82a80e4063
`./sylph-agent loose [task]` starts Claude Code detached with
--dangerously-skip-permissions, running /loop on loop-task.md: work the RE
backlog one item at a time, commit to auto/* branches, never push, record
withdrawn results rather than deleting them. `logs`/`attach`/`stop` to watch and
end it. Runs -d WITHOUT --rm so the transcript survives the container exiting —
for an unattended run that is the only record of what happened.
Two things had to be fixed for an agent to survive being left alone.
MEMORY CONTINUITY. The project is now bind-mounted twice: at /work, and at its
own host path. Claude Code derives its per-project state key from the working
directory, so running at /work handed the agent an empty project instead of the
accumulated one. Verified: a loose run now reports MEMORY=yes and reads back the
same branch and backlog as the host.
FOUR INTERACTIVE GATES, each a silent permanent hang with nobody at the keyboard
-- no error, no log line, just a container that looks healthy and does nothing:
theme picker hasCompletedOnboarding + lastOnboardingVersion. Re-fires
whenever the container's Claude Code is a different version
to the host's, which is the normal case.
folder trust projects.<path>.hasTrustDialogAccepted
bypass disclaimer answered in a pty by bin/claude-autonomous. It has no config
key by design -- it wants a person to accept once, and the
person did so by launching this.
fullscreen upsell fullscreenUpsellSeenCount. This one fires MID-SESSION, after
the pty wrapper has already handed over, so it cannot be
answered the same way.
Config key names were read out of the shipped binary's own strings, not guessed.
The pty wrapper matches SINGLE WORDS. Claude Code draws its UI with
absolute-column escapes between words, so the prompt arrives as
`Yes,\x1b[13GI\x1b[15Gaccept` and a multi-word pattern never matches -- failing
in a way indistinguishable from the wrapper not running at all. It stops
matching once the session is live so nothing later is answered by accident.
~/.claude.json is now mounted read-only at a staging path and copied in, so the
container cannot rewrite the host config. Credentials stay shared read-write in
~/.claude, which is what token refresh and memory continuity need.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
126 lines
6.4 KiB
Bash
Executable File
126 lines
6.4 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Bring up the headless display, then hand over to the command.
|
|
#
|
|
# Xvfb and openbox are started HERE, as children of PID 1 (tini), rather than by
|
|
# the toolkit scripts. That is the fix for the long-standing "Xvfb and the
|
|
# emulator die on their own every few minutes" note: nothing owned those
|
|
# processes, so nothing kept them alive, and a run could sit for 300 s in front
|
|
# of a visible MAIN MENU reporting "no main menu" because the display had gone.
|
|
# A container-lifetime display makes that failure mode impossible.
|
|
set -euo pipefail
|
|
|
|
log() { printf '[entrypoint] %s\n' "$*" >&2; }
|
|
|
|
DISPLAY="${DISPLAY:-:98}"
|
|
GEOM="${SCREEN_GEOMETRY:-1280x720x24}"
|
|
export DISPLAY
|
|
|
|
# ── Display ──────────────────────────────────────────────────────────────────
|
|
if ! xdpyinfo -display "$DISPLAY" >/dev/null 2>&1; then
|
|
rm -f "/tmp/.X${DISPLAY#:}-lock" "/tmp/.X11-unix/X${DISPLAY#:}" 2>/dev/null || true
|
|
# GLX and RANDR are both required: Canary's window is GTK+OpenGL even when the
|
|
# graphics backend is Vulkan, and xwininfo-based screen oracles need RANDR.
|
|
Xvfb "$DISPLAY" -screen 0 "$GEOM" -ac -nolisten tcp \
|
|
+extension GLX +extension RANDR >/tmp/xvfb.log 2>&1 &
|
|
for _ in $(seq 1 50); do
|
|
xdpyinfo -display "$DISPLAY" >/dev/null 2>&1 && break
|
|
sleep 0.2
|
|
done
|
|
fi
|
|
if ! xdpyinfo -display "$DISPLAY" >/dev/null 2>&1; then
|
|
log "FATAL: no display on $DISPLAY — see /tmp/xvfb.log"
|
|
exit 1
|
|
fi
|
|
|
|
# A window manager is not cosmetic here: without one the emulator window is
|
|
# never mapped at a known position, and every pixel oracle reads the wrong rows.
|
|
if ! pgrep -x openbox >/dev/null 2>&1; then
|
|
openbox >/tmp/openbox.log 2>&1 &
|
|
sleep 0.5
|
|
fi
|
|
log "display $DISPLAY ready ($GEOM)"
|
|
|
|
# ── Vulkan ───────────────────────────────────────────────────────────────────
|
|
# Prefer the real GPU when /dev/dri was passed through; fall back to lavapipe,
|
|
# which is slow but correct and needs no host device.
|
|
LVP=$(ls /usr/share/vulkan/icd.d/lvp_icd*.json 2>/dev/null | head -1)
|
|
if [ "${SYLPH_VULKAN:-auto}" = "sw" ] || [ ! -e /dev/dri/renderD128 ]; then
|
|
[ -n "$LVP" ] && export VK_ICD_FILENAMES="$LVP"
