veza/scripts/bootstrap/bootstrap-local.sh

#!/usr/bin/env bash
# bootstrap-local.sh — drive bootstrap from the operator's workstation.
#
# Phases (each idempotent ; skipped if state file marks DONE) :
#   1. preflight        — required tools, SSH to R720, DNS resolution
#   2. vault            — render + encrypt group_vars/all/vault.yml,
#                         write .vault-pass
#   3. forgejo          — set repo Secrets / Variables via Forgejo API
#   4. r720             — invoke bootstrap-remote.sh over SSH
#   5. haproxy          — ansible-playbook playbooks/haproxy.yml,
#                         verify Let's Encrypt certs land
#   6. summary          — final readiness report
#
# Resumable :
#   PHASE=4 ./bootstrap-local.sh    # restart at phase 4
#
# Inputs (env vars ; can be set in your shell or in scripts/bootstrap/.env) :
#   R720_HOST                 ssh target (default: 10.0.20.150)
#   R720_USER                 ssh user (default: ansible)
#   FORGEJO_API_URL           default: https://forgejo.talas.group
#                             override with http://10.0.20.105:3000 if no DNS yet
#   FORGEJO_OWNER             default: talas
#   FORGEJO_REPO              default: veza
#   FORGEJO_ADMIN_TOKEN       MANDATORY (Forgejo UI → Settings → Applications)
#   ALREADY_PUSHED            set to "1" if origin/main already has the
#                             current HEAD ; skips the auto-push prompt

set -Eeuo pipefail
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
# shellcheck source=lib.sh
. "$SCRIPT_DIR/lib.sh"
trap_errors

# Optional .env in the bootstrap dir for non-secret defaults.
[[ -f "$SCRIPT_DIR/.env" ]] && . "$SCRIPT_DIR/.env"

: "${R720_HOST:=10.0.20.150}"
: "${R720_USER:=ansible}"
: "${FORGEJO_API_URL:=https://forgejo.talas.group}"
: "${FORGEJO_OWNER:=talas}"
: "${FORGEJO_REPO:=veza}"

REPO_ROOT=$(git -C "$SCRIPT_DIR" rev-parse --show-toplevel 2>/dev/null) \
    || die "not in a git repo (or git missing)"

VAULT_YML="$REPO_ROOT/infra/ansible/group_vars/all/vault.yml"
VAULT_EXAMPLE="$REPO_ROOT/infra/ansible/group_vars/all/vault.yml.example"
VAULT_PASS="$REPO_ROOT/infra/ansible/.vault-pass"

# State file lives under the repo so the local script doesn't need root.
TALAS_STATE_DIR="$REPO_ROOT/.git/talas-bootstrap"
TALAS_STATE_FILE="$TALAS_STATE_DIR/local.state"

# ============================================================================
# Phase 1 — preflight
# ============================================================================
phase_1_preflight() {
    section "Phase 1 — Preflight"
    _current_phase=preflight
    phase preflight START

    skip_if_done preflight "preflight" && { phase preflight DONE; return 0; }

    require_cmd git ansible ansible-vault dig curl ssh openssl base64 jq
    require_file "$VAULT_EXAMPLE"
    require_file "$REPO_ROOT/infra/ansible/playbooks/haproxy.yml"
    require_file "$REPO_ROOT/infra/ansible/inventory/staging.yml"

    info "Testing SSH to $R720_USER@$R720_HOST…"
    if ! ssh -o ConnectTimeout=5 -o BatchMode=yes "$R720_USER@$R720_HOST" /bin/true 2>/dev/null; then
        TALAS_HINT="ensure your ssh key is in $R720_USER@$R720_HOST:~/.ssh/authorized_keys, then try ssh $R720_USER@$R720_HOST"
        die "SSH to $R720_USER@$R720_HOST failed"
    fi
    ok "SSH OK"

