Frank
d7bf9f119a
The frank-medium retirement tail the 2026-09-26 lucebox cutover left uncommitted: the radiance quadlet tree, its swap/fetch tooling and its seam test are deleted (archive copies live in dankserver/.AGENTTRASH/ 20260926-frank-medium-radiance/ and scripts/.AGENTTRASH/20260926- frank-medium-radiance/), the planner/allowlist/test-changed mappings drop the service, and frank-large's chat template moves to scripts/ (its old home was the retired frank-medium dir). Finished here: - tests/frank_primary_unit.bats: the lucebox quadlet seam (boot persistence, host-network bind, HIP_VISIBLE_DEVICES=0,1, HIP-reserved env-name guard, checkout-mounted entrypoint/healthcheck, first-start patience, deployer payload/port gates). - test-changed.sh: explicit .AGENTTRASH/ case — retirement commits move files to trash, and the wrapper refused those additions with "no focused-test mapping". - observability: the vllm: namespace left with the radiance runtime. Rules keep only llamacpp:* series (prefix-cache reuse, spec-decode, queueing, endpoint-down); the dashboard drops the vLLM KV/latency panels; prometheus.yml documents that frank-primary (lucebox) has no /metrics and therefore no scrape job. llm-fleet.json was left corrupted mid-edit (missing opening brace) and is rewritten from HEAD. Suite: 339 green (was 7 red).
128 lines
6.2 KiB
Bash
128 lines
6.2 KiB
Bash
#!/usr/bin/env bats
|
|
# Seam: target reachability and deployment flow integrity.
|
|
# These tests assert the service-scoped deployment contract:
|
|
# - deploy.sh accepts a target, optional service scope, and --dry-run
|
|
# - deploy-remote.sh owns per-service handlers and deployment state
|
|
# - no host-wide inference restart is hidden in the dispatcher
|
|
# - every host referenced in the repo is reachable over SSH (dank@host)
|
|
# - the local git remote is configured before deploy is attempted
|
|
# Reachability tests are SKIPPED when the target is unreachable so the suite
|
|
# still runs during offline development.
|
|
|
|
load helpers
|
|
|
|
@test "deploy.sh exists and is executable" {
|
|
[ -x "$REPO_ROOT/scripts/deploy.sh" ]
|
|
}
|
|
|
|
@test "deploy.sh accepts the two known targets" {
|
|
run bash "$REPO_ROOT/scripts/deploy.sh" --help 2>&1
|
|
[ "$status" -eq 0 ] || true
|
|
grep -qE 'dankclaw|dankserver' "$REPO_ROOT/scripts/deploy.sh"
|
|
}
|
|
|
|
@test "git remote origin is configured" {
|
|
git -C "$REPO_ROOT" remote get-url origin >/dev/null 2>&1 \
|
|
|| skip "no origin remote configured yet"
|
|
}
|
|
|
|
@test "dankclaw is reachable over ssh" {
|
|
timeout 8 ssh -o BatchMode=yes -o ConnectTimeout=5 dank@dankclaw 'true' 2>/dev/null \
|
|
|| skip "dankclaw not reachable from this host"
|
|
}
|
|
|
|
@test "dankserver is reachable over ssh" {
|
|
timeout 8 ssh -o BatchMode=yes -o ConnectTimeout=5 dank@dankserver 'true' 2>/dev/null \
|
|
|| skip "dankserver not reachable from this host"
|
|
}
|
|
|
|
# Regression: the Caddyfile render step in deploy.sh must survive a bcrypt
|
|
# hash (which contains '/' characters). Reproduce the sed expression with a
|
|
# slash-bearing hash and confirm the placeholder is replaced.
|
|
@test "scoped remote runner owns Caddy reload and safe fallback" {
|
|
# Caddy is handled only when selected by the planner. A failed reload may
|
|
# restart Caddy, but must not restart the whole compose project.
|
|
grep -q 'caddy reload' "$REPO_ROOT/scripts/deploy-remote.sh"
|
|
grep -q 'podman restart caddy' "$REPO_ROOT/scripts/deploy-remote.sh"
|
|
! grep -qE 'podman-compose.*(up|restart).*\$\(' "$REPO_ROOT/scripts/deploy-remote.sh"
|
|
}
|
|
|
|
@test "Caddy migration retires the standalone Gitea proxy" {
|
|
grep -q 'retire_legacy_gitea_caddy' "$REPO_ROOT/scripts/deploy-remote.sh"
|
|
grep -q 'systemctl --user stop gitea-caddy.service' "$REPO_ROOT/scripts/deploy-remote.sh"
|
|
grep -q 'systemctl --user disable gitea-caddy.service' "$REPO_ROOT/scripts/deploy-remote.sh"
|
|
! grep -q 'deploy_gitea_unit gitea-caddy' "$REPO_ROOT/scripts/deploy-remote.sh"