|
|
else
|
|
unset LIBGL_ALWAYS_SOFTWARE
|
|
fi
|
|
# Report what Vulkan ACTUALLY enumerated, not what we asked for. Announcing
|
|
# "host GPU via /dev/dri" because the device node exists is how an agent ends up
|
|
# believing it has hardware while running llvmpipe — an NVIDIA card needs the
|
|
# NVIDIA Container Toolkit, and /dev/dri alone does nothing for it.
|
|
if command -v vulkaninfo >/dev/null 2>&1; then
|
|
vkdev=$(vulkaninfo --summary 2>/dev/null | awk -F= '/deviceName/{gsub(/^ +| +$/,"",$2); print $2; exit}')
|
|
case "${vkdev:-}" in
|
|
"") log "Vulkan: NO DEVICE — vulkaninfo enumerated nothing" ;;
|
|
llvmpipe*|lavapipe*) log "Vulkan: $vkdev (SOFTWARE — correct but slow)" ;;
|
|
*) log "Vulkan: $vkdev (hardware)" ;;
|
|
esac
|
|
fi
|
|
|
|
# ── Build parallelism ────────────────────────────────────────────────────────
|
|
# Bounded by MEMORY, not just cores. A full-parallel build of this tree has
|
|
# OOM-killed the host outright, and inside a half-the-box container the ceiling
|
|
# is lower still. ~1.5 GiB per C++ TU is the rule of thumb that has held.
|
|
# nproc reports the HOST's core count: --cpus is a CFS quota, not a mask. Using
|
|
# it would oversubscribe a half-the-box container by exactly 2x, so read the
|
|
# quota the cgroup actually grants.
|
|
cpus=$(nproc)
|
|
if [ -r /sys/fs/cgroup/cpu.max ]; then
|
|
read -r _q _p < /sys/fs/cgroup/cpu.max || true
|
|
if [ "${_q:-max}" != max ] && [ "${_p:-0}" -gt 0 ]; then
|
|
cpus=$(( (_q + _p - 1) / _p ))
|
|
[ "$cpus" -lt 1 ] && cpus=1
|
|
fi
|
|
fi
|
|
mem_gib=$(awk '/MemAvailable/{printf "%d", $2/1048576}' /proc/meminfo)
|
|
# MemAvailable is the HOST's too under cgroup v2; prefer the container's cap.
|
|
if [ -r /sys/fs/cgroup/memory.max ]; then
|
|
_m=$(cat /sys/fs/cgroup/memory.max)
|
|
[ "$_m" != max ] && mem_gib=$(( _m / 1073741824 ))
|
|
fi
|
|
[ "${mem_gib:-0}" -lt 1 ] && mem_gib=1
|
|
by_mem=$(( mem_gib * 2 / 3 ))
|
|
[ "$by_mem" -lt 1 ] && by_mem=1
|
|
jobs=$(( cpus < by_mem ? cpus : by_mem ))
|
|
export SYLPH_JOBS="$jobs" CARGO_BUILD_JOBS="$jobs" CMAKE_BUILD_PARALLEL_LEVEL="$jobs"
|
|
log "build parallelism: $jobs (cpus=$cpus, mem=${mem_gib}GiB avail)"
|
|
|
|
mkdir -p "$HOME/shots" "$HOME/logs"
|
|
|
|
# ── Claude Code config ───────────────────────────────────────────────────────
|
|
# Seed ~/.claude.json from the host's read-only copy, then stamp onboarding as
|
|
# complete. Claude Code re-runs its first-run wizard whenever
|
|
# lastOnboardingVersion differs from the installed version — so a container with
|
|
# a newer Claude than the host stops on the theme picker, with no error and no
|
|
# log line, and an unattended agent sits there forever.
|
|
if [ -f "$HOME/.claude.host.json" ] && [ ! -s "$HOME/.claude.json" ]; then
|
|
cp "$HOME/.claude.host.json" "$HOME/.claude.json" 2>/dev/null || true
|
|
fi
|
|
CLAUDE_VER=$(claude --version 2>/dev/null | grep -oE '^[0-9][0-9.]*' || echo 0.0.0)
|
|
python3 /usr/local/bin/seed-claude-config.py "$HOME/.claude.json" "$CLAUDE_VER" \
|
|
"$PWD" "${PROJECT_DIR:-/work}" "$HOME" || true
|
|
chmod 600 "$HOME/.claude.json" 2>/dev/null || true
|
|
|
|
# ── Claude Code ──────────────────────────────────────────────────────────────
|
|
if [ "${SYLPH_AUTONOMOUS:-0}" = "1" ]; then
|
|
# Drop the image's default CMD first, or `claude` is handed the literal string
|
|
# "bash" as its prompt and answers a question nobody asked.
|
|
if [ "$#" -eq 1 ] && [ "$1" = "bash" ]; then
|
|
set --
|
|
fi
|
|
# The flag the user asked for. It is refused under root, which is why this
|
|
# image runs as `agent`.
|
|
# claude-autonomous wraps `claude --dangerously-skip-permissions` in a pty and
|
|
# answers the one-time first-run gates. The Bypass Permissions disclaimer in
|
|
# particular has no config key that skips it, so unattended it hangs forever.
|
|
set -- claude-autonomous "$@"
|
|
log "starting Claude Code with --dangerously-skip-permissions in $(pwd)"
|
|
fi
|
|
|
|
exec "$@"
|