail_mib} MiB); the appliance guest may pressure existing guests — consider the CPU/mem cap."
else
log_info " free RAM: ~${mem_avail_mib} MiB"
fi
fi
# Appliance-cap sanity (soft): a cap that EXCEEDS host resources won't protect other guests. WARN,
# never die — the operator may know better (e.g. capping below a future hardware upgrade).
if ! $SKIP_PROVISION; then
if [[ -n "$CPU_CORES" ]]; then
local host_cores; host_cores=$(nproc 2>/dev/null || echo 0)
if [[ "${host_cores:-0}" -gt 0 && "$CPU_CORES" -gt "$host_cores" ]]; then
log_warn " requested cap (${CPU_CORES} cores) exceeds host cores (${host_cores}); the cap won't protect other guests."
fi
fi
if [[ -n "$MEM_MIB" ]]; then
local host_mem_mib; host_mem_mib=$(awk '/^MemTotal:/{print int($2/1024)}' /proc/meminfo 2>/dev/null || echo 0)
if [[ "${host_mem_mib:-0}" -gt 0 && "$MEM_MIB" -gt "$host_mem_mib" ]]; then
log_warn " requested cap (${MEM_MIB} MiB) exceeds host RAM (~${host_mem_mib} MiB); the cap won't protect other guests."
fi
fi
fi
# archive-storage-exists guard (provision only — the golden lives there + the restore reads it).
if ! $SKIP_PROVISION; then
if pvesm status --storage "$ARCHIVE_STORAGE" >/dev/null 2>&1; then
log_info " archive storage '$ARCHIVE_STORAGE' present"
else
die "archive storage '$ARCHIVE_STORAGE' not found (pvesm status). Pass --archive-storage NAME."
fi
fi
# hub reachable
local hc; hc=$(http_code "$HUB_URL/api/v1/config/$CUSTOMER_ID" -H "X-Retrieval-Password: preflight-no-op" || echo 000)
[[ "$hc" != "000" ]] || die "hub unreachable at $HUB_URL"
log_info " hub reachable ($HUB_URL)"
# customer + passphrase valid (read-only GET /config/{id})
read_passphrase
local code; code=$(http_code "$HUB_URL/api/v1/config/$CUSTOMER_ID" -H "X-Retrieval-Password: $PASSPHRASE")
case "$code" in
200) log_success " customer '$CUSTOMER_ID' exists + passphrase valid" ;;
401) die "passphrase REJECTED (401) for customer '$CUSTOMER_ID'" ;;
404) die "customer '$CUSTOMER_ID' not found in hub (404) — create it in the hub first" ;;
*) die "unexpected hub status $code on config preflight" ;;
esac
# golden archive — auto-discover a LOCAL one for info; the golden step (7/8) ensures one exists
# (local else Gitea-fetched + verified), so a missing local golden is no longer fatal here.
if [[ -z "$GOLDEN_VOLID" ]] && ! $FORCE_GITEA_GOLDEN; then
GOLDEN_VOLID=$(pvesm list "$ARCHIVE_STORAGE" --content backup 2>/dev/null | awk -v v="$GOLDEN_VMID" '$0 ~ ("vzdump-lxc-" v "-"){print $1}' | sort | tail -1)
fi
if [[ -n "$GOLDEN_VOLID" ]]; then
pvesm list "$ARCHIVE_STORAGE" --content backup 2>/dev/null | grep -q "$(basename "$GOLDEN_VOLID")" || die "golden volid not resolvable: $GOLDEN_VOLID"
log_info " golden (local): $GOLDEN_VOLID"
else
log_info " golden: none local — will fetch + verify from Gitea in step 7/8"
fi
# vmid guard (irrelevant when --skip-provision: we never touch a guest). "In use" is checked
# against the pct+qm id-set (LXC and VMs share the space), not just `pct status`.
if $SKIP_PROVISION; then
log_info " --skip-provision: agent install/config only, no guest will be provisioned"
elif _vmid_in_use "$VMID"; then
if $VMID_EXPLICIT; then
# Explicit --vmid stays deterministic: die unless --force (which over-provisions, destructive).
if $FORCE; then
log_warn " vmid $VMID already exists — --force given, it WILL be destroyed by provision"
else
die "vmid $VMID already exists. Refusing to clobber a live guest. Pass --force to provision over it."
fi
elif $FORCE; then
# Default vmid + --force: honor the destructive over-provision without prompting.
log_warn " vmid $VMID already exists — --force given, it WILL be destroyed by provision"
else
# Default vmid in use, no --force: auto-pick the next free id and CONFIRM (never silent).
local free_vmid; free_vmid=$(next_free_vmid "$VMID")
log_info " vmid $VMID is in use; next free vmid is $free_vmid"
local ans; read -rp "VMID $VMID is in use. Use next free VMID $free_vmid? [y/N] " ans < /dev/tty
[[ "$ans" == "y" || "$ans" == "Y" ]] || die "no free vmid confirmed"
VMID="$free_vmid"
log_success " using auto-selected vmid $VMID"
fi
fi
# Record the customer into the install state (foundation for a later automatic --uninstall).
_state_put customer_id "$CUSTOMER_ID"
_state_mark preflight
log_success "pre-flight passed"
}
#-------------------------------------------------------------------------------
# STEP 2 — Proxmox API token (idempotent pveum; reuse-if-working else rotate)
#-------------------------------------------------------------------------------
step_token() {
log_step "2/8 Proxmox API token"
