Sylpheed/docker/port/sylph-port

#!/usr/bin/env bash
# Launcher for the Godot port agent.
#
#   ./sylph-port build          build the image
#   ./sylph-port shell          interactive shell
#   ./sylph-port loose [task]   detached, self-running on a fixed interval
#   ./sylph-port logs -f        follow it
#   ./sylph-port attach         chat with it (Ctrl-P Ctrl-Q to leave it running)
#   ./sylph-port remote         a link to chat with it from anywhere
#   ./sylph-port stop           stop it
#
# Env:
#   SYLPH_PORT_CPUS / SYLPH_PORT_MEM_GB   override the cap (default 3 / 4)
#   SYLPH_PORT_REPO     repo to mount at /work (default: this script's parent)
#   SYLPH_DISC          extracted disc root
#   SYLPH_GIT_CREDENTIALS   file with `https://<user>:<token>@host` for push-work
#   SYLPH_LOOP_INTERVAL     fixed loop cadence (default 45m)
#
# ── Two hard-won constraints ────────────────────────────────────────────────
#
# 1. THIS REPO IS ITS OWN CLONE. It is deliberately NOT the tree the RE agent
#    or a human is working in. Sharing a working tree between two writers means
#    files change under whoever is mid-edit, and a `git add -A` by one sweeps up
#    the other's work. That happened; do not re-create it.
#
# 2. IDENTITY GOES IN THE ENVIRONMENT, NOT `.git/config`. Writing `[user]` into
#    a repo's config captures every commit made in that tree, including a
#    human's. GIT_AUTHOR_*/GIT_COMMITTER_* apply to this container's commits and
#    nobody else's.
set -euo pipefail

HERE="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
# The repo to mount at /work. Overridable so this script can be run from a
# worktree -- a human editing on `main` must not repoint the agent's checkout.
# The checkout is now a volume the container clones into, so this is only used
# to locate things that live BESIDE the repository -- the disc, chiefly. Three
# levels up from docker/port/ is the workspace root.
WORKSPACE="$(cd "$HERE/../../.." && pwd)"
IMAGE="${SYLPH_PORT_IMAGE:-sylpheed-port:latest}"
NAME="${SYLPH_PORT_NAME:-sylpheed-port}"

# Half of what the RE container takes. That container builds a C++ emulator and
# drives it; this one converts assets and runs Godot. Two full-size containers
# do not fit on a 12-core / 15 GB box beside a desktop -- memory is the binding
# constraint, and an over-committed build has crashed this machine before.
CPUS="${SYLPH_PORT_CPUS:-3}"
MEM_GB="${SYLPH_PORT_MEM_GB:-4}"

DISC="${SYLPH_DISC:-$(cd "$WORKSPACE/sylph_extract" 2>/dev/null && pwd || true)}"

docker_args() {
  local _out=(
    --name "$NAME"
    --hostname sylph-port
    --cpus "$CPUS"
    --memory "${MEM_GB}g"
    --memory-swap "${MEM_GB}g"     # no swap escape hatch: a swapping build
                                   # thrashes the whole host
    --pids-limit 2048
    -v "sylpheed-port-repo:/work"
    -v "sylpheed-port-target:/sylph-home/port/target-container"
    # CARGO_HOME on a volume, not the container overlay: without it the pinned
    # decoder source is re-fetched from the network on every fresh container.
    -v "sylpheed-port-cargo:/sylph-home/port/.cargo"
    -v "sylpheed-port-claude:/sylph-home/port/.claude"
    -v "${SYLPH_CLAUDE_HOME:-$HOME/.claude}:/sylph-home/port/.claude.seed:ro"
    -v "${SYLPH_CLAUDE_JSON:-$HOME/.claude.json}:/sylph-home/port/.claude.host.json:ro"
    -v "sylpheed-exchange:/exchange"
    -e "PROJECT_DIR=/work"
    # Same guardrail as the decoder, added the same day and for its reason: the
    # decoder was OOM-killed mid-task by a RAW `cargo test --release`, which
    # never reaches `build-export`/`build-reference-cli` and so never saw their
    # CARGO_BUILD_JOBS. This container is smaller (4 GB, 3 CPUs), so the same
    # bypass is at least as easy to hit here.
    -e "CARGO_BUILD_JOBS=${SYLPH_PORT_JOBS:-2}"
    -e "SYLPH_EXCHANGE=/exchange"
    -e "SYLPH_AGENT=port"
    -e "SYLPH_REPO_URL=https://git.mc02.dev/fabi/Sylpheed.git"
  )


  if [ -n "$DISC" ] && [ -d "$DISC" ]; then
    _out+=(-v "$DISC:/disc:ro" -e "SYLPHEED_DISC=/disc")
  else
    echo "==> NOTE: no extracted disc found; the exporter has nothing to read." >&2
    echo "    Set SYLPH_DISC to the directory holding dat/ and hidden/." >&2
  fi