    info "Checking that incus is reachable on R720…"
    if ! ssh "$R720_USER@$R720_HOST" "command -v incus >/dev/null && incus list >/dev/null 2>&1"; then
        TALAS_HINT="run 'incus list' as $R720_USER on $R720_HOST manually ; verify the user is in the 'incus-admin' group"
        die "incus on $R720_HOST not accessible by $R720_USER"
    fi
    ok "incus reachable"

    info "Checking DNS resolution for the public domains…"
    local missing_dns=()
    for d in veza.fr staging.veza.fr talas.fr forgejo.talas.group; do
        if ! dig +short +time=2 +tries=1 "$d" @1.1.1.1 2>/dev/null | grep -qE '^[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+$'; then
            missing_dns+=("$d")
        fi
    done
    if (( ${#missing_dns[@]} > 0 )); then
        warn "DNS not resolved for: ${missing_dns[*]}"
        warn "Let's Encrypt (phase 5) will fail for those domains. Configure DNS first or expect partial cert issuance."
    else
        ok "all 4 public domains resolve"
    fi

    mark_done preflight
    phase preflight DONE
}

# ============================================================================
# Phase 2 — vault
# ============================================================================
phase_2_vault() {
    section "Phase 2 — Local vault"
    _current_phase=vault
    phase vault START

    if skip_if_done vault "vault setup"; then
        phase vault DONE; return 0
    fi

    if [[ -f "$VAULT_YML" ]] && head -1 "$VAULT_YML" 2>/dev/null | grep -q '^\$ANSIBLE_VAULT'; then
        info "vault.yml already encrypted — verifying password works"
        [[ -f "$VAULT_PASS" ]] || die "vault.yml encrypted but $VAULT_PASS missing — re-create it manually"
    elif [[ -f "$VAULT_YML" ]]; then
        warn "vault.yml exists in PLAINTEXT — will encrypt now"
    else
        info "rendering vault.yml from example"
        cp "$VAULT_EXAMPLE" "$VAULT_YML"
        warn "edit $VAULT_YML now to fill in <TODO> placeholders"
        warn "(JWT keys are auto-generated below if you leave their <TODO> values)"
        prompt_value _ "Press Enter when done editing"
        # Auto-fill JWT keys if user left the TODO placeholders
        if grep -q '<TODO: base64 of RS256 private PEM>' "$VAULT_YML"; then
            info "generating RS256 JWT keypair"
            local jwt_priv jwt_pub
            jwt_priv=$(openssl genrsa 4096 2>/dev/null | base64 -w0)
            jwt_pub=$(echo "$jwt_priv" | base64 -d | openssl rsa -pubout 2>/dev/null | base64 -w0)
            sed -i "s|<TODO: base64 of RS256 private PEM>|$jwt_priv|" "$VAULT_YML"
            sed -i "s|<TODO: base64 of RS256 public PEM>|$jwt_pub|" "$VAULT_YML"
            ok "JWT keys generated and inserted"
        fi
        if grep -qE '<TODO' "$VAULT_YML"; then
            local remaining
            remaining=$(grep -cE '<TODO' "$VAULT_YML")
            die "$remaining <TODO> placeholders still in $VAULT_YML — fill them and rerun PHASE=2 ./bootstrap-local.sh"
        fi
    fi

    if [[ ! -f "$VAULT_PASS" ]]; then
        local pw=""
        prompt_password pw "choose a vault password (memorize it !)"
        echo "$pw" > "$VAULT_PASS"
        chmod 0400 "$VAULT_PASS"
        ok "wrote $VAULT_PASS"
        # If vault.yml is plaintext, encrypt now.
        if ! head -1 "$VAULT_YML" | grep -q '^\$ANSIBLE_VAULT'; then
            info "encrypting vault.yml"
            ansible-vault encrypt --vault-password-file "$VAULT_PASS" "$VAULT_YML"
            ok "encrypted"
        fi
    fi