if should_skip token && [[ -n "$PVE_TOKEN" ]]; then return 0; fi
# Pool BEFORE the ACL: /pool/felhom must exist before apply_scoped_acl grants on it (3b). Always —
# even under --skip-provision (the token exists now; a later provision-into-pool needs pool + grant).
# The 3 scoped roles + grants are created by apply_scoped_acl below (AFTER the token exists).
ensure_felhom_pool
# user: tolerate-exists
if pveum user list --output-format json 2>/dev/null | python3 -c "import json,sys;sys.exit(0 if any(u['userid']=='$PVE_USER' for u in json.load(sys.stdin)) else 1)"; then
log_info " user $PVE_USER exists"
else
run pveum user add "$PVE_USER"
fi
# token: reuse if the existing agent config token still authenticates, else rotate
local reused=false
if [[ -f "$AGENT_CONFIG" ]] && python3 -c "import json,sys;d=json.load(open('$AGENT_CONFIG'));sys.exit(0 if d.get('proxmox',{}).get('token') else 1)" 2>/dev/null; then
log_info " existing agent config has a token — testing it (read-only --selftest)"
if felhom-agent --config "$AGENT_CONFIG" --selftest >/dev/null 2>&1; then
log_success " existing token authenticates — REUSING (no rotation)"
PVE_TOKEN=$(python3 -c "import json;print(json.load(open('$AGENT_CONFIG'))['proxmox']['token'])")
reused=true
else
log_warn " existing token failed selftest — will rotate"
fi
fi
if ! $reused; then
if $DRY_RUN; then
log_dry "pveum user token remove $PVE_USER $PVE_TOKENID # if present"
log_dry "pveum user token add $PVE_USER $PVE_TOKENID --privsep 1 --output-format json # capture .value"
PVE_TOKEN="${PVE_USER}!${PVE_TOKENID}=<DRY-RUN-SECRET>"
else
if pveum user token list "$PVE_USER" --output-format json 2>/dev/null | python3 -c "import json,sys;sys.exit(0 if any(t['tokenid']=='$PVE_TOKENID' for t in json.load(sys.stdin)) else 1)"; then
log_info " removing stale token $PVE_TOKENID (secret unrecoverable — rotating)"
pveum user token remove "$PVE_USER" "$PVE_TOKENID"
fi
local secret
secret=$(pveum user token add "$PVE_USER" "$PVE_TOKENID" --privsep 1 --output-format json | python3 -c "import json,sys;print(json.load(sys.stdin)['value'])")
[[ -n "$secret" ]] || die "failed to capture new token secret"
PVE_TOKEN="${PVE_USER}!${PVE_TOKENID}=${secret}"
log_success " token minted (secret captured, not logged)"
fi
fi
# Scoped ACL grants — AFTER the token exists (`pveum user token remove` purges the token's ACL, so
# re-applying post-rotate is mandatory; `acl modify` is idempotent so this is safe on the reuse path).
apply_scoped_acl
# If this box previously ran the pre-3b broad grant (re-install/upgrade), remove it — else the old
# FelhomAgent role at / would UNION with the scoped grant and defeat containment. Tolerate-absent.
remove_old_broad_acl
_state_mark token
}
#-------------------------------------------------------------------------------
# STEP 3 — compute grows (floors) if not passed
#-------------------------------------------------------------------------------
step_grows() {
log_step "3/8 compute volume grows"
# Golden base: rootfs 32G + Docker-data 16G + user-data 8G (build-golden.sh).
if [[ -z "$ROOTFS_GROW$DATAVOL_GROW$SYSDATA_GROW" ]]; then
local free_gib
free_gib=$(lvs --noheadings --units g -o lv_size,data_percent /dev/pve/data 2>/dev/null | awk '{gsub(/[^0-9.]/,"",$1); used=$2; print int($1*(100-used)/100)}' 2>/dev/null || echo 0)
# Reserve headroom; split the rest ~ docker 80% / sysdata 20%; rootfs stays golden.
ROOTFS_GROW=0
if [[ "${free_gib:-0}" -ge 300 ]]; then
DATAVOL_GROW=184; SYSDATA_GROW=42 # reproduces the standard 200G/50G appliance
elif [[ "${free_gib:-0}" -ge 150 ]]; then
DATAVOL_GROW=84; SYSDATA_GROW=22
else
DATAVOL_GROW=34; SYSDATA_GROW=12 # minimal floors
fi
log_info " auto-computed from ~${free_gib} GiB free"
fi
ROOTFS_GROW="${ROOTFS_GROW:-0}"; DATAVOL_GROW="${DATAVOL_GROW:-0}"; SYSDATA_GROW="${SYSDATA_GROW:-0}"
log_info " grows: rootfs +${ROOTFS_GROW}G (->$((32+ROOTFS_GROW))G), docker +${DATAVOL_GROW}G (->$((16+DATAVOL_GROW))G), sys_drive +${SYSDATA_GROW}G (->$((8+SYSDATA_GROW))G)"
_state_mark grows
}
#-------------------------------------------------------------------------------
# STEP 4 — host enroll (option C; single secret, no global key)
#-------------------------------------------------------------------------------
step_enroll() {
log_step "4/8 host enrollment (POST /host-enroll)"
if $DRY_RUN; then
log_dry "curl -fsS -X POST $HUB_URL/api/v1/host-enroll -H 'X-Retrieval-Password: <pass>' -d '{\"customer_id\":\"$CUSTOMER_ID\"}'"
HOST_ID="<dry-run-host-id>"; HOST_API_KEY="<dry-run-key>"; _state_mark enroll; return 0
fi
local resp code body
resp=$(curl -sS -w $'\n%{http_code}' -X POST "$HUB_URL/api/v1/host-enroll" \
-H "X-Retrieval-Password: $PASSPHRASE" -H 'Content-Type: application/json' \
-d "{\"customer_id\":\"$CUSTOMER_ID\"}")
code=$(tail -n1 <<<"$resp"); body=$(sed '$d' <<<"$resp")
case "$code" in
201) log_success " host MINTED (first enroll)" ;;
200) log_success " host REUSED (idempotent — existing credential)" ;;
401) die "host-enroll 401 (passphrase) — should have been caught in preflight" ;;
404) die "host-enroll 404 (unknown customer)" ;;
*) die "host-enroll unexpected $code: $body" ;;
esac
HOST_ID=$(python3 -c "import json,sys;print(json.loads(sys.argv[1])['host_id'])" "$body")
HOST_API_KEY=$(python3 -c "import json,sys;print(json.loads(sys.argv[1])['api_key'])" "$body")
[[ -n "$HOST_ID" && -n "$HOST_API_KEY" ]] || die "host-enroll: malformed response"
log_info " host_id: $HOST_ID (api_key captured, not logged)"
_state_mark enroll
}
#-------------------------------------------------------------------------------
# STEP 4b — break-glass credential (TASK G1): generate + set + vault the root@pam console password
#-------------------------------------------------------------------------------
# The human fallback for when BOTH the sshd path AND the agent-independent auto-heal (layers 1+2) have
# failed: a strong root@pam password lets the operator reach the PVE WEB CONSOLE (pveproxy :8006 — a
# failure domain distinct from sshd) and run the one-line /run/sshd fix. Generated with strong entropy,
# set via chpasswd, and vaulted to the hub over the enroll-authenticated channel (host api_key). The
# password is NEVER logged, printed, or written to any file — it goes stdin→chpasswd and stdin→curl
# only (SPIKE-felhom-sshd finding #9 / TASK G1 trap 3). Idempotent: skipped if already vaulted unless
# --rotate-recovery (a re-set would strand the operator's saved copy).
step_break_glass() {
log_step "4b/8 break-glass credential (root@pam console password → hub vault)"
if [[ -z "${HOST_ID:-}" || -z "${HOST_API_KEY:-}" ]]; then
log_warn " no host_id/api_key (enroll skipped?) — cannot vault a recovery credential; skipping"
return 0
fi
if $DRY_RUN; then
log_dry "openssl rand → strong root@pam password (never logged) ; chpasswd ; PUT $HUB_URL/api/v1/hosts/$HOST_ID/recovery-credential (Bearer host key)"
_state_mark break_glass; return 0
fi
if _state_has break_glass && ! $ROTATE_RECOVERY; then
log_skip " recovery credential already vaulted (use --rotate-recovery to regenerate)"