  # Commits are attributed to the port agent, via the environment so that
  # nothing is written into the repository's config. See constraint 2 above.
  _out+=(
    -e "GIT_AUTHOR_NAME=Sylpheed port agent"
    -e "GIT_AUTHOR_EMAIL=port-agent@localhost"
    -e "GIT_COMMITTER_NAME=Sylpheed port agent"
    -e "GIT_COMMITTER_EMAIL=port-agent@localhost"
  )

  # Mounted as `.host` and copied to a writable file by the entrypoint, exactly
  # like .claude.json. `credential.helper=store` REWRITES its file after a
  # successful auth -- it writes a temp file and renames over the target, and
  # renaming onto a bind-mount point gives EBUSY, which surfaces as
  # `fatal: unable to write credential store: Device or resource busy`.
  #
  # The push still succeeds, which is the actual danger: a `fatal:` line that is
  # routinely wrong teaches the reader to ignore the one that is real. Mounting
  # rw would also silence it, but then the container can clobber the host's
  # credential file; copying cannot.
  # ── Claude auth ──
  # See the decoder's launcher for the full note. Short version: the OAuth
  # credential file holds a refresh token that ROTATES ON USE, three clients were
  # seeded from one copy, and the loser of a rotation race has its tokens CLEARED
  # to empty strings by Claude Code and parks at "Login expired". A long-lived
  # `claude setup-token` credential passed in the environment has nothing to
  # rotate and no file to empty. Same subscription, not API billing.
  # Inert until the file exists.
  local claudetok="${SYLPH_CLAUDE_TOKEN:-$HOME/.sylph-claude-token}"
  if [ -f "$claudetok" ]; then
    _out+=(-e "CLAUDE_CODE_OAUTH_TOKEN=$(tr -d '[:space:]' < "$claudetok")")
    echo "==> auth: long-lived token from $claudetok (no rotating credential file)" >&2
  fi

  local gitcred="${SYLPH_GIT_CREDENTIALS:-$HOME/.sylph-git-credentials}"
  if [ -f "$gitcred" ]; then
    _out+=(-v "$gitcred:/sylph-home/port/.git-credentials.host:ro")
  else
    echo "==> NOTE: no git credentials at $gitcred — the agent cannot push," >&2
    echo "    so its work dies with the container." >&2
  fi

  [ -n "${ANTHROPIC_API_KEY:-}" ] && _out+=(-e "ANTHROPIC_API_KEY=$ANTHROPIC_API_KEY")

  # ── GPU ──
  # This block did not exist until 2026-09-01, and its absence was reported as
  # a symptom rather than a cause: **the port agent reported low FPS.** Godot 4
  # renders through Vulkan, and with nothing passed through it was falling back
  # to lavapipe — software Vulkan, which is correct and slow. The decoder's
  # launcher had this logic; this one never did, so the container that actually
  # runs a renderer was the one without a GPU.
  #
  # Three distinct cases, and conflating them is how you end up believing you
  # have hardware Vulkan while running llvmpipe:
  #
  #   NVIDIA  needs the NVIDIA Container Toolkit (`--gpus all`). Passing
  #           /dev/dri alone does NOT work — Mesa cannot drive an NVIDIA card,
  #           and the proprietary userspace lives outside the image.
  #   Mesa    (AMD/Intel) works with a plain /dev/dri passthrough plus the
  #           host's render/video GIDs.
  #   neither software Vulkan (lavapipe): correct, and slow.
  if [ "${SYLPH_VULKAN:-auto}" = "sw" ]; then
    _out+=(-e SYLPH_VULKAN=sw)
  elif command -v nvidia-smi >/dev/null 2>&1 && nvidia-smi -L >/dev/null 2>&1; then
    if docker info --format '{{json .Runtimes}}' 2>/dev/null | grep -q nvidia; then
      _out+=(--gpus all)
    else
      echo "==> NOTE: NVIDIA GPU found but the NVIDIA Container Toolkit is not" >&2
      echo "    installed, so Godot falls back to lavapipe (software — correct," >&2
      echo "    slow, and the reason for any low-FPS report). To enable it:" >&2
      echo "      curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey \\" >&2
      echo "        | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg" >&2
      echo "      curl -fsSL https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list \\" >&2
      echo "        | sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' \\" >&2
      echo "        | sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list" >&2
      echo "      sudo apt update && sudo apt install -y nvidia-container-toolkit" >&2
      echo "      sudo nvidia-ctk runtime configure --runtime=docker" >&2
      echo "      sudo systemctl restart docker" >&2
      _out+=(-e SYLPH_VULKAN=sw)
    fi
  elif [ -e /dev/dri/renderD128 ]; then
    _out+=(--device /dev/dri)
    for g in render video; do
      gid=$(getent group "$g" | cut -d: -f3 || true)
      [ -n "$gid" ] && _out+=(--group-add "$gid")
    done
  else
    _out+=(-e SYLPH_VULKAN=sw)
  fi

