# frank-tts-engine — the arm A TTS engine: qwentts.cpp's resident `tts-server`
# (the CPU binary that frank-tts on :7772 forwards to). The runbook is
# [[Frank TTS Engine]]; the fleet-facing endpoint is [[Frank TTS]].
#
# WHAT THIS IS. The upstream source is NOT vendored here: the image clones
# ServeurpersoCom/qwentts.cpp at one pinned commit and builds it. Rebuilding is
# therefore a network operation (github.com plus objects.githubusercontent.com
# for the `ggml` submodule), and build_compose_image in scripts/deploy-remote.sh
# skips it whenever this Containerfile's sha256 label already matches the built
# image — the same offline-safe idiom as loki/alloy/comfyui, so a re-deploy of
# an unchanged engine needs no network.
#
# THE PINNED COMMIT IS THE CONTRACT. 5916bf7c79dbb4e66fc059cdc507a79a23a28bb4
# is the commit the 2026-10-18 CPU trial on Dankclaw measured (server-side TTFA
# 94-112 ms, warm RTF 0.55-0.67, run spread +-0.01 — the numbers that won the
# engine decision). Moving it means re-measuring, not just editing this line.
# `ggml` is a submodule of the repo (the only one; vendor/cpp-httplib and
# vendor/yyjson are ordinary directories in the tree), and the submodule commit
# is recorded in the parent tree, so cloning the parent commit recursively is
# reproducible without a second pin.
#
# THE BUILD LINE IS THE ONE PROVEN ON DANKCLAW, verbatim:
#
#   cmake -B build -DCMAKE_BUILD_TYPE=Release -DGGML_CCACHE=OFF \
#       -DGGML_BACKEND_DL=OFF -DGGML_CPU_ALL_VARIANTS=OFF -DGGML_OPENMP=ON \
#       -DGGML_BLAS=OFF -DGGML_CUDA=OFF -DGGML_HIP=OFF -DGGML_VULKAN=OFF \
#       -DGGML_METAL=OFF -DGGML_SYCL=OFF -DGGML_RPC=OFF \
#   && cmake --build build -j 8
#
# Every flag is load-bearing, so do not "tidy" it:
#   GGML_BLAS=OFF is FORCED, not a preference — Dankclaw has libopenblas.so.0
#     but no BLAS dev headers, so the upstream default (BLAS on) fails to
#     configure. Upstream's own Dockerfile and buildcpu.sh both pass BLAS on,
#     which is why this file does not copy them.
#   GGML_CCACHE=OFF because a container build layer has no persistent ccache
#     directory to hit; on, it only writes a useless one.
#   GGML_OPENMP=ON is what makes the runtime need libgomp1 (installed below).
#   GGML_BACKEND_DL=OFF / GGML_CPU_ALL_VARIANTS=OFF: upstream's images build
#     every x86 ISA as a loadable backend so one image runs anywhere. This one
#     is built on the machine that runs it, so the single native CPU backend is
#     what was measured. That is also why no -DGGML_NATIVE is passed: ggml
#     defaults it ON outside wasm/cross-compiles, i.e. -march=native for THIS
#     host — correct while build host == run host, wrong if anyone ever builds
#     this image elsewhere, which is why the fleet builds it on Dankclaw.
#   CUDA/HIP/VULKAN/METAL/SYCL/RPC all OFF: this is a CPU endpoint (the trial
#     ran on CPU; the box's GPUs belong to the text endpoints).
#
# BUILD SHARED LIBS, RUNTIME SMALL. BUILD_SHARED_LIBS defaults ON on Linux, so
# tts-server links libggml*.so rather than swallowing them; the runtime stage
# copies the binary and its shared objects out of the build tree and points
# LD_LIBRARY_PATH at them, exactly as upstream's own Dockerfile does (the RPATH
# baked at link time names the build directory, which does not exist here).
#
# BASE PINNED BY DIGEST, like every other image this fleet builds: the digest
# is the multi-arch INDEX of ubuntu:24.04 as resolved from Docker Hub on
# 2026-10-18; Dankclaw takes the amd64 entry. One base for both stages so there
# is exactly one thing to re-resolve.
#
# NO HEALTHCHECK IN THIS FILE. The probe lives in the Quadlet unit
# (HealthCmd=), which is the fleet pattern for anything with a shell — see the
# alertmanager/prometheus units, and the opposite case in dankclaw/loki, whose
# distroless image has no /bin/sh for the generator's CMD-SHELL wrapping.
# `curl` is therefore installed in the runtime stage, for that probe only.

