#!/usr/bin/env bash
# Serve jcbtc/Qwen3.8-Flash-CIRU-STRIX-Orca as frank-large on Dankclaw's
# Strix Halo iGPU (gfx1151), using the CIRU v4.4.1 runtime with the QSA
# window hotfix.
#
# Runtime: the v4.4.1 source with the QSA window hotfix pre-applied
# (ciru-runtime-v4.4.1-qsa-hotfix-source.tar.gz, shipped in the model repo
# under runtime/v4.4.1/qsa-window-hotfix/), built ON the host against the
# private ROCm 10.0.0 SDK that scripts/ciru/setup-linux-amd.sh installs into
# the runtime checkout's own venv. The launcher below re-verifies on every
# start that the built libraries carry the v4.4.1 corrections (it greps the
# common and HIP libraries for the fix markers) before exec.
#
# The launcher owns the flag list: -sm none (one iGPU, no split), -ngl all,
# f16 KV, flash attention, cont-batching, the PLE sidecar, the MTP drafter
# (depth 4 for the Orca variant) and the production kernel-bundle profile.
# Tunables come from frank-large.env unless FRANK_LARGE_ENV_FILE overrides it;
# anything not set there falls through to the launcher's own defaults.
#
# It replaces the halogen-flash-server quadlet, which served
# peonist-ai/halogen-qwen3.8-flash-next on this same iGPU since 2026-09-16.
set -euo pipefail

SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
ENV_FILE="${FRANK_LARGE_ENV_FILE:-$SCRIPT_DIR/frank-large.env}"
if [[ -f "$ENV_FILE" ]]; then
    set -a
    # shellcheck disable=SC1090
    source "$ENV_FILE"
    set +a
fi

# --- defaults (used when the env file does not set them) ------------------
: "${RUNTIME_DIR:=/home/dank/GitPackages/ciru-runtime-v4.4.1-qsa-hotfix}"
: "${MODEL_DIR:=/home/dank/models/Qwen3.8-Flash-CIRU-STRIX-Orca}"
: "${HOST:=0.0.0.0}"
: "${PORT:=7770}"
: "${CONTEXT_SIZE:=262144}"
: "${PARALLEL_SLOTS:=1}"

LAUNCHER="$RUNTIME_DIR/scripts/ciru/run-orca-server.sh"
SERVER_BIN="$RUNTIME_DIR/build-gfx1151-sdk/bin/llama-server"

if [[ ! -x "$LAUNCHER" ]]; then
    echo "missing runtime launcher: $LAUNCHER" >&2
    echo "fetch the hotfix source tarball from the model repo" >&2
    echo "(runtime/v4.4.1/qsa-window-hotfix/) and build it:" >&2
    echo "  bash $RUNTIME_DIR/scripts/ciru/setup-linux-amd.sh --install-host-deps" >&2
    exit 1
fi
if [[ ! -x "$SERVER_BIN" ]]; then
    echo "missing built runtime: $SERVER_BIN" >&2
    echo "build it: bash $RUNTIME_DIR/scripts/ciru/setup-linux-amd.sh --install-host-deps" >&2
    exit 1
fi

# The launcher gates on a runtime root holding hip/lib/libamdhip64.so and
# rocr/lib/libhsa-runtime64.so (it prepends both to LD_LIBRARY_PATH). Our
# build links the private SDK venv through its RUNPATH, so point those
# entries at the venv's unversioned devel symlinks. Idempotent: ln -sfn.
VENV_LIB="$(ls -d "$RUNTIME_DIR"/.venv-rocm/lib/python*/site-packages/_rocm_sdk_devel/lib 2>/dev/null | head -1 || true)"
if [[ -z "$VENV_LIB" || ! -e "$VENV_LIB/libamdhip64.so" || ! -e "$VENV_LIB/libhsa-runtime64.so" ]]; then
    echo "missing SDK venv runtime under $RUNTIME_DIR/.venv-rocm (libamdhip64.so, libhsa-runtime64.so)" >&2
    echo "build it: bash $RUNTIME_DIR/scripts/ciru/setup-linux-amd.sh --install-host-deps" >&2
    exit 1
fi
mkdir -p "$RUNTIME_DIR/runtime/hip/lib" "$RUNTIME_DIR/runtime/rocr/lib"
ln -sfn "$VENV_LIB/libamdhip64.so" "$RUNTIME_DIR/runtime/hip/lib/libamdhip64.so"
ln -sfn "$VENV_LIB/libhsa-runtime64.so" "$RUNTIME_DIR/runtime/rocr/lib/libhsa-runtime64.so"
if [[ ! -r "$MODEL_DIR/Qwen3.8-Flash-CIRU-STRIX-Orca.gguf" ]]; then
    echo "missing target model: $MODEL_DIR/Qwen3.8-Flash-CIRU-STRIX-Orca.gguf" >&2
    echo "fetch and assemble it: bash $SCRIPT_DIR/download-frank-large-orca.sh" >&2
    exit 1
fi

# The launcher checks the MTP head and the PLE sidecar itself, but a missing
# payload should be a deploy error with a pointer, not a runtime exit 2.
for required in \
    "$MODEL_DIR/mtp/Qwen3.8-Flash-CIRU-STRIX-Orca-MTP-Q8_0.gguf" \
    "$MODEL_DIR/ple/ple.payload.bin" \
    "$MODEL_DIR/ple/ple.manifest.json" \
    "$MODEL_DIR/ple/ple.scale.bf16"; do
    if [[ ! -r "$required" ]]; then
        echo "missing payload: $required" >&2
        echo "fetch and assemble it: bash $SCRIPT_DIR/download-frank-large-orca.sh" >&2
        exit 1
    fi
done

# The Qwen3.8 family template keeps prior thinking blocks across turns when
# preserve_thinking is set; the launcher passes --jinja but no template
# kwargs, so name them here. A request-level chat_template_kwargs still
# wins over this.
exec "$LAUNCHER" --chat-template-kwargs '{"preserve_thinking":true}'