return 0
fi
# Strong password: 24 url-safe bytes (~144 bits). Kept ONLY in a local shell var, never on disk.
local newpw
newpw=$(openssl rand -base64 24 2>/dev/null | tr -d '\n' | tr '+/' '-_')
[[ ${#newpw} -ge 24 ]] || die "failed to generate a strong recovery password"
# Set root@pam (= the Linux root user on PVE) via chpasswd on STDIN — no argv, no log.
if ! printf 'root:%s\n' "$newpw" | chpasswd 2>/dev/null; then
newpw="" # scrub
die "chpasswd failed to set the root@pam recovery password"
fi
# Vault to the hub over the host-key-authenticated channel; password only on stdin (-d @-).
local code
code=$(printf '{"username":"root@pam","password":"%s"}' "$newpw" \
| curl -sS -o /dev/null -w '%{http_code}' -X PUT \
"$HUB_URL/api/v1/hosts/$HOST_ID/recovery-credential" \
-H "Authorization: Bearer $HOST_API_KEY" -H 'Content-Type: application/json' -d @- 2>/dev/null)
newpw="" # scrub the plaintext from the shell var the moment it is vaulted
case "$code" in
200) log_success " root@pam password set + vaulted to the hub (retrieve via the operator /admin path; never logged here)" ;;
401|403) die "recovery-credential vault rejected ($code) — host key/authorization problem" ;;
*) die "recovery-credential vault failed (HTTP $code)" ;;
esac
_state_mark break_glass
}
#-------------------------------------------------------------------------------
# STEP 5 — agent install: fetch+verify the binary, ensure the service user, sudoers, unit
#-------------------------------------------------------------------------------
# Closes the old prerequisite "install the agent binary + unit manually". Fetches the binary from
# Gitea (git token from controller.yaml), VERIFIES its sha256 against the hub manifest, then installs
# the non-root felhom-agent user + binary + sudoers + unit. The SERVICE is started in step 6 (after the
# config is written) — here we only install + daemon-reload + enable.
step_agent_install() {
log_step "5/8 agent install (fetch + verify + install)"
# Manifest + git fetch credential (both passphrase / config-retrieve — NO new credential).
resolve_artifacts
resolve_git_creds
[[ -n "$ART_AGENT_VER" ]] || die "hub artifact manifest has no agent version — set it in the operator UI (Configs → Day-0 artifacts)"
log_info " manifest: agent v$ART_AGENT_VER (sha ${ART_AGENT_SHA:0:16}…), golden v${ART_GOLDEN_VER:-<unset>}"
# Idempotent skip: same version already installed AND the service is healthy.
local cur=""
[[ -x "$AGENT_BIN" ]] && cur=$("$AGENT_BIN" --version 2>/dev/null | awk '{print $2}')
if [[ "$cur" == "$ART_AGENT_VER" ]] && systemctl is-active --quiet felhom-agent 2>/dev/null; then
log_skip " agent v$cur already installed + service active — skipping binary install"
else
local url="$GITEA_BASE/api/packages/$GITEA_OWNER/generic/felhom-agent/$ART_AGENT_VER/felhom-agent"
log_info " fetching agent binary v$ART_AGENT_VER from Gitea …"
if $DRY_RUN; then
log_dry "curl -u <git> -o /tmp/felhom-agent.new $url ; verify sha256=$ART_AGENT_SHA ; install -m0755 -> $AGENT_BIN"
else
local tmp; tmp=$(mktemp -t felhom-agent.XXXXXX)
fetch_verify "$url" "$tmp" "$ART_AGENT_SHA"
# back up any existing binary before replacing
if [[ -f "$AGENT_BIN" ]]; then
cp -a "$AGENT_BIN" "${AGENT_BIN}.bak-$(date +%s)" 2>/dev/null || true
fi
install -m 0755 -o root -g root "$tmp" "$AGENT_BIN"
rm -f "$tmp"
log_success " installed $AGENT_BIN ($("$AGENT_BIN" --version 2>&1 | head -1))"
fi
fi
# The non-root model REQUIRES the `sudo` package (provides both `sudo` and `visudo`). A host that
# previously ran the agent as root+`direct` won't have it installed. Install it idempotently before
# the sudoers (visudo validates it) and before the daemon starts (it shells out via `sudo -n`).
if ! command -v sudo >/dev/null 2>&1 || ! command -v visudo >/dev/null 2>&1; then
if $DRY_RUN; then
log_dry "apt-get install -y sudo # required for the non-root agent (provides sudo + visudo)"
else
log_info " installing the 'sudo' package (required for the non-root agent model) …"
DEBIAN_FRONTEND=noninteractive apt-get install -y -q sudo >/dev/null 2>&1 \
|| { apt-get update -q >/dev/null 2>&1; DEBIAN_FRONTEND=noninteractive apt-get install -y -q sudo >/dev/null 2>&1; } \
|| die "failed to install the 'sudo' package (needed for the non-root agent)"
log_success " sudo installed ($(sudo --version 2>/dev/null | head -1))"
fi
fi
# Resolve visudo by absolute path too (non-login SSH PATH can miss /usr/sbin).
local VISUDO; VISUDO=$(command -v visudo 2>/dev/null || echo /usr/sbin/visudo)
# Service user (system, no login, no home dir creation needed beyond state).
if $DRY_RUN; then
log_dry "useradd --system --no-create-home --shell /usr/sbin/nologin $AGENT_USER # if absent"
elif id "$AGENT_USER" >/dev/null 2>&1; then
log_info " service user $AGENT_USER exists"
else
useradd --system --no-create-home --shell /usr/sbin/nologin "$AGENT_USER"
log_success " created service user $AGENT_USER"
fi
# State dir (the old root deployment may have created it root-owned; StateDirectory= also adjusts
# on start, but chown here so the very first start has a writable dir).
run mkdir -p "$AGENT_STATE_DIR"
run chown -R "${AGENT_USER}:${AGENT_USER}" "$AGENT_STATE_DIR"
run chmod 0750 "$AGENT_STATE_DIR"
