Sylpheed/docker/port/entrypoint.sh

#!/usr/bin/env bash
# Bring up the headless display, then hand over.
#
# Xvfb and openbox are started as children of PID 1 (tini), NOT of the agent's
# shell, so they outlive any single command. The RE container learned this the
# hard way: a display owned by a shell gets reaped when that shell exits, which
# reads as "Xvfb dies on its own every few minutes".
set -euo pipefail

: "${DISPLAY:=:97}"
: "${SCREEN_GEOMETRY:=1280x720x24}"

if ! xdpyinfo -display "$DISPLAY" >/dev/null 2>&1; then
  Xvfb "$DISPLAY" -screen 0 "$SCREEN_GEOMETRY" -nolisten tcp &
  for _ in $(seq 50); do
    xdpyinfo -display "$DISPLAY" >/dev/null 2>&1 && break
    sleep 0.1
  done
  openbox >/dev/null 2>&1 &
fi
echo "[entrypoint] display $DISPLAY ready ($SCREEN_GEOMETRY)"


# ── Claude state: this agent's own, seeded once from the host ───────────────
# Isolated per agent. Both working directories are /work, and Claude Code keys
# its per-project state off the working directory -- so a SHARED ~/.claude put
# two independent agents in the same projects/-work/ directory, which undoes the
# point of giving them separate checkouts.
#
# Seeded rather than shared because credentials live in .credentials.json and a
# token refresh must be able to write. Copying once means each agent refreshes
# its own token and neither can corrupt the host's.
# Re-seed whenever the HOST's credentials are newer than ours, not only when
# ours are missing. The missing-only guard meant an expired token could never be
# replaced: the file existed, so the copy was skipped, and restarting the
# container changed nothing. A human re-logging in on the host is exactly the
# recovery path, and it has to reach here.
#
# Newer-wins rather than always-copy, because the container refreshes its own
# token during a run and that copy may legitimately be the fresher one.
# 🔴 A LONG-LIVED TOKEN WINS, AND THE SEEDING MUST NOT FIGHT IT. With
# CLAUDE_CODE_OAUTH_TOKEN set, copying the host's rotating credential file in
# would re-create the collision the token exists to remove: three clients on one
# rotating refresh token, and the loser of a rotation race gets its stored tokens
# CLEARED to empty strings by Claude Code and parks. Measured 2026-09-04.
# 🔴 PER-AGENT LOGIN: never seed. Set SYLPH_OWN_LOGIN=1 once this container
# has run `claude auth login` itself. Its grant is its OWN -- copying the
# host's over it re-creates the rotation collision that empties credentials
# and parks the session, which is the whole reason per-agent logins exist.
if [ -n "${SYLPH_OWN_LOGIN:-}" ] && [ "${SYLPH_OWN_LOGIN}" != "0" ]; then
  echo "[entrypoint] auth: this agent has its own login; not seeding from the host"
elif [ -n "${CLAUDE_CODE_OAUTH_TOKEN:-}" ]; then
  echo "[entrypoint] auth: long-lived token from the environment; not seeding OAuth"
elif [ -d "$HOME/.claude.seed" ] && \
   { [ ! -s "$HOME/.claude/.credentials.json" ] || \
     [ "$HOME/.claude.seed/.credentials.json" -nt "$HOME/.claude/.credentials.json" ]; }; then
  mkdir -p "$HOME/.claude"
  cp -a "$HOME/.claude.seed/.credentials.json" "$HOME/.claude/" 2>/dev/null || true
  for f in settings.json CLAUDE.md; do
    [ -e "$HOME/.claude.seed/$f" ] && cp -a "$HOME/.claude.seed/$f" "$HOME/.claude/" 2>/dev/null || true
  done
  echo "[entrypoint] refreshed ~/.claude credentials from the host"
fi

# 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 -- no error, 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

# Nothing is restored into `~/.claude.json` on purpose. Resuming is done by
# SESSION ID off the transcript instead — see the resume block below for why the
# index cannot serve.
# Same reason as .claude.json above: `credential.helper=store` rewrites this
# file by rename-over-target, which fails with EBUSY on a bind mount. Copy it to
# a writable path; nothing is ever written back to the host's file.
if [ -f "$HOME/.git-credentials.host" ]; then
  cp "$HOME/.git-credentials.host" "$HOME/.git-credentials" 2>/dev/null || true
  chmod 600 "$HOME/.git-credentials" 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

