Frank
fbfbc5c6db
Operator request (2026-08-22): the primary inference server (frank-default-large, the 27B CIRU model on Dankclaw) moves to the standard llama.cpp port 7770. Both LLM services now listen on :7770, distinguished by host (dankserver vs dankclaw). Functional changes: - scripts/frank-default-large.env: LISTEN_PORT 52625 -> 7770 - scripts/serve-frank-large.sh: default LISTEN_PORT 52625 -> 7770 - scripts/deploy.sh: LLM_HEALTH[dankclaw] -> :7770 - open-webui quadlet: OPENAI_API_BASE_URL -> 192.168.0.143:7770 (re-pointed so chat keeps working; data dir preserved) - scripts/bench-fast-greedy.sh: PORT 52625 -> 7770 Tests updated to the new topology (both LLM endpoints on :7770 by host; open-webui -> :7770). Docs + pi KB updated; dated historical runbooks keep their point-in-time ports. models.json (pi client) re-pointed to :7770 separately, effective on the next client restart.
94 lines
4.2 KiB
Bash
94 lines
4.2 KiB
Bash
#!/usr/bin/env bats
|
|
# Seam: target reachability and deployment flow integrity.
|
|
# These tests assert the deployment contract of the unified repo:
|
|
# - a deploy.sh exists and accepts <dankclaw|dankserver> and --dry-run
|
|
# - deploy.sh covers both the podman stack and the LLM fleet services
|
|
# - 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 "$REPO_ROOT" remote get-url origin >/dev/null 2>&1 \
|
|
|| skip "no origin remote configured yet"
|
|
}
|
|
|
|
@test "dankclaw is reachable over ssh" {
|
|
timeout 8 ssh -o BatchMode=yes -o ConnectTimeout=5 dank@dankclaw 'true' 2>/dev/null \
|
|
|| skip "dankclaw not reachable from this host"
|
|
}
|
|
|
|
@test "dankserver is reachable over ssh" {
|
|
timeout 8 ssh -o BatchMode=yes -o ConnectTimeout=5 dank@dankserver 'true' 2>/dev/null \
|
|
|| skip "dankserver not reachable from this host"
|
|
}
|
|
|
|
# Regression: the Caddyfile render step in deploy.sh must survive a bcrypt
|
|
# hash (which contains '/' characters). Reproduce the sed expression with a
|
|
# slash-bearing hash and confirm the placeholder is replaced.
|
|
@test "deploy.sh reloads Caddy after rendering (hot reload, not just container start)" {
|
|
# The caddy container often survives 'up -d' (a Caddyfile change is a
|
|
# bind-mount content change, not a container config change). Without an
|
|
# explicit reload, a rendered fix can sit on disk while Caddy serves the
|
|
# stale in-memory config.
|
|
grep -q 'caddy reload' "$REPO_ROOT/scripts/deploy.sh"
|
|
}
|
|
|
|
@test "deploy.sh restarts caddy when the reload cannot be applied" {
|
|
# If the running config has the admin API disabled (or the API is down),
|
|
# 'caddy reload' can never apply the new file -- the fix cannot be
|
|
# delivered over the API it is meant to enable. The fallback is a
|
|
# container restart, which always reads the file.
|
|
grep -q 'podman restart caddy' "$REPO_ROOT/scripts/deploy.sh"
|
|
}
|
|
|
|
# The unified deploy.sh must manage the LLM fleet services on both hosts:
|
|
# frank-default-small (dankserver) and frank-default-large (dankclaw). A
|
|
# deploy that only restarts the podman stack leaves the LLM units pointing
|
|
# at the retired vllmScripts checkout.
|
|
@test "deploy.sh restarts the LLM services on both targets" {
|
|
grep -q 'frank-default-small' "$REPO_ROOT/scripts/deploy.sh"
|
|
grep -q 'frank-default-large' "$REPO_ROOT/scripts/deploy.sh"
|
|
}
|
|
|
|
@test "deploy.sh health-checks both LLM endpoints (both on :7770, by host)" {
|
|
# 2026-08-22: frank-default-large moved from :52625 to :7770 on
|
|
# dankclaw. Both LLM services now listen on :7770, distinguished by
|
|
# host (dankserver vs dankclaw).
|
|
grep -qE '^LLM_HEALTH\[dankserver\]="http://127\.0\.0\.1:7770/health"' "$REPO_ROOT/scripts/deploy.sh"
|
|
grep -qE '^LLM_HEALTH\[dankclaw\]="http://127\.0\.0\.1:7770/health"' "$REPO_ROOT/scripts/deploy.sh"
|
|
}
|
|
|
|
@test "deploy.sh pulls on the merged checkout on both targets" {
|
|
# Both targets run the whole stack (podman + LLM) from one checkout.
|
|
local count
|
|
count=$(grep -c '/home/dank/serverAppConfigs' "$REPO_ROOT/scripts/deploy.sh")
|
|
[ "$count" -ge 2 ]
|
|
}
|
|
|
|
@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 "dank <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 "dank ${hash}" <<< "$rendered"
|
|
! grep -qF '$2a$14$$2a$14$' <<< "$rendered"
|
|
}
|