#!/usr/bin/env bats
# Seam: frank-primary — the Dankserver LLM endpoint on :7770.
#
# This file asserts the tcclaviger RDNA4 vLLM ROOT-UNIT shape (the
# 2026-10-01 BF16 cutover, the overnight redo campaign's verdict): the serve
# script drives `podman run` DIRECTLY (the image entrypoint execs
# `vllm serve`), with every engine flag qualified by boot probe and carried
# in the repo env file. The seam pins what the flags alone do not say: the
# KV qualification law (11.05 GiB/rank boots bf16 at 798,280 tokens / 3.05x
# concurrency; the old 7.2 GiB ceiling was the MTP4 workspace, not VRAM),
# the bf16-KV trade (double the attention-KV bytes/token, ~14% decode cost,
# clean cache + 262k windows), the automatic-offload law (the fork plans
# the tiered-expert offload itself; no flag exists to set), the self-healing
# law (the run returns before the engine is up, so the serve script must
# wait on the container for Restart=on-failure to mean anything), the
# memlock law that makes the pinned host rows legal, the deployer's
# image/payload gates with the false-green MainPID check, and the measured
# laws: expert prefetch ABSENT (36% precision), NO speculative decode (the
# no-spec family measured fastest once the prefetch tax was removed; MTP
# re-measures pending), gather geometry 32x64 PRESENT (+18.7% decode),
# MNBT 1024 (Frank's lock), and NO tool dialect.

load helpers

UNIT="$REPO_ROOT/scripts/frank-primary.service"
SERVE="$REPO_ROOT/scripts/serve-frank-primary.sh"
ENV_FILE="$REPO_ROOT/scripts/frank-primary.env"
REMOTE_DEPLOY="$REPO_ROOT/scripts/deploy-remote.sh"
DOWNLOAD="$REPO_ROOT/scripts/download-frank-primary.sh"

@test "frank-primary unit, serve script and env exist in scripts/" {
    [ -f "$UNIT" ]
    [ -x "$SERVE" ]
    [ -f "$ENV_FILE" ]
}

@test "frank-primary is boot-persistent, self-healing and unprivileged" {
    # Root unit parity with frank-large/frank-small: enable is the [Install]
    # section, the restart policy survives a crash, and the tiered-expert
    # pin needs an unbounded memlock (a root unit grants it via PID1; the
    # dank session's own hard limit is 8 MiB and cannot be raised without
    # restarting user@1000.service).
    grep -q '^WantedBy=multi-user.target$' "$UNIT"
    grep -q '^Restart=on-failure$' "$UNIT"
    grep -q '^RestartSec=' "$UNIT"
    grep -q '^User=dank$' "$UNIT"
    grep -q '^LimitMEMLOCK=infinity$' "$UNIT"
}

@test "frank-primary runs the repo's own serve script with the repo's env" {
    grep -q '^ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-primary.sh$' "$UNIT"
    grep -q 'FRANK_PRIMARY_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-primary.env' "$UNIT"
}

@test "the unit stops the container child explicitly" {
    # The serve script blocks on podman wait, which cannot stop the
    # container child; systemd stop goes through ExecStop or the engine
    # outlives the unit and holds both GPUs. The container name must match
    # the env file's identity.
    grep -q '^ExecStop=/usr/bin/podman stop' "$UNIT"
    grep -q 'frank-primary-qwen' "$UNIT"
    grep -q '^FRANK_PRIMARY_CONTAINER=frank-primary-qwen$' "$ENV_FILE"
}

@test "the serve shape is direct podman run, not a launcher or shim" {
    # The tcclaviger stack is fully expressed by flags; the R9V launcher,
    # docker->podman shim and setup-state layering are the RETIRED shape.
    grep -q 'podman run' "$SERVE"
    ! grep -q 'launch.sh' "$SERVE"
    ! grep -q 'podman-shim' "$SERVE"
    ! grep -q 'R9V_STATE_FILE' "$SERVE"
    ! grep -q -- '--model-draft' "$SERVE"
    ! grep -q -- '--spec-type' "$SERVE"
}

