#!/usr/bin/env bats
# Seam: the frank-large Kairic Edge root unit on dankclaw.
#
# The 2026-09-21 cutover moved this service from the unsloth llama.cpp
# prebuilt (b11030-mix-5ff778e, ROCm gfx1151) serving
# unsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ4_XS onto the Kairic Edge runtime
# (ciru-ai/ROCmFPX, branch kairic-edge-qwen38-27b-v1.2, commit 205a3e5)
# serving jcbtc/Qwen3.8-27B-IU4-Kairic-Edge, still as a ROOT unit: a
# source-built runtime has no container image to install and no generated
# unit to dodge. This seam pins what a flag list cannot show: the
# operator's one-stream / full-window shape, the payload the serve script
# refuses to start without, the MTP + n-gram spec wiring (DFlash is NOT
# available for this model), compatibility mode (the harness needs
# sampling/tools/reasoning, which fast-greedy rejects), a deploy handler
# that gates on the port, and the fact that the sweep for a stray
# benchmark run cannot take frank-small down with it.

load helpers

ENV_FILE="$REPO_ROOT/scripts/frank-large.env"
UNIT="$REPO_ROOT/scripts/frank-large.service"
SERVE="$REPO_ROOT/scripts/serve-frank-large.sh"
FETCH="$REPO_ROOT/scripts/download-frank-large-kairic.sh"
BUILD="$REPO_ROOT/scripts/build-kairic-edge-gfx1151.sh"
REMOTE_DEPLOY="$REPO_ROOT/scripts/deploy-remote.sh"

@test "the frank-large unit, env, serve and build files exist where the deployer installs them from" {
    [ -f "$ENV_FILE" ]
    [ -f "$UNIT" ]
    [ -x "$SERVE" ]
    [ -f "$BUILD" ]
}

@test "frank-large is boot-persistent, self-healing and unprivileged" {
    grep -q '^WantedBy=multi-user.target$' "$UNIT"
    grep -q '^Restart=on-failure$' "$UNIT"
    grep -q '^RestartSec=' "$UNIT"
    grep -q '^User=dank$' "$UNIT"
    # The engine pins staging buffers; the memlock budget must be unbounded
    # or the load fails on the RLIMIT.
    grep -q '^LimitMEMLOCK=infinity$' "$UNIT"
    # The unit runs the repo's own serve script with the repo's env.
    grep -q 'ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-large.sh' "$UNIT"
    grep -q 'FRANK_LARGE_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-large.env' "$UNIT"
}

@test "the operator's shape is one stream of the full 262144 window with MTP depth 4" {
    local ctx slots
    ctx="$(sed -nE 's/^CONTEXT_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")"
    slots="$(sed -nE 's/^PARALLEL_SLOTS=([0-9]+)$/\1/p' "$ENV_FILE")"
    # 262144 is the model's native window (the operator's call, 2026-09-21).
    [ "$ctx" -eq 262144 ]
    # One stream.
    [ "$slots" -eq 1 ]
    # MTP depth 4 (the model's MTP layers) + n-gram drafting (24/64/64).
    grep -q '^SPEC_DRAFT_N_MAX=4$' "$ENV_FILE"
}

@test "the harness needs compatibility mode (sampling, tools, reasoning)" {
    # The fast-greedy path rejects sampling, penalties, probabilities,
    # grammar-constrained tool calls, logit bias, LoRA and a reasoning
    # budget. The harness needs all three, so COMPATIBILITY_MODE=1.
    grep -q '^COMPATIBILITY_MODE=1$' "$ENV_FILE"
    # The serve script enables the fastpath off in compatibility mode.
    grep -q 'LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=0' "$SERVE"
}

@test "frank-large stays text-only" {
    # The Kairic Edge model is text-only (no vision projector). The fleet's
    # image path is frank-small; models.yml declares frank-large text-only.
    ! grep -q -- '--mmproj' "$SERVE"
    grep -q -- '--mmproj' "$REPO_ROOT/scripts/serve-frank-small.sh"
}

@test "the serve script pins the Kairic Edge runtime and refuses a missing build" {
    grep -q 'ROCmFPX-kairic' "$SERVE"
    grep -q 'llama-server' "$SERVE"
    # A missing runtime or payload is a deploy error with a pointer, not a
    # restart loop.
    grep -q 'Kairic Edge runtime not found' "$SERVE"
    grep -q 'missing asset' "$SERVE"
    # The Qwen3.8 template keeps prior thinking blocks across turns only
    # when the kwarg is set.
    grep -q 'preserve_thinking' "$SERVE"
}