    info "verifying we can decrypt"
    if ! ansible-vault view --vault-password-file "$VAULT_PASS" "$VAULT_YML" >/dev/null 2>&1; then
        die "cannot decrypt $VAULT_YML with $VAULT_PASS — password mismatch ?"
    fi
    ok "vault decryption verified"

    mark_done vault
    phase vault DONE
}

# ============================================================================
# Phase 3 — Forgejo Secrets + Variables
# ============================================================================
phase_3_forgejo() {
    section "Phase 3 — Forgejo Secrets + Variables"
    _current_phase=forgejo
    phase forgejo START

    if skip_if_done forgejo "Forgejo provisioning"; then
        phase forgejo DONE; return 0
    fi

    require_env FORGEJO_ADMIN_TOKEN \
        "create at $FORGEJO_API_URL/-/user/settings/applications (scopes: write:admin, write:repository, write:package)"

    info "checking Forgejo API reachability"
    if ! curl -fsSL --max-time 10 \
            -H "Authorization: token $FORGEJO_ADMIN_TOKEN" \
            "$FORGEJO_API_URL/api/v1/user" >/dev/null 2>&1; then
        TALAS_HINT="check FORGEJO_API_URL ($FORGEJO_API_URL) ; if no DNS yet, try FORGEJO_API_URL=http://10.0.20.105:3000"
        die "Forgejo API unreachable or token invalid"
    fi
    ok "Forgejo API reachable, token valid"

    info "checking repo $FORGEJO_OWNER/$FORGEJO_REPO exists"
    if ! forgejo_api GET "/repos/$FORGEJO_OWNER/$FORGEJO_REPO" >/dev/null 2>&1; then
        TALAS_HINT="set FORGEJO_OWNER + FORGEJO_REPO env vars (currently $FORGEJO_OWNER/$FORGEJO_REPO)"
        die "repo $FORGEJO_OWNER/$FORGEJO_REPO not found"
    fi

    # Create a long-lived registry token via the API.
    info "creating a registry token (write:package)"
    local registry_token
    registry_token=$(forgejo_api POST "/users/$FORGEJO_OWNER/tokens" \
            --data "$(jq -nc --arg n "veza-deploy-registry-$(date +%s)" \
                                --argjson s '["write:package", "read:package"]' \
                                '{name: $n, scopes: $s}')" \
            | jq -er '.sha1 // empty') \
        || die "could not create registry token via API ; create one manually at $FORGEJO_API_URL/-/user/settings/applications and re-run with FORGEJO_REGISTRY_TOKEN env var set"

    forgejo_set_secret "$FORGEJO_OWNER" "$FORGEJO_REPO" FORGEJO_REGISTRY_TOKEN "$registry_token"
    forgejo_set_secret "$FORGEJO_OWNER" "$FORGEJO_REPO" ANSIBLE_VAULT_PASSWORD "$(cat "$VAULT_PASS")"
    forgejo_set_var "$FORGEJO_OWNER" "$FORGEJO_REPO" FORGEJO_REGISTRY_URL \
        "$FORGEJO_API_URL/api/packages/$FORGEJO_OWNER/generic"

    mark_done forgejo
    phase forgejo DONE
}

# ============================================================================
# Phase 4 — R720 remote bootstrap
# ============================================================================
phase_4_r720() {
    section "Phase 4 — R720 remote bootstrap (Incus profiles + runner labels)"
    _current_phase=r720
    phase r720 START

    if skip_if_done r720 "R720 remote bootstrap"; then
        phase r720 DONE; return 0
    fi

    require_env FORGEJO_ADMIN_TOKEN
    info "fetching a runner registration token from Forgejo"
    local reg_token
    reg_token=$(forgejo_get_runner_token "$FORGEJO_OWNER" "$FORGEJO_REPO") \
        || die "could not fetch runner registration token"
    info "got registration token (${#reg_token} chars)"

    local remote_script="$SCRIPT_DIR/bootstrap-remote.sh"
    local remote_lib="$SCRIPT_DIR/lib.sh"
    require_file "$remote_script"
    require_file "$remote_lib"