@test "the qualified engine shape is in the env file" {
    # 2026-10-01 boot probe: 262,144 x 3 seqs at bf16 KV, util 0.98,
    # KV_BYTES 11,047,010,304 PER RANK boots at "KV cache size: 798,280
    # tokens" and reports max concurrency 3.05x for 262,144-token requests
    # — all three full windows fit with an 11,848-token margin. The old
    # "KV_BYTES is PER RANK, 9/16 GiB OOM" law was the MTP4 drafter's
    # workspace reservation, not a VRAM wall: no-spec takes 11.05 GiB/rank
    # and boots clean.
    grep -q '^FRANK_PRIMARY_MAXLEN=262144$' "$ENV_FILE"
    grep -q '^FRANK_PRIMARY_SEQS=3$' "$ENV_FILE"
    grep -q '^FRANK_PRIMARY_UTIL=0.98$' "$ENV_FILE"
    grep -q '^FRANK_PRIMARY_KV_BYTES=11047010304$' "$ENV_FILE"
    grep -q '^FRANK_PRIMARY_KV_DTYPE=auto$' "$ENV_FILE"
    grep -q '^FRANK_PRIMARY_MNBT=1024$' "$ENV_FILE"
    grep -q '^FRANK_PRIMARY_GATHER_CHUNKS=32$' "$ENV_FILE"
    grep -q '^FRANK_PRIMARY_GATHER_LANES=64$' "$ENV_FILE"
    ! grep -q '^FRANK_PRIMARY_SPEC=' "$ENV_FILE"
    grep -q '^FRANK_PRIMARY_MODEL_SHARDS=131$' "$ENV_FILE"
}

@test "the serve script wires the engine flags from the env" {
    grep -q -- '--max-num-seqs "$FRANK_PRIMARY_SEQS"' "$SERVE"
    grep -q -- '--max-model-len "$FRANK_PRIMARY_MAXLEN"' "$SERVE"
    grep -q -- '--kv-cache-memory-bytes "$FRANK_PRIMARY_KV_BYTES"' "$SERVE"
    grep -q -- '--kv-cache-dtype "$FRANK_PRIMARY_KV_DTYPE"' "$SERVE"
    grep -q -- '--max-num-batched-tokens "$FRANK_PRIMARY_MNBT"' "$SERVE"
    grep -q -- '-e R4D_LRU_GATHER_CHUNKS="$FRANK_PRIMARY_GATHER_CHUNKS"' "$SERVE"
    grep -q -- '-e R4D_LRU_GATHER_LANES="$FRANK_PRIMARY_GATHER_LANES"' "$SERVE"
    ! grep -q -- '--speculative-config' "$SERVE"
    grep -q -- '--tensor-parallel-size 2' "$SERVE"
    grep -q -- '--enable-prefix-caching' "$SERVE"
    grep -q -- '--trust-remote-code' "$SERVE"
}

@test "the endpoint serves NO tool dialect — tool agents route elsewhere" {
    # The 2339fae trio does NOT wire --enable-auto-tool-choice /
    # --tool-call-parser (the GLM era added glm47 dialect flags; the rollback
    # dropped them). tool_choice "auto" gets a 400 here — tool-using agents
    # must route at frank-small or frank-large until a parser is qualified
    # for this arm (a behavior change beyond the rollback, not a silent fix).
    ! grep -q -- '--enable-auto-tool-choice' "$SERVE"
    ! grep -q -- '--tool-call-parser' "$SERVE"
}

@test "expert offload is AUTOMATIC — the payload cannot fit VRAM and no flag sets it" {
    # ~86 GiB/rank of FP8 trunk against 32 GiB of VRAM: the fork's tiered-
    # expert planner moves the overflow to pinned host rows by itself (the
    # arena 6,574 slots x 2.344 MiB plus host rows). There is no
    # --enable-expert-offload flag in this arm; the legality of the pin is
    # the unit's unbounded LimitMEMLOCK.
    ! grep -q -- '--enable-expert-offload' "$SERVE"
    ! grep -q -- '--expert-precise-memory' "$SERVE"
    grep -q '^LimitMEMLOCK=infinity$' "$UNIT"
    grep -q -- '--ipc=host --ulimit memlock=-1:-1' "$SERVE"
}