ARG BASE_IMAGE=docker.io/library/ubuntu:24.04@sha256:68ee22004a9109b44973313b02ff7b1de250f1de0f5ecb628d73f579aaff33ac

# ------------------------------------------------------------------ build
FROM ${BASE_IMAGE} AS build

RUN apt-get update -qq \
    && apt-get install -y -qq --no-install-recommends \
        ca-certificates cmake g++ git make \
    && rm -rf /var/lib/apt/lists/*

# Checked out detached at a full SHA, then the recorded submodule. No branch
# name anywhere: a branch moves, this commit does not.
ARG QWENTTS_COMMIT=5916bf7c79dbb4e66fc059cdc507a79a23a28bb4
RUN git clone --no-checkout https://github.com/ServeurpersoCom/qwentts.cpp /src \
    && git -C /src checkout --detach "${QWENTTS_COMMIT}" \
    && git -C /src submodule update --init --depth 1 \
    && git -C /src rev-parse HEAD \
    && git -C /src submodule status

WORKDIR /src
RUN cmake -B build -DCMAKE_BUILD_TYPE=Release \
        -DGGML_CCACHE=OFF \
        -DGGML_BACKEND_DL=OFF \
        -DGGML_CPU_ALL_VARIANTS=OFF \
        -DGGML_OPENMP=ON \
        -DGGML_BLAS=OFF \
        -DGGML_CUDA=OFF \
        -DGGML_HIP=OFF \
        -DGGML_VULKAN=OFF \
        -DGGML_METAL=OFF \
        -DGGML_SYCL=OFF \
        -DGGML_RPC=OFF \
    && cmake --build build -j 8

# ---------------------------------------------------------------- runtime
FROM ${BASE_IMAGE}

# libgomp1: the OpenMP runtime the build above links against. curl: the unit's
# HealthCmd. ca-certificates: so that curl can speak https if anyone ever
# points a probe at a URL with a scheme this host terminates elsewhere.
RUN apt-get update -qq \
    && apt-get install -y -qq --no-install-recommends \
        ca-certificates curl libgomp1 \
    && rm -rf /var/lib/apt/lists/*

# Same unprivileged uid as the frank-tts façade (10000): the voice packs and the
# model directory are host state mounted read-only, and one uid across the pair
# means one thing to remember about what is world-readable.
RUN adduser --system --uid 10000 --home /app --shell /usr/sbin/nologin tts

WORKDIR /app
COPY --from=build /src/build/tts-server /src/build/*.so* /app/
COPY dankclaw/voiceservice/tts-engine-start.sh /app/start.sh
# The boot warmer lives INSIDE the image because the engine publishes no port:
# the unit reaches it with `podman exec`, and the script needs the same curl,
# base64 and /voices the engine's own namespace has. It is a sibling of
# start.sh, not a second entrypoint — CMD stays the server.
COPY dankclaw/voiceservice/tts-engine-warm.sh /app/warm-voices.sh
RUN chmod 755 /app/start.sh /app/warm-voices.sh

# The binary's RPATH points inside the build tree; this is what makes it find
# the libggml*.so copied beside it.
ENV LD_LIBRARY_PATH=/app

USER tts
EXPOSE 8880
CMD ["/app/start.sh"]