# ── Agent local-API leaf lifecycle (B.2) ──────────────────────────────────────────────────────
# The leaf's SHA-256 is pinned into EVERY guest's bootstrap. A reinstall that REGENERATES the leaf
# invalidates every controller's pin (the 2026-06-28 root→non-root incident → controller↔agent dead
# for days). Two protections:
# (a) --preserve-state-from DIR: carry the prior leaf+key+token-store over → the fp stays STABLE,
# no re-bootstrap needed. (Distinct from --preserve-from, which merges config sections only.)
# (b) populated-host guard: REFUSE to proceed leaf-less on a host that already has guests, unless
# --preserve-state-from or an explicit --allow-new-leaf is given. Converts the silent footgun
# into a hard stop.
local _have_leaf=false
[[ -f "$AGENT_STATE_DIR/local-api.crt" && -f "$AGENT_STATE_DIR/local-api.key" ]] && _have_leaf=true
if [[ -n "$PRESERVE_STATE_FROM" ]]; then
[[ -f "$PRESERVE_STATE_FROM/local-api.crt" && -f "$PRESERVE_STATE_FROM/local-api.key" ]] \
|| die "--preserve-state-from $PRESERVE_STATE_FROM: local-api.crt/key not found there"
openssl x509 -in "$PRESERVE_STATE_FROM/local-api.crt" -noout >/dev/null 2>&1 \
|| die "--preserve-state-from: $PRESERVE_STATE_FROM/local-api.crt does not parse as an X.509 cert — refusing"
if $DRY_RUN; then
log_dry "preserve agent state: copy local-api.{crt,key}+local-tokens.log from $PRESERVE_STATE_FROM -> $AGENT_STATE_DIR (chown $AGENT_USER; 644/600/600)"
else
install -o "$AGENT_USER" -g "$AGENT_USER" -m 0644 "$PRESERVE_STATE_FROM/local-api.crt" "$AGENT_STATE_DIR/local-api.crt"
install -o "$AGENT_USER" -g "$AGENT_USER" -m 0600 "$PRESERVE_STATE_FROM/local-api.key" "$AGENT_STATE_DIR/local-api.key"
[[ -f "$PRESERVE_STATE_FROM/local-tokens.log" ]] && \
install -o "$AGENT_USER" -g "$AGENT_USER" -m 0600 "$PRESERVE_STATE_FROM/local-tokens.log" "$AGENT_STATE_DIR/local-tokens.log"
log_success " preserved agent leaf+token store from $PRESERVE_STATE_FROM (pin stays stable — no re-bootstrap)"
fi
_have_leaf=true
fi
if ! $_have_leaf && ! $ALLOW_NEW_LEAF; then
if pct list 2>/dev/null | tail -n +2 | grep -q .; then
die "this host already has guests but $AGENT_STATE_DIR has no agent leaf to preserve.
Re-running here will REGENERATE the leaf and invalidate every controller's pin (the 2026-06-28 incident).
Pass --preserve-state-from <old state dir> to keep the pin stable, or --allow-new-leaf to regenerate
intentionally (every guest must then be re-bootstrapped)."
fi
fi
# Guarded-mkfs wrapper (Impl-1 Part B) — the ONLY mkfs path the sudoers permits. Install it BEFORE
# the sudoers (which allowlists it), 0755 root:root under /usr/local/sbin. bash -n before install.
if $DRY_RUN; then
log_dry "fetch configs/felhom-mkfs-guarded.sh ; bash -n ; install 0755 -> /usr/local/sbin/felhom-mkfs-guarded"
else
local wtmp; wtmp=$(mktemp -t felhom-mkfs.XXXXXX)
fetch_raw "configs/felhom-mkfs-guarded.sh" "$wtmp"
bash -n "$wtmp" || { rm -f "$wtmp"; die "fetched felhom-mkfs-guarded.sh failed bash -n — refusing to install"; }
install -m 0755 -o root -g root "$wtmp" /usr/local/sbin/felhom-mkfs-guarded
rm -f "$wtmp"
log_success " installed /usr/local/sbin/felhom-mkfs-guarded (0755, the guarded mkfs path)"
fi
# Self-update guarded wrapper (TASK D1) — the ONLY binary-swap path the sudoers permits. Install
# it BEFORE the sudoers (which allowlists it), 0755 root:root under /usr/local/sbin. sh -n first.
if $DRY_RUN; then
log_dry "fetch configs/felhom-selfupdate-guarded ; sh -n ; install 0755 -> /usr/local/sbin/felhom-selfupdate-guarded"
else
local sutmp; sutmp=$(mktemp -t felhom-selfupd.XXXXXX)
fetch_raw "configs/felhom-selfupdate-guarded" "$sutmp"
sh -n "$sutmp" || { rm -f "$sutmp"; die "fetched felhom-selfupdate-guarded failed sh -n — refusing to install"; }
install -m 0755 -o root -g root "$sutmp" /usr/local/sbin/felhom-selfupdate-guarded
rm -f "$sutmp"
log_success " installed /usr/local/sbin/felhom-selfupdate-guarded (0755, the guarded A/B binary-swap path)"
fi
# Sudoers — fetch the canonical file, validate with visudo -cf BEFORE installing (0440 root:root).
if $DRY_RUN; then
log_dry "fetch configs/felhom-agent.sudoers ; visudo -cf ; install 0440 -> $AGENT_SUDOERS"
else
local sdtmp; sdtmp=$(mktemp -t felhom-sudoers.XXXXXX)
fetch_raw "configs/felhom-agent.sudoers" "$sdtmp"
"$VISUDO" -cf "$sdtmp" >/dev/null || { rm -f "$sdtmp"; die "fetched sudoers failed visudo -cf — refusing to install"; }
install -m 0440 -o root -g root "$sdtmp" "$AGENT_SUDOERS"
rm -f "$sdtmp"
# re-validate the live drop-in in the full sudoers context
"$VISUDO" -cf /etc/sudoers >/dev/null || die "sudoers invalid after installing $AGENT_SUDOERS"
log_success " installed $AGENT_SUDOERS (0440, visudo-validated)"
fi
# systemd unit — fetch the canonical unit, install, daemon-reload, enable (NOT start — no config yet).
if $DRY_RUN; then
log_dry "fetch configs/felhom-agent.service -> $AGENT_UNIT ; systemctl daemon-reload ; systemctl enable felhom-agent"
else
local untmp; untmp=$(mktemp -t felhom-unit.XXXXXX)
fetch_raw "configs/felhom-agent.service" "$untmp"
grep -q "User=$AGENT_USER" "$untmp" || { rm -f "$untmp"; die "fetched unit does not run as $AGENT_USER — refusing"; }
if [[ -f "$AGENT_UNIT" ]]; then cp -a "$AGENT_UNIT" "${AGENT_UNIT}.bak-$(date +%s)" 2>/dev/null || true; fi
install -m 0644 -o root -g root "$untmp" "$AGENT_UNIT"
rm -f "$untmp"
systemctl daemon-reload
systemctl enable felhom-agent >/dev/null 2>&1 || true
log_success " installed $AGENT_UNIT + enabled (started in step 6 after config)"
fi
# Self-update rollback unit + start-limit drop-in (TASK D1). The drop-in gives felhom-agent the
# tuned start-limit (SPIKE-agent-selfupdate: [Unit] StartLimitIntervalSec=120 + Burst=4 → a
# crash-looping update reaches terminal `failed` in ~20s instead of looping forever) and the
# OnFailure= that auto-reverts. Both are idempotent installs (+ daemon-reload). Non-fatal on a
# box whose agent repo predates them (the raw fetch would 404) — self-update just stays manual.
if $DRY_RUN; then
log_dry "fetch configs/felhom-agent-rollback.service -> /etc/systemd/system/ ; fetch configs/felhom-agent-limits.conf -> $AGENT_UNIT.d/ ; daemon-reload"
else
local rbtmp; rbtmp=$(mktemp -t felhom-rollback.XXXXXX)
if fetch_raw "configs/felhom-agent-rollback.service" "$rbtmp" 2>/dev/null; then
install -m 0644 -o root -g root "$rbtmp" /etc/systemd/system/felhom-agent-rollback.service
local ddir="${AGENT_UNIT}.d"; mkdir -p "$ddir"
local lmtmp; lmtmp=$(mktemp -t felhom-limits.XXXXXX)
fetch_raw "configs/felhom-agent-limits.conf" "$lmtmp"