@test "speculative decode is ABSENT BY MEASUREMENT" {
    # The 2026-10-01 overnight redo (prefetch OFF) re-measured the whole
    # spec family against no-spec at matched geometry: no-spec measured
    # 41.46/41.29/41.47 tok/s while the spec-era incumbent's 37-40 carried
    # the prefetch tax, and MTP's 2.6 GiB/rank drafter reservation halves
    # the pool (729,545 vs 975,342 tokens). The MTP3/4/6 untaxed re-measures
    # never completed; until one shows a real win, no spec is the incumbent.
    ! grep -q '^FRANK_PRIMARY_SPEC=' "$ENV_FILE"
    ! grep -q -- '--speculative-config' "$SERVE"
}

@test "bf16 KV is PRESENT — clean cache won the trade" {
    # --kv-cache-dtype auto = bf16 attention KV. Doubles attention-KV
    # bytes/token (measured 14,047 vs 7,926) and costs ~14% decode vs fp8
    # at 4064 ctx (49.25 -> 36.42 with the gather win) — traded deliberately
    # for clean cache and 262k windows (Frank's call). The fp8 shape is
    # restorable from git tag frank-primary-fp8-mtp-20261001.
    grep -q '^FRANK_PRIMARY_KV_DTYPE=auto$' "$ENV_FILE"
    grep -q -- '--kv-cache-dtype "$FRANK_PRIMARY_KV_DTYPE"' "$SERVE"
}

@test "gather geometry 32x64 is PRESENT BY MEASUREMENT" {
    # R4D_LRU_GATHER_CHUNKS=32 / R4D_LRU_GATHER_LANES=64: the overnight
    # sweep's biggest lever, +18.7% decode vs default geometry, and the win
    # GROWS with depth (39.5@166 -> 54.1@1087 -> 49.3@4064 in the fp8 era).
    # g64x128 is past the peak; g8x16 mild. They are container ENV (the
    # fork's knobs), not engine flags — passed through with -e.
    grep -q '^FRANK_PRIMARY_GATHER_CHUNKS=32$' "$ENV_FILE"
    grep -q '^FRANK_PRIMARY_GATHER_LANES=64$' "$ENV_FILE"
    grep -q -- '-e R4D_LRU_GATHER_CHUNKS="$FRANK_PRIMARY_GATHER_CHUNKS"' "$SERVE"
}

@test "MNBT is locked at 1024" {
    # Frank's lock: MNBT 512 doubles TTFT at 4064 ctx (2.46 s vs 1.36 s);
    # 1024-4096 are interchangeable on decode; 12288 costs 2.5% plus arena.
    # 1024 keeps the workspace floor so the expert arena stays max.
    grep -q '^FRANK_PRIMARY_MNBT=1024$' "$ENV_FILE"
    grep -q -- '--max-num-batched-tokens "$FRANK_PRIMARY_MNBT"' "$SERVE"
}

@test "expert prefetch is absent BY LAW, not by omission" {
    # Telemetry (2026-09-29): the prefetcher served 13,369 of 36,720
    # prefetched slabs (36% precision) — roughly half the gather traffic was
    # waste, and the "savings" would have been installs anyway. Deleting the
    # flag moved decode 26.8 -> 40.6 tok/s. Any future flag must come with a
    # fresh A/B, so the serve script must NOT wire it unconditionally.
    ! grep -q -- '--expert-prefetch' "$SERVE"
    ! grep -q 'expert_prefetch' "$ENV_FILE"
    grep -q 'PREFETCH IS ABSENT BY LAW' "$ENV_FILE"
}

@test "TunableOp stays off" {
    # CLAV_TUNABLEOP_SWEEP silently skips under expert offload unless
    # CLAV_TUNABLEOP_WITH_OFFLOAD=1, and forcing it corrupts numerics
    # (repetition loops, early halts, invalid measurements).
    ! grep -q 'TUNABLEOP' "$ENV_FILE"
    ! grep -q 'TUNABLEOP' "$SERVE"
}

@test "the serve script gates the digest-pinned image and the payload" {
    # The image is pinned by OCI manifest digest (the floating :latest moved
    # once already). The payload gate checks config.json and the exact shard
    # count from the env — a missing shard means a guaranteed long-timeout
    # boot instead of a fast failure.
    grep -q 'FRANK_PRIMARY_IMAGE' "$SERVE"
    grep -q 'RepoDigests' "$SERVE"
    grep -q 'FRANK_PRIMARY_MODEL_SHARDS' "$SERVE"
    grep -q 'config.json' "$SERVE"
    grep -q '/dev/kfd' "$SERVE"
    grep -q -- '--device /dev/dri' "$SERVE"
    ! grep -q 'tcclaviger/vllm:latest' "$ENV_FILE"
}