@test "the serve script wires the MTP + n-gram spec method and the sidecars" {
    # The Kairic Edge model uses native MTP depth 4 + n-gram drafting
    # (24/64/64). DFlash is NOT available for this model (no DRAFT_DFLASH
    # spec type in the Kairic Edge runtime).
    grep -q -- '--spec-type draft-mtp' "$SERVE"
    grep -q -- '--kairic-edge' "$SERVE"
    grep -q -- '--spec-draft-n-max' "$SERVE"
    # The three PromptForge sidecars (FFN, GDN, GDN-Output) are wired via
    # the PROMPTFORGE_* env block.
    grep -q 'PROMPTFORGE_IU4_SIDECAR' "$SERVE"
    grep -q 'PROMPTFORGE_GDN_SIDECAR' "$SERVE"
    grep -q 'PROMPTFORGE_GDN_OUTPUT_SIDECAR' "$SERVE"
}

@test "the payload is fetched resumably and verified against declared sizes + sha256" {
    grep -q 'jcbtc/Qwen3.8-27B-IU4-Kairic-Edge' "$FETCH"
    grep -q -- '-fL -C -' "$FETCH"
    # Each file's local sha256 is compared to its declared oid and a
    # mismatch fails the run.
    grep -q 'SHA256 MISMATCH' "$FETCH"
}

@test "the build script pins the Kairic Edge commit and the CK patch" {
    grep -q 'fdf4bb7fcc984811cef48ce817d89aac064b984a' "$BUILD"
    grep -q 'composable-kernel-gfx1151-iu4.patch' "$BUILD"
    grep -q 'gfx1151' "$BUILD"
}

@test "the fleet endpoint and alias survive the cutover" {
    grep -q '^HOST=0.0.0.0$' "$ENV_FILE"
    grep -q '^PORT=7770$' "$ENV_FILE"
    grep -q '^MODEL_DIR=/home/dank/models/Qwen3.8-27B-IU4-Kairic-Edge$' "$ENV_FILE"
    grep -q -- '--alias frank-large' "$SERVE"
}

@test "the deploy handler retires the halogen quadlet without deleting it" {
    grep -q 'retire_halogen_large_quadlet' "$REMOTE_DEPLOY"
    grep -q 'HOME/.AGENTTRASH' "$REMOTE_DEPLOY"
    ! grep -qE '(^|[^[:alnum:]_])rm (-[a-zA-Z]+ )?.*frank-large' "$REMOTE_DEPLOY"
}

@test "the deploy handler installs the root unit, gates the port and refuses a missing payload" {
    grep -q 'relink_unit frank-large' "$REMOTE_DEPLOY"
    grep -q 'systemctl enable frank-large.service' "$REMOTE_DEPLOY"
    grep -q 'wait_port_free 7770' "$REMOTE_DEPLOY"
    grep -q '127.0.0.1:7770/health' "$REMOTE_DEPLOY"
    grep -q 'LLM_LARGE_MODEL' "$REMOTE_DEPLOY"
    grep -q 'LLM_LARGE_DRAFT' "$REMOTE_DEPLOY"
}

@test "the stray-run sweep cannot take frank-small down" {
    # frank-small on this host is ALSO a llama-server. The sweep must match
    # the model path, not the binary name, or a frank-large deploy restarts
    # the 3090 endpoint.
    grep -q "pkill -f 'Qwen3.8-27B-IU4-Kairic-Edge'" "$REMOTE_DEPLOY"
    # ...and only inside the large handler: extract it and check there is no
    # bare binary-name pkill in it.
    local large
    large="$(sed -n '/^deploy_llm_large() {/,/^}/p' "$REMOTE_DEPLOY")"
    ! grep -q 'pkill -x llama-server' <<<"$large"
}

@test "the halogen quadlet is archived, not live" {
    [ ! -e "$REPO_ROOT/dankclaw/frank-large/quadlet/frank-large.container" ]
    [ -f "$REPO_ROOT/dankclaw/.AGENTTRASH/frank-large.container.halogen" ]
}