# [SF-3] the keys MUST be in [Unit] — refuse a drop-in that would half-apply in [Service].
grep -q '^\[Unit\]' "$lmtmp" || { rm -f "$lmtmp" "$rbtmp"; die "self-update limits drop-in missing [Unit] section — refusing"; }
install -m 0644 -o root -g root "$lmtmp" "$ddir/felhom-agent-limits.conf"
rm -f "$lmtmp"
systemctl daemon-reload
log_success " installed self-update rollback unit + start-limit drop-in (auto-rollback armed)"
else
log_skip " self-update rollback artifacts not in the agent repo yet — self-update stays manual"
fi
rm -f "$rbtmp"
fi
# Management-plane break-glass layers 1+2 (TASK G1). Three artifacts that keep the host reachable
# even if a second sshd (H1) removes the SHARED /run/sshd privsep dir (SPIKE-felhom-sshd §8):
# • felhom-privsep.conf (tmpfiles) — layer 1: /run/sshd is boot-persistent, owned by no unit.
# • felhom-mgmt-watchdog (script) — layer 2 heal action (recreate dir + reset-failed sshd).
# • .service + .timer — run it every ~60s, AGENT-INDEPENDENTLY (heals with the
# agent down — the whole point; trap 1).
# Non-fatal if the agent repo predates them (raw fetch 404s → break-glass just stays manual).
# HARD GUARD: refuse ANY fetched unit that declares RuntimeDirectory= — that directive is the very
# incident G1 closes (a second sshd's `RuntimeDirectory=sshd` removed the shared /run/sshd).
install_mgmt_watchdog
# H1: dedicated felhom-sshd OOB instance + static belt (gated by --enable-oob).
install_oob
_state_mark agent_install
}
# install_mgmt_watchdog fetches + installs the G1 break-glass host artifacts (idempotent; enables the
# timer). Split out for readability; called from step_agent_install. Every unit is RuntimeDirectory-
# guarded (trap 2). Non-fatal on a repo that predates the artifacts.
install_mgmt_watchdog() {
if $DRY_RUN; then
log_dry "fetch configs/felhom-privsep.tmpfiles -> /etc/tmpfiles.d/felhom-privsep.conf ; systemd-tmpfiles --create"
log_dry "fetch configs/felhom-mgmt-watchdog.sh -> /usr/local/sbin/felhom-mgmt-watchdog (0755)"
log_dry "fetch configs/felhom-mgmt-watchdog.{service,timer} -> /etc/systemd/system/ ; enable --now felhom-mgmt-watchdog.timer"
return 0
fi
local wdtmp; wdtmp=$(mktemp -t felhom-mgmt-wd.XXXXXX)
if ! fetch_raw "configs/felhom-mgmt-watchdog.sh" "$wdtmp" 2>/dev/null; then
log_skip " mgmt-watchdog artifacts not in the agent repo yet — break-glass auto-heal stays manual"
rm -f "$wdtmp"; return 0
fi
sh -n "$wdtmp" || { rm -f "$wdtmp"; die "fetched felhom-mgmt-watchdog.sh failed sh -n — refusing to install"; }
install -m 0755 -o root -g root "$wdtmp" /usr/local/sbin/felhom-mgmt-watchdog
rm -f "$wdtmp"
# tmpfiles (layer 1) — install + create now so /run/sshd is guaranteed present immediately.
local tftmp; tftmp=$(mktemp -t felhom-privsep.XXXXXX)
fetch_raw "configs/felhom-privsep.tmpfiles" "$tftmp"
install -m 0644 -o root -g root "$tftmp" /etc/tmpfiles.d/felhom-privsep.conf
rm -f "$tftmp"
systemd-tmpfiles --create /etc/tmpfiles.d/felhom-privsep.conf 2>/dev/null || true
# units (layer 2) — RuntimeDirectory guard on BOTH before install (trap 2 / the incident cause).
local svctmp tmrtmp; svctmp=$(mktemp -t felhom-wd-svc.XXXXXX); tmrtmp=$(mktemp -t felhom-wd-tmr.XXXXXX)
fetch_raw "configs/felhom-mgmt-watchdog.service" "$svctmp"
fetch_raw "configs/felhom-mgmt-watchdog.timer" "$tmrtmp"
if grep -qiE '^[[:space:]]*RuntimeDirectory[[:space:]]*=' "$svctmp" "$tmrtmp"; then
rm -f "$svctmp" "$tmrtmp"
die "mgmt-watchdog unit declares RuntimeDirectory= — that is the incident G1 fixes; refusing to install"
fi
install -m 0644 -o root -g root "$svctmp" /etc/systemd/system/felhom-mgmt-watchdog.service
install -m 0644 -o root -g root "$tmrtmp" /etc/systemd/system/felhom-mgmt-watchdog.timer
rm -f "$svctmp" "$tmrtmp"
systemctl daemon-reload
systemctl enable --now felhom-mgmt-watchdog.timer >/dev/null 2>&1 || true
log_success " installed break-glass layers 1+2 (tmpfiles /run/sshd + agent-independent watchdog timer)"
}
# install_oob installs the dedicated felhom-sshd OOB instance + the static nft belt (TASK H1). The
# STATIC parts land here (unit, host key, felhom-op user + sudoers, belt table + loader); the agent
# reconciles the DYNAMIC parts (port claim, config render, authorized_keys, belt set elements) once
# oob.enabled=true. Gated by --enable-oob. Non-fatal if the agent repo predates the artifacts.
# The felhom-sshd unit is RuntimeDirectory-guarded (the G1 incident cause) before install.
install_oob() {
$ENABLE_OOB || { log_skip " OOB (felhom-sshd) not requested (--enable-oob) — skipping"; return 0; }
if $DRY_RUN; then
log_dry "mkdir /etc/felhom-sshd{,/authorized_keys} ; ssh-keygen host key ; useradd felhom-op ; install felhom-op sudoers"
log_dry "fetch felhom-sshd.service (RuntimeDirectory-guarded) + felhom-oob.nft + felhom-oob-nft.service ; enable"
return 0
fi
install -d -o root -g root -m 0755 /etc/felhom-sshd /etc/felhom-sshd/authorized_keys
# dedicated host key (stable across reloads) — generate once.
if [[ ! -f /etc/felhom-sshd/ssh_host_ed25519_key ]]; then
ssh-keygen -t ed25519 -N "" -f /etc/felhom-sshd/ssh_host_ed25519_key -C felhom-sshd-hostkey -q
chmod 600 /etc/felhom-sshd/ssh_host_ed25519_key
fi
# operator login user (no ambient privilege; escalates only via the felhom-op sudoers verbs).
id felhom-op >/dev/null 2>&1 || useradd --create-home --shell /bin/bash felhom-op