|
|
}
|
|
|
|
@test "canonical Caddy deployment installs its boot-persistent quadlet" {
|
|
# 2026-08-26: a bare compose container never came back after reboot.
|
|
# deploy_caddy must install and start the quadlet unit instead of
|
|
# `podman-compose up`. Boot persistence comes from the quadlet generator's
|
|
# default.target.wants symlink (is-enabled reports "generated"), so there
|
|
# is no explicit systemctl enable — it fails on generated units.
|
|
grep -q 'install_quadlet caddy dankclaw/caddy/quadlet caddy' "$REPO_ROOT/scripts/deploy-remote.sh"
|
|
grep -q 'systemctl --user restart caddy.service' "$REPO_ROOT/scripts/deploy-remote.sh"
|
|
! grep -q 'systemctl --user enable caddy.service' "$REPO_ROOT/scripts/deploy-remote.sh"
|
|
! grep -q 'podman-compose -f dankclaw/compose.yaml up -d --no-deps caddy' "$REPO_ROOT/scripts/deploy-remote.sh"
|
|
! grep -q 'no proxy was stopped or replaced' "$REPO_ROOT/scripts/deploy-remote.sh"
|
|
}
|
|
|
|
@test "remote runner has a handler per inference service" {
|
|
grep -q 'deploy_llm_large' "$REPO_ROOT/scripts/deploy-remote.sh"
|
|
grep -q 'deploy_llm_primary' "$REPO_ROOT/scripts/deploy-remote.sh"
|
|
grep -q 'deploy_llm_small' "$REPO_ROOT/scripts/deploy-remote.sh"
|
|
}
|
|
|
|
@test "inference restarts are absent from the top-level dispatcher" {
|
|
! grep -qE 'systemctl .*restart (frank-medium|frank-large|frank-npu)' "$REPO_ROOT/scripts/deploy.sh"
|
|
}
|
|
|
|
@test "remote runner health-checks an inference endpoint" {
|
|
grep -q '127.0.0.1:7770/health' "$REPO_ROOT/scripts/deploy-remote.sh"
|
|
}
|
|
|
|
@test "deploy.sh pulls the merged checkout on the target" {
|
|
grep -q 'git pull --ff-only origin main' "$REPO_ROOT/scripts/deploy.sh"
|
|
grep -q '/home/dank/serverAppConfigs' "$REPO_ROOT/scripts/deploy.sh"
|
|
}
|
|
|
|
@test "deploy.sh Caddyfile render survives a slash-bearing bcrypt hash" {
|
|
local hash='$2a$14$dndiQ9EaycJv0w3Gp2oAYO/xH6O9x2ZRhMLJdCxrgi9rMn1te9D/spy'
|
|
local rendered
|
|
rendered=$(sed "s|REPLACE_WITH_HASH|${hash}|g" "$REPO_ROOT/dankclaw/Caddyfile")
|
|
[ -n "$rendered" ]
|
|
[[ "$rendered" == *"${hash}"* ]]
|
|
! grep -q 'REPLACE_WITH_HASH' <<< "$rendered"
|
|
# The rendered line must be exactly "dankuser <hash>". A template that
|
|
# keeps its own $2a$14$ prefix renders an invalid double-prefixed hash
|
|
# and every basicauth vhost returns 401 (2026-08-22 incident).
|
|
grep -qF "dankuser ${hash}" <<< "$rendered"
|
|
! grep -qF '$2a$14$$2a$14$' <<< "$rendered"
|
|
}
|
|
|
|
@test "the pending pass prunes retired-service state instead of blocking the run" {
|
|
# Regression: a pending state entry for frank-default-sightsound (an
|
|
# endpoint retired 2026-09-11) made every --pending run exit 2 at the
|
|
# dispatcher before the Playwright e2e gate could execute. The pending
|
|
# pass must drop entries the target no longer allows into the trash and
|
|
# still deploy the services that remain.
|
|
local sandbox="$BATS_TEST_TMPDIR/st"
|
|
mkdir -p "$sandbox"
|
|
printf 'revision=deadbeef\nstatus=pending\n' > "$sandbox/frank-default-sightsound"
|
|
printf 'revision=deadbeef\nstatus=pending\n' > "$sandbox/searxng"
|
|
run env HOME="$BATS_TEST_TMPDIR" STATE_DIR="$sandbox" bash -c '
|
|
set -euo pipefail
|
|
SERVICES=()
|
|
REVISION=cafebabe
|
|
TARGET=dankclaw
|
|
service_is_allowed() { [[ "$1" == searxng ]]; }
|
|
eval "$(sed -n "/^state_revision()/,/^}/p" "$1/scripts/deploy-remote.sh"; sed -n "/^state_status()/,/^}/p" "$1/scripts/deploy-remote.sh"; sed -n "/^add_pending_services()/,/^}/p" "$1/scripts/deploy-remote.sh")"
|
|
add_pending_services >/dev/null 2>&1
|
|
printf "%s\n" "${SERVICES[@]:-}"
|
|
' _ "$REPO_ROOT"
|
|
[ "$status" -eq 0 ]
|
|
[ "$output" = "searxng" ]
|
|
[ ! -e "$sandbox/frank-default-sightsound" ]
|
|
[ -e "$BATS_TEST_TMPDIR/.AGENTTRASH/$(date +%Y%m%d)-retired-deploy-state/frank-default-sightsound" ]
|
|
}
|