serverAppConfigs/scripts/serve-frank-primary.sh

#!/usr/bin/env bash
# serve-frank-primary.sh — frank-primary endpoint (R9V radiance-vLLM fork,
# Qwen3.8-Flash-Next-Uncensored IQ4_XS + MTP4 drafter, 2x R9700, dankserver
# :7770).
#
# The engine is the upstream R9V launcher (scripts/launch.sh in the fork
# checkout), NOT a hand-frozen podman argv: launch.sh owns the resolved
# docker/podman args (binds, overlays, device passthrough, publish lines)
# and the fork's qualification was measured through it. This script's job:
#
#   1. layer the on-host R9V setup state (the 104-key tuned shape the
#      profile setup qualified) under this repo's frank-primary.env
#      overrides (bind/port/alias/container);
#   2. gate on the pinned runtime image (by its OCI manifest digest, the
#      podman RepoDigest), the exact-size PLE payload, and the GGUF shards;
#   3. exec the launcher, then wait on the container: launch.sh --detach
#      exits as soon as the container is created, so without the wait the
#      unit would be "green" while the engine crashes — the wait is what
#      keeps systemd's Restart=on-failure self-healing real.
#
# The root unit (scripts/frank-primary.service, User=dank,
# LimitMEMLOCK=infinity) grants the pin budget for the tiered-expert UVA
# host copy (~43 GiB pinned) and the 16 GiB PLE pinned reserve. A plain
# shell session also works (proven 2026-09-27: podman rootless inherits
# usable limits here), but the unit is the fleet-parity boot-persistent
# shape.
set -euo pipefail

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
ENV_FILE="${FRANK_PRIMARY_ENV_FILE:-$SCRIPT_DIR/frank-primary.env}"

if [ ! -f "$ENV_FILE" ]; then
    echo "serve-frank-primary: env file missing: $ENV_FILE" >&2
    exit 1
fi
set -a
# shellcheck disable=SC1090
source "$ENV_FILE"
set +a

: "${R9V_HOME:?R9V_HOME must name the fork checkout}"
: "${R9V_STATE_FILE:?R9V_STATE_FILE must name the setup state}"
: "${R9V_HOST_BIND:?R9V_HOST_BIND must be set}"
: "${R9V_HOST_PORT:?R9V_HOST_PORT must be set}"
: "${R9V_SERVED_MODEL_NAME:?R9V_SERVED_MODEL_NAME must be set}"
: "${R9V_CONTAINER_NAME:?R9V_CONTAINER_NAME must be set}"

LAUNCHER="$R9V_HOME/scripts/launch.sh"
if [ ! -x "$LAUNCHER" ]; then
    echo "serve-frank-primary: R9V launcher missing: $LAUNCHER" >&2
    exit 1
fi

# The docker->podman shim is REQUIRED: the launcher and its doctor speak
# docker (OCI-manifest-digest image IDs, LogConfig fields) that podman's
# native CLI answers differently. The shim carries those laws.
SHIM_DIR="$R9V_HOME/.podman-shim"
if [ ! -x "$SHIM_DIR/docker" ]; then
    echo "serve-frank-primary: docker->podman shim missing: $SHIM_DIR/docker" >&2
    exit 1
fi
export PATH="$SHIM_DIR:$PATH"

# --- layer 1: the qualified setup state (production overrides never come
# from here; keys already defined in the env file are skipped) -------------
STATE_FILE="$R9V_STATE_FILE"
if [ ! -f "$STATE_FILE" ]; then
    echo "serve-frank-primary: R9V setup state missing: $STATE_FILE" >&2
    echo "  run the profile setup first (r9v setup qwen38-mtp4-uncensored ...)" >&2
    exit 1
fi
STATE_EXPORTS="$(python3 - "$STATE_FILE" <<'PY'
import json, shlex, sys, os
state = json.load(open(sys.argv[1]))
config = state.get("config") or {}
if state.get("ready") is not True:
    sys.exit("R9V setup state is not ready; rerun setup before serving")
env_keys = {k for k in os.environ if k.startswith("R9V_")}
for key in sorted(config):
    if key.startswith("R9V_") and key not in env_keys:
        print(f"export {key}={shlex.quote(config[key])}")
PY
)"
eval "$STATE_EXPORTS"

: "${R9V_IMAGE:?state must carry R9V_IMAGE}"
: "${R9V_MODEL_DIR:?state must carry R9V_MODEL_DIR}"
: "${R9V_PLE_PATH:?state must carry R9V_PLE_PATH}"

# --- gates: never serve a half-finished payload or a missing image --------
# Runtime image by pinned OCI manifest digest (podman keys images by config
# digest but preserves the manifest digest in RepoDigests — the shim's ID law).
if ! podman images --format '{{.RepoDigests}}' | grep -qF "${R9V_IMAGE#sha256:}"; then
    echo "serve-frank-primary: pinned R9V image absent: $R9V_IMAGE" >&2
    echo "  load the bundle: ./r9v setup qwen38-mtp4-uncensored --state-dir ..." >&2
    exit 1
fi

# PLE payload at its pinned byte count (stat -c %s, never wc -c), plus the
# three target GGUF shards and the mmproj the launcher mounts.
PLE_BYTES="${R9V_PLE_EXPECTED_BYTES:-}"
if [ -n "$PLE_BYTES" ]; then
    ACTUAL="$(stat -c %s "$R9V_PLE_PATH" 2>/dev/null || echo 0)"
    if [ "$ACTUAL" != "$PLE_BYTES" ]; then
        echo "serve-frank-primary: PLE payload wrong size: $R9V_PLE_PATH" >&2
        echo "  expected $PLE_BYTES, found $ACTUAL" >&2
        exit 1
    fi
else
    if [ ! -f "$R9V_PLE_PATH" ]; then
        echo "serve-frank-primary: PLE payload missing: $R9V_PLE_PATH" >&2
        exit 1
    fi
fi
for rel in "$R9V_TARGET_REL" "$R9V_TARGET_SHARD2_REL" "$R9V_TARGET_SHARD3_REL" "$R9V_MMPROJ_REL"; do
    if [ -z "$rel" ]; then continue; fi
    if [ ! -f "$R9V_MODEL_DIR/$rel" ]; then
        echo "serve-frank-primary: payload file missing: $R9V_MODEL_DIR/$rel" >&2
        exit 1
    fi
done

if [ ! -e /dev/kfd ] || [ ! -d /dev/dri ]; then
    echo "serve-frank-primary: GPU device nodes absent (/dev/kfd, /dev/dri)" >&2
    exit 1
fi

# A crashed/killed unit can leave the container name registered (systemd
# SIGKILLs conmon before cleanup runs); the launcher refuses an existing
# name forever after. Clear any orphan of OUR name first — idempotent.
docker rm -f "$R9V_CONTAINER_NAME" >/dev/null 2>&1 || true

# launch.sh detaches after preflight; from here on, this script's lifetime
# IS the container's: wait returns the container's exit code, so a crash is
# a nonzero ExecStart and Restart=on-failure fires. (systemd stop goes
# through ExecStop in the unit — docker wait alone cannot stop the child.)
"$LAUNCHER"
exec docker wait "$R9V_CONTAINER_NAME"