# felhom-op scoped sudoers (visudo-validated before install).
local optmp; optmp=$(mktemp -t felhom-op-sudoers.XXXXXX)
if fetch_raw "configs/felhom-op.sudoers" "$optmp" 2>/dev/null; then
"$VISUDO" -cf "$optmp" >/dev/null || { rm -f "$optmp"; die "fetched felhom-op sudoers failed visudo -cf"; }
install -m 0440 -o root -g root "$optmp" /etc/sudoers.d/felhom-op
fi
rm -f "$optmp"
# felhom-sshd unit — RuntimeDirectory guard (the G1 incident cause) BEFORE install.
local sutmp; sutmp=$(mktemp -t felhom-sshd-unit.XXXXXX)
if ! fetch_raw "configs/felhom-sshd.service" "$sutmp" 2>/dev/null; then
log_skip " felhom-sshd.service not in the agent repo yet — OOB stays unconfigured"
rm -f "$sutmp"; return 0
fi
if grep -qiE '^[[:space:]]*RuntimeDirectory[[:space:]]*=' "$sutmp"; then
rm -f "$sutmp"; die "felhom-sshd unit declares RuntimeDirectory= — the SPIKE-felhom-sshd §8 incident cause; refusing"
fi
install -m 0644 -o root -g root "$sutmp" /etc/systemd/system/felhom-sshd.service
rm -f "$sutmp"
# static belt table + boot loader.
local ntmp utmp; ntmp=$(mktemp -t felhom-oob-nft.XXXXXX); utmp=$(mktemp -t felhom-oob-unit.XXXXXX)
fetch_raw "configs/felhom-oob.nft" "$ntmp"
fetch_raw "configs/felhom-oob-nft.service" "$utmp"
nft -c -f "$ntmp" >/dev/null 2>&1 || { rm -f "$ntmp" "$utmp"; die "felhom-oob.nft failed nft -c — refusing"; }
install -m 0644 -o root -g root "$ntmp" /etc/felhom-oob.nft
install -m 0644 -o root -g root "$utmp" /etc/systemd/system/felhom-oob-nft.service
rm -f "$ntmp" "$utmp"
systemctl daemon-reload
systemctl enable --now felhom-oob-nft.service >/dev/null 2>&1 || true # load the static belt now
systemctl enable felhom-sshd >/dev/null 2>&1 || true # NOT start — the agent renders the config first
log_success " installed OOB felhom-sshd instance + static belt (agent renders config + fills sets once oob.enabled)"
}
#-------------------------------------------------------------------------------
# STEP 6 — write agent config + ensure service healthy
#-------------------------------------------------------------------------------
step_agent_config() {
log_step "6/8 agent config + service"
# TLS pin: the SERVED leaf cert fingerprint (not pvesh node info — may differ)
local fp
fp=$(echo | openssl s_client -connect 127.0.0.1:8006 2>/dev/null | openssl x509 -noout -fingerprint -sha256 2>/dev/null | sed 's/.*=//')
[[ -n "$fp" ]] || log_warn " could not compute TLS fingerprint (leaving empty — agent will use system trust)"
# bridge / local-api addr
if [[ -z "$BRIDGE_ADDR" ]]; then
local ip; ip=$(ip -4 -o addr show vmbr0 2>/dev/null | awk '{print $4}' | cut -d/ -f1 | head -1)
BRIDGE_ADDR="${ip:-127.0.0.1}:8443"
elif [[ "$BRIDGE_ADDR" != *:* ]]; then
BRIDGE_ADDR="${BRIDGE_ADDR}:8443"
fi
log_info " node=$NODE local_api=$BRIDGE_ADDR tls_fp=${fp:0:17}…"
if $DRY_RUN; then
log_dry "write $AGENT_CONFIG (0600): proxmox{endpoint,node=$NODE,token=<secret>,tls.fingerprint=$fp} hub{url=$HUB_URL,host_id=$HOST_ID,api_key=<secret>} local_api{$BRIDGE_ADDR}"
log_dry "systemctl restart felhom-agent && felhom-agent --config $AGENT_CONFIG --selftest"
_state_mark agent_config; return 0
fi
mkdir -p "$(dirname "$AGENT_CONFIG")"
# Build config: optional preserve base + fresh-host defaults + Day-0 overrides.
# Secrets passed via env (NOT argv) to avoid ps exposure.
PVE_TOKEN="$PVE_TOKEN" HOST_API_KEY="$HOST_API_KEY" \
NODE="$NODE" FP="$fp" HUB_URL="$HUB_URL" HOST_ID="$HOST_ID" BRIDGE_ADDR="$BRIDGE_ADDR" \
PRESERVE_FROM="$PRESERVE_FROM" OUT="$AGENT_CONFIG" python3 <<'PY'
import json, os
out = os.environ['OUT']
base = {}
pf = os.environ.get('PRESERVE_FROM','')
if pf and os.path.exists(pf):
try: base = json.load(open(pf))
except Exception: base = {}
# fresh-host defaults for any section not preserved
base.setdefault('log_level','info')
# privileged.mode = "sudo": the canonical unit runs the agent as the NON-root felhom-agent user, so
# every host-root op goes through `sudo -n` against /etc/sudoers.d/felhom-agent. ("direct" was the old
# dev/CI shortcut for a root agent.) Force the mode authoritative (a stale preserved "direct" config
# would otherwise break the non-root daemon); the binary paths MUST match the sudoers allowlist.
base.setdefault('privileged', {})
base['privileged']['mode'] = 'sudo'
base['privileged'].setdefault('sudo_path','sudo')
for _k,_v in {"unit_dir":"/etc/systemd/system","stage_dir":"/var/lib/felhom-agent/units","systemctl":"/usr/bin/systemctl","install":"/usr/bin/install","smartctl":"/usr/sbin/smartctl","lvs":"/usr/sbin/lvs"}.items():
base['privileged'].setdefault(_k,_v)
base.setdefault('storage', {"watchdog_interval_seconds":5,"watchdog_debounce_seconds":15,"known_refresh_seconds":20})
base.setdefault('backup', {"local_backup_target":"local","local_backup_retention":3,"restore_storage":"local-lvm","restore_test_cadence_seconds":0,"scratch_vmid_min":990000,"scratch_vmid_max":990009,"pbs_secret_dir":"/etc/pve/priv/storage","backup_cadence_seconds":0})
base.setdefault('local_api', {})
base['local_api'].setdefault('enable', True)
base['local_api']['listen_addr'] = os.environ['BRIDGE_ADDR']
base['local_api'].setdefault('cert_file','/var/lib/felhom-agent/local-api.crt')
base['local_api'].setdefault('key_file','/var/lib/felhom-agent/local-api.key')
base['local_api'].setdefault('token_store','/var/lib/felhom-agent/local-tokens.log')
base.setdefault('lan_resolver', {"enable": True})
# Day-0 overrides (always authoritative)
base['proxmox'] = {
"endpoint":"https://127.0.0.1:8006",
"node": os.environ['NODE'],
"token": os.environ['PVE_TOKEN'],
"tls": {"fingerprint": os.environ['FP'], "insecure_skip_verify": False},
}
base['hub'] = {
"url": os.environ['HUB_URL'],
"host_id": os.environ['HOST_ID'],
"api_key": os.environ['HOST_API_KEY'],
"poll_seconds": base.get('hub',{}).get('poll_seconds',900),
"timeout_seconds": base.get('hub',{}).get('timeout_seconds',30),
}
fd = os.open(out, os.O_WRONLY|os.O_CREAT|os.O_TRUNC, 0o600)
with os.fdopen(fd,'w') as f:
json.dump(base, f, indent=2); f.write('\n')