@test "the serve script clears stale containers and self-heals via podman wait" {
    # A crashed unit can leave the container name registered forever after;
    # the legacy identities (the retired R9V container and the ad hoc
    # experiment container) hold the same GPUs and die here too. Then block
    # on the container so a crash is a nonzero ExecStart.
    grep -q 'FRANK_PRIMARY_LEGACY_CONTAINERS' "$ENV_FILE"
    grep -q 'frank-primary-r9v' "$ENV_FILE"
    grep -q 'qwen-fp8' "$ENV_FILE"
    grep -q 'exec podman wait "$FRANK_PRIMARY_CONTAINER"' "$SERVE"
}

@test "frank-primary holds the single fleet port under its own alias" {
    # The scratch identity (qwen3.8-flash-next on :7773) must never leak
    # into production: LAN publish of :7770, the harness's model id.
    grep -q '^FRANK_PRIMARY_PUBLISH=7770:7770$' "$ENV_FILE"
    grep -q '^FRANK_PRIMARY_SERVED_NAME=frank-primary$' "$ENV_FILE"
}

@test "the model id matches the payload's served alias wiring" {
    # The payload dir and its shard count are the fetch script's output
    # layout; the fetch script must write where the env points.
    grep -q '^FRANK_PRIMARY_MODEL_DIR=/home/dank/models/Qwen3.8-Flash-Next-Uncensored-FP8$' "$ENV_FILE"
    grep -q '^FRANK_PRIMARY_MODEL_SHARDS=131$' "$ENV_FILE"
    grep -q 'Qwen3.8-Flash-Next-Uncensored-FP8' "$DOWNLOAD"
    grep -q 'orcarouter/Qwen3.8-Flash-Next-Uncensored-FP8' "$DOWNLOAD"
}

@test "no bare HIP-reserved env var is defined" {
    # HIP reads bare TEMP for its JIT cache path (2026-08-13: TEMP=1.0
    # segfaulted every load), and HOST/GPU_MAX_HEAP_SIZE are the same
    # class. Every key here is FRANK_PRIMARY_-prefixed.
    ! grep -qE '^(TEMP|HOST|GPU_MAX_HEAP_SIZE)=' "$ENV_FILE"
    ! grep -qE '^(export )?(TEMP|HOST|GPU_MAX_HEAP_SIZE)=' "$SERVE"
}

@test "the deployer gates the image digest and payload, then health-checks" {
    # The deployer refuses when the pinned image is absent from rootless
    # storage or the payload is missing/wrong-sharded — then clears stale
    # containers (including the legacy identities), waits out the port,
    # relinks/enables/restarts the root unit and health-gates it.
    grep -q 'LLM_PRIMARY_CONTAINER=frank-primary-qwen' "$REMOTE_DEPLOY"
    grep -q 'FRANK_PRIMARY_IMAGE' "$REMOTE_DEPLOY"
    grep -q "podman images --format '{{.RepoDigests}}'" "$REMOTE_DEPLOY"
    grep -q 'FRANK_PRIMARY_MODEL_SHARDS' "$REMOTE_DEPLOY"
    grep -q 'config.json' "$REMOTE_DEPLOY"
    grep -q 'qwen-fp8' "$REMOTE_DEPLOY"
    grep -q 'glm-probe' "$REMOTE_DEPLOY"
    grep -q 'wait_port_free 7770' "$REMOTE_DEPLOY"
    grep -q 'relink_unit frank-primary' "$REMOTE_DEPLOY"
    grep -q 'systemctl enable frank-primary.service' "$REMOTE_DEPLOY"
    grep -q 'systemctl restart frank-primary.service' "$REMOTE_DEPLOY"
    grep -q 'wait_for_health frank-primary http://127.0.0.1:7770/health 1800' "$REMOTE_DEPLOY"
}

@test "the deployer will not report green on a stray port-holder" {
    # The 2026-09-26 false green: a leftover probe held :7770 and satisfied
    # the health curl while the real unit was stopped. The deploy is only
    # green when the unit's own MainPID is live behind the health answer.
    grep -q 'systemctl show -p MainPID --value frank-primary.service' "$REMOTE_DEPLOY"
    grep -q 'stray process holds the port' "$REMOTE_DEPLOY"
}