    info "streaming bootstrap-remote.sh over SSH (logs to /var/log/talas-bootstrap.log on R720)"
    # Concatenate lib.sh + remote script so the remote bash sees both.
    {
        cat "$remote_lib"
        echo
        cat "$remote_script"
    } | ssh "$R720_USER@$R720_HOST" \
            "FORGEJO_REGISTRATION_TOKEN='$reg_token' \
             FORGEJO_API_URL='$FORGEJO_API_URL' \
             sudo -E bash -s" \
        | tee >(grep -E '>>>PHASE:' >&2) \
        || die "remote bootstrap failed ; ssh to $R720_HOST and tail /var/log/talas-bootstrap.log"

    mark_done r720
    phase r720 DONE
}

# ============================================================================
# Phase 5 — Edge HAProxy + Let's Encrypt
# ============================================================================
phase_5_haproxy() {
    section "Phase 5 — Edge HAProxy + Let's Encrypt certs"
    _current_phase=haproxy
    phase haproxy START

    if skip_if_done haproxy "haproxy + LE"; then
        phase haproxy DONE; return 0
    fi

    cd "$REPO_ROOT/infra/ansible"
    info "running ansible-playbook playbooks/haproxy.yml (5–10 min)"
    if ! ansible-playbook -i inventory/staging.yml playbooks/haproxy.yml \
            --vault-password-file .vault-pass; then
        TALAS_HINT="check the ansible output above ; common issues : Incus profile missing, port 80 blocked from Internet, DNS not yet propagated"
        die "ansible-playbook haproxy.yml failed"
    fi

    info "verifying Let's Encrypt certs landed"
    local certs
    certs=$(ssh "$R720_USER@$R720_HOST" "incus exec veza-haproxy -- ls /usr/local/etc/tls/haproxy/ 2>/dev/null" || true)
    if [[ -z "$certs" ]]; then
        warn "no certs found in /usr/local/etc/tls/haproxy/ on veza-haproxy"
        warn "check /var/log/letsencrypt or run again — dehydrated retries on next playbook run"
        return 1
    fi
    ok "certs : $(echo "$certs" | tr '\n' ' ')"

    mark_done haproxy
    phase haproxy DONE
}

# ============================================================================
# Phase 6 — Summary
# ============================================================================
phase_6_summary() {
    section "Phase 6 — Summary"
    _current_phase=summary
    phase summary START

    cat <<EOF >&2

  ${_GREEN}${_BOLD}✓ Bootstrap complete.${_RESET}

  What works now :
    • Forgejo registry has the deploy secrets + variable.
    • forgejo-runner has the 'incus' label and Incus socket access.
    • veza-haproxy edge container is up with Let's Encrypt certs.

  What you can do next :
    1. Trigger a manual deploy via Forgejo Actions UI :
         $FORGEJO_API_URL/$FORGEJO_OWNER/$FORGEJO_REPO/actions
       → "Veza deploy" → "Run workflow" → env=staging.

    2. Once that run is green, re-enable auto-trigger :
         $SCRIPT_DIR/enable-auto-deploy.sh

    3. Verify state any time :
         $SCRIPT_DIR/verify-local.sh
         ssh $R720_USER@$R720_HOST $SCRIPT_DIR/verify-remote.sh

  State file : $TALAS_STATE_FILE
EOF

    mark_done summary
    phase summary DONE
}

# ============================================================================
# main
# ============================================================================
main() {
    local start=${PHASE:-1}
    info "starting at phase $start"

    [[ $start -le 1 ]] && phase_1_preflight
    [[ $start -le 2 ]] && phase_2_vault
    [[ $start -le 3 ]] && phase_3_forgejo
    [[ $start -le 4 ]] && phase_4_r720
    [[ $start -le 5 ]] && phase_5_haproxy
    [[ $start -le 6 ]] && phase_6_summary

    ok "ALL DONE"
}

main "$@"