PY
# The non-root felhom-agent daemon must READ this config (token + hub api_key live here). Own it by
# the service user, 0600 (root still reads it for the provision one-shot).
chown "${AGENT_USER}:${AGENT_USER}" "$AGENT_CONFIG" 2>/dev/null || chmod 600 "$AGENT_CONFIG"
chmod 600 "$AGENT_CONFIG"
log_success " wrote $AGENT_CONFIG (0600 ${AGENT_USER})"
# health: read-only selftest (proxmox) must pass before provisioning
if ! felhom-agent --config "$AGENT_CONFIG" --selftest >/dev/null 2>&1; then
felhom-agent --config "$AGENT_CONFIG" --selftest 2>&1 | tail -20 >&2
die "agent --selftest FAILED with the new config (token/ACL/TLS problem) — fix before provisioning"
fi
log_success " agent --selftest (read-only) passed"
# start the daemon (host-report loop) as the felhom-agent user and confirm it stays up. is-active is
# the real proof the NON-root user can read the 0600 config (the root selftest above can't show that).
if systemctl list-unit-files felhom-agent.service >/dev/null 2>&1; then
run systemctl enable felhom-agent >/dev/null 2>&1 || true
run systemctl restart felhom-agent
if ! $DRY_RUN; then
sleep 3
if systemctl is-active --quiet felhom-agent; then
log_success " felhom-agent service active (non-root $AGENT_USER reads the config OK)"
else
systemctl status felhom-agent --no-pager -l 2>&1 | tail -20 >&2
journalctl -u felhom-agent -n 20 --no-pager 2>&1 | tail -20 >&2
die "felhom-agent did not stay active after restart — see status/journal above"
fi
fi
else
log_warn " no felhom-agent systemd unit — daemon host-report loop not started (provision one-shot still works)"
fi
_state_mark agent_config
}
#-------------------------------------------------------------------------------
# STEP 7 — golden: ensure a restorable golden archive (local else Gitea-fetched + verified)
#-------------------------------------------------------------------------------
# Local auto-discovery is the default + fallback. When no local golden exists (or --force-gitea-golden),
# fetch the golden from Gitea (git token), VERIFY its sha256 against the hub manifest, and import it
# into the archive storage's dump dir under a valid vzdump name so the provision restore can use it.
step_golden() {
log_step "7/8 golden archive"
if [[ -n "$GOLDEN_VOLID" ]] && ! $FORCE_GITEA_GOLDEN; then
log_skip " using local golden: $GOLDEN_VOLID"
_state_mark golden; return 0
fi
# Need the manifest + git creds (already resolved in step 5, but re-resolve on a fresh --resume run).
[[ -n "$ART_GOLDEN_VER" ]] || resolve_artifacts
[[ -n "$GIT_TOKEN" ]] || resolve_git_creds
[[ -n "$ART_GOLDEN_VER" && -n "$ART_GOLDEN_SHA" ]] || die "hub manifest has no golden version/sha256 — set it in the operator UI, or pass --golden VOLID"
local url="$GITEA_BASE/api/packages/$GITEA_OWNER/generic/felhom-golden/$ART_GOLDEN_VER/golden.tar.zst"
if $DRY_RUN; then
log_dry "curl -u <git> -o <dump>/vzdump-lxc-${GOLDEN_VMID}-<ts>.tar.zst $url ; verify sha256=$ART_GOLDEN_SHA ; set GOLDEN_VOLID"
GOLDEN_VOLID="${ARCHIVE_STORAGE}:backup/vzdump-lxc-${GOLDEN_VMID}-<dry-run>.tar.zst"
_state_mark golden; return 0
fi
# Resolve the archive storage's dump dir (pvesm path maps a volid → fs path without needing it to exist).
local dump_dir fname dest
dump_dir=$(dirname "$(pvesm path "${ARCHIVE_STORAGE}:backup/vzdump-lxc-${GOLDEN_VMID}-2000_01_01-00_00_00.tar.zst" 2>/dev/null)")
[[ -d "$dump_dir" ]] || die "could not resolve dump dir for storage $ARCHIVE_STORAGE (got '$dump_dir')"
fname="vzdump-lxc-${GOLDEN_VMID}-$(date +%Y_%m_%d-%H_%M_%S).tar.zst"
dest="${dump_dir}/${fname}"
log_info " fetching golden v$ART_GOLDEN_VER from Gitea → $dest"
fetch_verify "$url" "$dest" "$ART_GOLDEN_SHA"
GOLDEN_VOLID="${ARCHIVE_STORAGE}:backup/${fname}"
pvesm list "$ARCHIVE_STORAGE" --content backup 2>/dev/null | grep -q "$fname" \
|| log_warn " imported golden not yet listed by pvesm (continuing — restore uses the volid directly)"
log_success " golden imported + verified: $GOLDEN_VOLID"
_state_mark golden
}
#-------------------------------------------------------------------------------
# STEP 8 — provision (golden restore -> resize -> bootstrap.json -> onboot:1)
#-------------------------------------------------------------------------------
step_provision() {
log_step "8/8 provision guest $VMID"
# NOTE: -hub-password is passed on argv (the agent's only input for it) — briefly
# visible in ps. Tracked as an Observation (candidate: env/stdin in the agent).
# Optional operator CPU/RAM cap — passed to the agent ONLY when set (an agent < v0.52.0 would
# reject the unknown flag and die; opt-in means no one hits that until they intentionally cap).
local -a cap_args=()
[[ -n "$CPU_CORES" ]] && cap_args+=(-cores "$CPU_CORES")
[[ -n "$MEM_MIB" ]] && cap_args+=(-memory "$MEM_MIB")
# felhom pool: ensure it exists before the restore (step_token already created it; this is a
# belt-and-suspenders no-op that also covers a --resume path). The AGENT adds the guest to the pool
# atomically via restore --pool (v0.53.0) — no separate script-side pool_add_guest.
ensure_felhom_pool
if $DRY_RUN; then
log_dry "felhom-agent --config $AGENT_CONFIG --selftest=provision -archive $GOLDEN_VOLID -vmid $VMID -customer-id $CUSTOMER_ID -hub-password <pass> -rootfs-grow $ROOTFS_GROW -datavol-grow $DATAVOL_GROW -sysdata-grow $SYSDATA_GROW ${cap_args[*]} # agent restores INTO pool $PVE_POOL"
log_dry "record provisioned_vmid=$VMID in $STATE_FILE (for a later automatic --uninstall)"
_state_mark provision; return 0
fi
if ! felhom-agent --config "$AGENT_CONFIG" --selftest=provision \
-archive "$GOLDEN_VOLID" -vmid "$VMID" \
-customer-id "$CUSTOMER_ID" -hub-password "$PASSPHRASE" \
-rootfs-grow "$ROOTFS_GROW" -datavol-grow "$DATAVOL_GROW" -sysdata-grow "$SYSDATA_GROW" \
"${cap_args[@]}"; then
die "provision FAILED — see the agent error above. Fix and re-run with --resume."
