#!/usr/bin/env bash # llm-gates.sh — the artifact gates every LLM endpoint runs before it starts. # # Why this file exists: the fleet law from the 2026-10-01 crash-loop is that # a serve script and the deployer must refuse the SAME missing/truncated # artifact, the SAME way. When the two gates were hand-written twins they # drifted mid-cutover — green deploy, red unit, every time the payload moved. # Both sides source this library, so the refusal is one text and one rule. # # Contract (public interface): # require_file PATH LABEL HINT # require_bytes PATH LABEL WANT_BYTES HINT # require_min_mib PATH LABEL MIN_MIB HINT # require_dir_files DIR LABEL HINT FILE... # require_image REF HINT # # Each returns 0 and prints nothing on success. On failure it prints two # lines to stderr — the first naming the endpoint ($GATE_PREFIX) and the # artifact, the second the remedy — and returns 1. It NEVER exits: the serve # scripts run under `set -e` (so a refusal is terminal), while the deployer # wants `|| return 1` so a failed gate reports a red deploy for that one # service and the dispatcher's state marker stays pending. # # The size law is equality, not a floor, for `require_bytes`: a hub fetch # that truncates is the fleet's standing hazard (curl exits 0 on 401/403 and # writes the error body as the artifact), and the declared byte count is a # contract in both directions — a bigger file is a DIFFERENT artifact. # GATE_PREFIX names the endpoint in every refusal (e.g. frank-dragoon). : "${GATE_PREFIX:=gate}" _gate_fail() { printf '%s: %s\n' "$GATE_PREFIX" "$1" >&2 printf ' hint: %s\n' "$2" >&2 return 1 } # require_file — PATH must be a regular file. A directory (an unpacked # staging dir wearing the payload's name) and a symlink (a HuggingFace cache # snapshot's entry, which dangles inside the container mount) both refuse. require_file() { local path="$1" label="$2" hint="$3" if [[ -L "$path" || ! -f "$path" ]]; then _gate_fail "$label: missing at $path" "$hint" fi } # require_bytes — PATH must exist AND be exactly WANT_BYTES bytes. require_bytes() { local path="$1" label="$2" want="$3" hint="$4" got require_file "$path" "$label" "$hint" || return 1 got="$(stat -c %s "$path")" if [[ "$got" != "$want" ]]; then _gate_fail "$label: is $got bytes, expected $want" "$hint" fi } # require_min_mib — PATH must be at least MIN_MIB mebibytes. The floor form # is for build products (a .rad container is a range of legal sizes; a # truncated convert is not). require_min_mib() { local path="$1" label="$2" min="$3" hint="$4" mib require_file "$path" "$label" "$hint" || return 1 mib=$(( $(stat -c %s "$path") / 1048576 )) if (( mib < min )); then _gate_fail "$label: is $mib MiB, expected >= $min MiB" "$hint" fi } # require_dir_files — DIR must be a directory and every named member a # regular file (the flat-tokenizer law: snapshot symlinks dangle in the # container mount even when the directory itself is real). require_dir_files() { local dir="$1" label="$2" hint="$3" shift 3 local f if [[ ! -d "$dir" ]]; then _gate_fail "$label: missing at $dir" "$hint" fi for f in "$@"; do if [[ -L "$dir/$f" || ! -f "$dir/$f" ]]; then _gate_fail "$label: $dir/$f is missing or a symlink" "$hint" fi done } # require_image — the image ref must be in podman storage. A name@sha256 ref # exists only if THAT manifest was pulled, so the gate is the ref itself, in # one command: no pipefail/grep race (the 2026-09-30 lesson). require_image() { local ref="$1" hint="$2" if ! podman image exists "$ref"; then _gate_fail "image: $ref is not in podman storage" "$hint" fi }