  printf '%s\n' "${_out[@]}"
}

mapfile -t ARGS < <(docker_args)

case "${1:-}" in
  build)
    exec docker build -t "$IMAGE" \
      --build-arg "AGENT_UID=$(id -u)" --build-arg "AGENT_GID=$(id -g)" "$HERE"
    ;;

  shell)
    TTY=(-i); [ -t 0 ] && TTY=(-it)
    exec docker run --rm "${TTY[@]}" "${ARGS[@]}" "$IMAGE" bash
    ;;

  loose)
    shift
    TASK="${1:-}"
    if [ -z "$TASK" ]; then
      if [ -f "$HERE/../../docs/agents/port-loop.md" ]; then
        TASK="$(cat "$HERE/../../docs/agents/port-loop.md")"
      else
        TASK="Work the milestones in docs/MISSION.md."
      fi
    fi
    # A FIXED interval, not self-pacing: the one thing an agent deep in a
    # milestone reliably forgets is the bookkeeping after it, and a forgotten
    # wake-up silently ends the loop.
    INTERVAL="${SYLPH_LOOP_INTERVAL-45m}"
    echo "==> loose  |  cpus=$CPUS  mem=${MEM_GB}g  pacing=${INTERVAL:-self}"
    echo "==> repo:   own clone in volume sylpheed-port-repo -> /work"
    # `unless-stopped`, NOT `on-failure`: an OOM kill on this setup reports
    # `OOMKilled: true` with **ExitCode 0**, so `on-failure` would read a memory
    # kill as a clean finish and leave the agent down. Restarting into the same
    # death is handled in the entrypoint, which refuses to `--continue` when the
    # last start was under two minutes ago.
    docker run -d -i -t --restart unless-stopped "${ARGS[@]}" -e SYLPH_AUTONOMOUS=1 -w /work "$IMAGE" \
      "/loop ${INTERVAL:+$INTERVAL }$TASK" >/dev/null
    echo
    echo "    running detached as '$NAME'."
    echo "      ./sylph-port remote      link to chat with it from anywhere"
    echo "      ./sylph-port logs -f     follow it"
    echo "      ./sylph-port attach      chat with it locally"
    echo "      ./sylph-port stop        stop it"
    ;;

  logs)   shift; exec docker logs "$@" "$NAME" ;;
  attach) exec docker attach "$NAME" ;;
  stop)   exec docker rm -f "$NAME" ;;

  remote)
    echo "waiting for the session to register" >&2
    for _ in $(seq 60); do
      # Read the container LOG, not the session transcript. The transcript
      # records every command run inside the container -- including this
      # lookup -- so grepping it matched our own pattern string back.
      url=$(docker logs "$NAME" 2>&1 \
        | grep -aoE 'https://claude\.ai/code/session_[A-Za-z0-9]+' \
        | tail -1 || true)
      [ -n "$url" ] && { echo "$url"; exit 0; }
      sleep 2
    done
    echo "no session link yet — try ./sylph-port logs -f" >&2
    exit 1
    ;;

  *)
    sed -n '2,25p' "$0" | sed 's/^# \{0,1\}//'
    ;;
esac