fi
log_success " provision completed"
_state_mark provision
# Record the provisioned vmid so a later --uninstall resolves the target automatically + safely.
_state_put provisioned_vmid "$VMID"
# (No pool_add_guest here — the agent's restore --pool already made the guest a member.)
# Reboot the guest ONCE: the golden's controller-bootstrap unit evaluates its
# ConditionPathExists=/etc/felhom-bootstrap/bootstrap.json at BOOT, and the back-half attaches
# the bootstrap mount to the ALREADY-RUNNING guest — without a reboot the unit stays skipped and
# the controller never deploys (drill finding R6; the agent's own provision output says
# "next: reboot the guest"). On fast hosts the first boot sometimes wins the race — the reboot
# is idempotent either way (the unit no-ops when the controller already runs).
log_info " rebooting guest $VMID so the baked controller-bootstrap unit picks up the mount"
run pct reboot "$VMID"
}
#-------------------------------------------------------------------------------
# STEP 7 — verify
#-------------------------------------------------------------------------------
step_verify() {
log_step "verify"
if $DRY_RUN; then log_dry "pct status/config $VMID; docker ps in-guest; host-report includes $VMID"; return 0; fi
local ok=true
local st; st=$(pct status "$VMID" 2>/dev/null | awk '{print $2}')
[[ "$st" == "running" ]] && log_success " pct status: running" || { log_error " pct status: $st"; ok=false; }
if pct config "$VMID" 2>/dev/null | grep -q '^onboot: 1'; then log_success " onboot: 1"; else log_error " onboot NOT 1"; ok=false; fi
pct config "$VMID" 2>/dev/null | grep -E '^(rootfs|mp0|mp1|mp8):' | sed 's/^/ /'
# controller container healthy in-guest — bounded wait (the post-provision reboot + docker start
# take a while, especially on modest hardware; drill R6 re-verify)
local cstat="" _waited=0
while [[ -z "$cstat" && $_waited -lt 180 ]]; do
cstat=$(pct exec "$VMID" -- docker ps --filter name=felhom-controller --format '{{.Status}}' 2>/dev/null | head -1)
[[ -n "$cstat" ]] || { sleep 5; _waited=$((_waited+5)); }
done
if [[ -n "$cstat" ]]; then log_success " controller: $cstat (after ~${_waited}s)"; else log_warn " controller container not visible after ${_waited}s — check 'pct exec $VMID -- journalctl -u felhom-controller-bootstrap'"; fi
local cver; cver=$(pct exec "$VMID" -- docker ps --filter name=felhom-controller --format '{{.Image}}' 2>/dev/null | head -1)
[[ -n "$cver" ]] && log_info " controller image: $cver"
# tunnel
local tun; tun=$(pct exec "$VMID" -- docker ps --filter name=cloudflared --format '{{.Status}}' 2>/dev/null | head -1)
[[ -n "$tun" ]] && log_info " cloudflared: $tun" || log_warn " cloudflared not visible yet"
# host-report includes the guest (best-effort via the agent's hub selftest)
log_info " (confirm in the hub UI that host $HOST_ID reports guest $VMID)"
_state_mark verify
echo ""
if $ok; then
log_success "Day-0 provision SUCCESS — vmid=$VMID host_id=$HOST_ID customer=$CUSTOMER_ID golden=$GOLDEN_VOLID"
else
log_warn "Day-0 provision completed WITH WARNINGS — review the checks above"
fi
}
#-------------------------------------------------------------------------------
# verify (agent-only, for --skip-provision): the agent is installed, runs non-root, and reports.
#-------------------------------------------------------------------------------
step_verify_agent() {
log_step "verify (agent only)"
if $DRY_RUN; then log_dry "felhom-agent --version; systemctl is-active felhom-agent; --selftest=hub (one collect+report)"; return 0; fi
local ok=true
log_info " binary: $("$AGENT_BIN" --version 2>&1 | head -1)"
log_info " runs as: $(systemctl show felhom-agent -p User --value 2>/dev/null) (want $AGENT_USER)"
if systemctl is-active --quiet felhom-agent; then log_success " service active"; else log_error " service NOT active"; ok=false; fi
# one explicit collect+report to prove the hub link end-to-end (host-report lands).
if felhom-agent --config "$AGENT_CONFIG" --selftest=hub >/dev/null 2>&1; then
log_success " --selftest=hub OK (a host-report reached the hub)"
else
log_warn " --selftest=hub did not confirm (the daemon loop still reports every poll_seconds)"
fi
_state_mark verify
echo ""
if $ok; then
log_success "Agent install SUCCESS — $("$AGENT_BIN" --version 2>&1 | head -1) as $AGENT_USER, host_id=$HOST_ID customer=$CUSTOMER_ID"
else
log_warn "Agent install completed WITH WARNINGS — review the checks above"
fi
}
#-------------------------------------------------------------------------------
# Main
#-------------------------------------------------------------------------------
trap 'PASSPHRASE=""; PVE_TOKEN=""; HOST_API_KEY=""; GIT_TOKEN=""' EXIT
if $RESUME && _state_has preflight; then
# still need the passphrase for enroll/provision even on resume
read_passphrase
# re-resolve cheap derived values skipped steps would have set
[[ -n "$NODE" ]] || NODE=$(pvesh get /nodes --output-format json 2>/dev/null | python3 -c "import json,sys;print(json.load(sys.stdin)[0]['node'])" 2>/dev/null || hostname)
if [[ -z "$AGENT_CONFIG" ]] && systemctl cat felhom-agent >/dev/null 2>&1; then
AGENT_CONFIG=$(systemctl cat felhom-agent 2>/dev/null | grep -oP '(?<=-config )\S+' | head -1)
fi
[[ -n "$AGENT_CONFIG" ]] || AGENT_CONFIG="/etc/felhom-agent/agent.json"
# Backfill display values from the already-written config so the summary is complete.
[[ -f "$AGENT_CONFIG" ]] && HOST_ID=$(python3 -c "import json;print(json.load(open('$AGENT_CONFIG')).get('hub',{}).get('host_id',''))" 2>/dev/null || true)
log_skip "pre-flight (resumed)"
else
step_preflight
fi
should_skip token || step_token
should_skip grows || step_grows
should_skip enroll || step_enroll
should_skip break_glass || step_break_glass
should_skip agent_install || step_agent_install
should_skip agent_config || step_agent_config
should_skip golden || step_golden
if $SKIP_PROVISION; then
log_skip "provision (--skip-provision) — agent install/config verified only"
step_verify_agent
else
should_skip provision || step_provision
step_verify
fi
Reference in New Issue View Git Blame Copy Permalink