#!/usr/bin/env bash
# deploy.sh - Deploy the vllmScripts repo to a target and restart its service.
#
# This script implements the second half of the git deployment workflow from
# AGENTS.md. It assumes the local changes are committed and pushed, then:
#   1. Pulls the repo on the target
#   2. Symlinks the systemd unit
#   3. Reloads systemd and restarts the service
#   4. Waits for the health endpoint and reports status
#
# Sudo: set FRANK_SUDO_PW so remote sudo reads the password from stdin
# (`sudo -S`). The passwordless restart helpers installed for the retired
# topology are obsolete and must not be used.
#
# Usage:
#   ./deploy.sh <target> [--dry-run]
#   FRANK_SUDO_PW=... ./deploy.sh <target>
#
# Targets (2026-08-18 topology):
#   dankserver - llama.cpp Qwen3.6-35B-A3B Q6_K_P (frank-default-small.service, port 7770)
#   dankclaw   - CIRU ROCmFPX llama.cpp Qwen3.8-27B (frank-default-large.service, port 52625)
set -euo pipefail

# ---------------------------------------------------------------------------
# Target configuration
# ---------------------------------------------------------------------------
declare -A REMOTE_USER REMOTE_HOST REMOTE_DIR SERVICE SERVICE_HEALTH DROP_CACHES HEALTH_WAIT

REMOTE_USER[dankserver]=dank
REMOTE_HOST[dankserver]=dankserver
REMOTE_DIR[dankserver]="/home/dank/vLLM"
SERVICE[dankserver]="frank-default-small"
SERVICE_HEALTH[dankserver]="http://127.0.0.1:7770/health"
DROP_CACHES[dankserver]=0
# Cold load: --no-mmap reads the 30.6 GB Q6_K_P through RAM (MoE experts on
# CPU); allow 20 minutes.
HEALTH_WAIT[dankserver]=600

REMOTE_USER[dankclaw]=dank
REMOTE_HOST[dankclaw]=dankclaw
REMOTE_DIR[dankclaw]="/home/dank/vllmScripts"
SERVICE[dankclaw]="frank-default-large"
SERVICE_HEALTH[dankclaw]="http://127.0.0.1:52625/health"
DROP_CACHES[dankclaw]=0
# CIRU llama.cpp (ROCm 7.15) loads the v3 five-file payload (GGUF + FFN +
# GDN + Output-K8 .pfs + mmproj, ~36.7 GiB) + MTP draft/Output-K8 proxy and
# initializes PromptForge views; allow 20 minutes.
HEALTH_WAIT[dankclaw]=600

TARGET="${1:-}"
DRY_RUN=0
if [ "${2:-}" = "--dry-run" ]; then
    DRY_RUN=1
fi

# ---------------------------------------------------------------------------
# Validation
# ---------------------------------------------------------------------------
if [ -z "${TARGET:-}" ]; then
    echo "Usage: $0 <dankserver|dankclaw> [--dry-run]"
    exit 1
fi
if [ -z "${REMOTE_HOST[$TARGET]:-}" ]; then
    echo "Unknown target: $TARGET"
    exit 1
fi

# ---------------------------------------------------------------------------
# Sudo wrapper (headless-friendly)
# ---------------------------------------------------------------------------
SUDO_PREFIX="sudo"
if [ -n "${FRANK_SUDO_PW:-}" ]; then
    SUDO_PREFIX="printf '%s\n' '$FRANK_SUDO_PW' | sudo -S"
fi

# ---------------------------------------------------------------------------
# Local checks (pre-flight)
# ---------------------------------------------------------------------------
cd "$(dirname "$0")/.."
if ! git diff --quiet HEAD; then
    echo "FAIL: Local working tree has uncommitted changes."
    echo "Commit or stash them before deploying."
    exit 1
fi
if [ "$(git rev-parse --abbrev-ref HEAD)" != "main" ]; then
    echo "WARN: Not on 'main'; deploying a non-main branch."
fi

echo "=== Deploying to ${TARGET} ==="
echo "  host:    ${REMOTE_HOST[$TARGET]}"
echo "  dir:     ${REMOTE_DIR[$TARGET]}"
echo "  service: ${SERVICE[$TARGET]}"
echo "  health:  ${SERVICE_HEALTH[$TARGET]}"
echo ""

# ---------------------------------------------------------------------------
# Push (unless dry-run)
# ---------------------------------------------------------------------------
if [ "$DRY_RUN" = "1" ]; then
    echo "[dry-run] Would push local main to origin"
    echo "[dry-run] Would SSH to ${REMOTE_HOST[$TARGET]} and git pull"
else
    echo "[1/4] Pushing local main to origin..."
    git push origin main
fi

REMOTE="$(
    printf '%s@%s' "${REMOTE_USER[$TARGET]}" "${REMOTE_HOST[$TARGET]}"
)"

# ---------------------------------------------------------------------------
# Remote: pull + install + restart
# ---------------------------------------------------------------------------
DROP_CACHES_CMD=""
if [ "${DROP_CACHES[$TARGET]}" = "1" ]; then
    DROP_CACHES_CMD="
echo 'Dropping page caches for reliable model load...'
${SUDO_PREFIX} sh -c 'sync; echo 3 > /proc/sys/vm/drop_caches'
"
fi

REMOTE_SCRIPT="
set -euo pipefail
cd '${REMOTE_DIR[$TARGET]}'

echo '[2/4] Pulling repo on ${TARGET}...'
git pull origin main

echo '[3/4] Symlink unit and restart ${SERVICE[$TARGET]}...'
${SUDO_PREFIX} ln -sf '${REMOTE_DIR[$TARGET]}/scripts/${SERVICE[$TARGET]}.service' /etc/systemd/system/${SERVICE[$TARGET]}.service
${DROP_CACHES_CMD}
${SUDO_PREFIX} systemctl daemon-reload
${SUDO_PREFIX} systemctl enable '${SERVICE[$TARGET]}'
${SUDO_PREFIX} systemctl restart '${SERVICE[$TARGET]}'
"

if [ "$DRY_RUN" = "1" ]; then
    echo "[dry-run] Remote commands would run:"
    echo "$REMOTE_SCRIPT"
else
    # shellcheck disable=SC2087
    ssh "$REMOTE" bash -s <<REMOTE_EOF
${REMOTE_SCRIPT}
REMOTE_EOF
fi

# ---------------------------------------------------------------------------
# Health check
# ---------------------------------------------------------------------------
if [ "$DRY_RUN" = "1" ]; then
    echo "[dry-run] Would wait for health at ${SERVICE_HEALTH[$TARGET]}"
else
    echo "[4/4] Waiting for health endpoint ${SERVICE_HEALTH[$TARGET]} (via ssh)..."
    HEALTH_URL="${SERVICE_HEALTH[$TARGET]}"
    HEALTH_ITERS="${HEALTH_WAIT[$TARGET]:-300}"
    for i in $(seq 1 "$HEALTH_ITERS"); do
        if ssh "$REMOTE" "curl -sf '$HEALTH_URL'" > /dev/null 2>&1; then
            echo "  Service healthy after approx $((i * 2))s"
            echo ""
            echo "=== Deploy complete: ${TARGET} ==="
            exit 0
        fi
        sleep 2
    done
    echo "FAIL: Service did not become healthy in $((HEALTH_ITERS * 2))s"
    exit 1
fi