# ── The Gitea MCP server ─────────────────────────────────────────────────────
# Registered at USER scope rather than from a committed `.mcp.json`: the token
# differs per agent and none of it belongs in git.
#
# 🔴 THE TOKEN IS PASSED AS A PATH, NOT A VALUE. `-e GITEA_ACCESS_TOKEN=$(cat
# …)` would write the secret in cleartext into ~/.claude.json, where it is read
# by every session in this container and lands in any copy of that file.
# `GITEA_ACCESS_TOKEN_FILE` (gitea-mcp ≥ 1.7.0) leaves the token in its
# read-only mount and lets the server read it itself.
#
# Re-registered on every start, remove-then-add: `claude mcp add` refuses a name
# that already exists, and ~/.claude.json is re-seeded above — neither ordering
# survives alone.
GITEA_TOKEN_FILE="${GITEA_TOKEN_FILE:-$HOME/.sylph-gitea-token}"
GITEA_HOST_URL="${SYLPH_GITEA_HOST:-https://git.mc02.dev}"
# Which tools this agent gets. Deliberately not all of them:
#
#   * `pull_request_review_write` IS ABSENT, and that is the load-bearing one.
#     Gitea will not let an author approve its own pull request — but the moment
#     the two agents are separate people, nothing stops them approving each
#     OTHER's and satisfying `required_approvals` between themselves with no
#     human involved. Separate identities open that hole; withholding the tool
#     closes it here, and the approvals whitelist on `main` closes it there.
#   * the file / branch / repo WRITE tools are absent: a change reaches `main`
#     as a reviewable commit through git, or it does not reach it.
#
# `pull_request_write` bundles `merge` into one tool and cannot be split, so
# merging stays blocked where the agent cannot reach it — the merge whitelist in
# branch protection. This list is defence in depth BEHIND that, never instead.
GITEA_MCP_TOOLS="${SYLPH_GITEA_TOOLS:-get_me,notification_read,notification_write,list_issues,issue_read,issue_write,attachment_read,search_issues,label_read,milestone_read,list_pull_requests,pull_request_read,pull_request_write}"
if [ ! -s "$GITEA_TOKEN_FILE" ]; then
  echo "[entrypoint] no Gitea token at $GITEA_TOKEN_FILE — MCP not registered."
  echo "[entrypoint]   This agent cannot read its notifications or open a pull"
  echo "[entrypoint]   request, which is most of what its brief asks of it."
elif ! command -v gitea-mcp >/dev/null 2>&1; then
  echo "[entrypoint] gitea-mcp is not in this image — rebuild it." >&2
else
  claude mcp remove gitea -s user >/dev/null 2>&1 || true
  if claude mcp add -s user gitea \
       -e "GITEA_ACCESS_TOKEN_FILE=$GITEA_TOKEN_FILE" \
       -- gitea-mcp -t stdio -H "$GITEA_HOST_URL" -O "$GITEA_MCP_TOOLS" >/dev/null 2>&1; then
    echo "[entrypoint] gitea MCP registered against $GITEA_HOST_URL"
  else
    echo "[entrypoint] gitea MCP registration FAILED — the agent has no issues," >&2
    echo "[entrypoint]   no pull requests and no notifications." >&2
  fi
fi

# ── The repository, cloned into THIS AGENT'S OWN volume ─────────────────────
# Not a bind mount of a human's working tree. That arrangement bit this project
# three times: an agent's `git config --local` captured a human's commits, a
# credential helper leaked a container-only path onto the host, and a `git add
# -A` swept an agent's in-flight files into somebody else's commit. Separate
# checkouts make all three impossible rather than discouraged.
#
# Cloned ONCE. Never auto-pulled: pulling under a running agent moves files out
# from under whatever it is mid-edit, which is the same class of bug again.
if ! git -C /work rev-parse --verify HEAD >/dev/null 2>&1; then
  # Checks for a usable HEAD, not merely a .git directory. A clone interrupted
  # partway -- the container stopped while it ran, which has happened -- leaves
  # a .git with no commits, and a presence check would then skip the retry
  # forever and hand the agent an empty repository.
  echo "[entrypoint] cloning ${SYLPH_REPO_URL:-https://git.mc02.dev/fabi/Sylpheed.git} into /work"
  _tmp=$(mktemp -d)
  if git clone --quiet "${SYLPH_REPO_URL:-https://git.mc02.dev/fabi/Sylpheed.git}" "$_tmp/r"; then
    find /work -mindepth 1 -maxdepth 1 -exec rm -rf {} + 2>/dev/null || true
    mv "$_tmp/r"/.[!.]* "$_tmp/r"/* /work/ 2>/dev/null || true
    echo "[entrypoint] /work at $(git -C /work rev-parse --short HEAD) on $(git -C /work rev-parse --abbrev-ref HEAD)"
  else
    echo "[entrypoint] clone FAILED -- the agent has no repository" >&2
  fi
  rm -rf "$_tmp"
else
  echo "[entrypoint] /work at $(git -C /work rev-parse --short HEAD) on $(git -C /work rev-parse --abbrev-ref HEAD)"
fi

# The shared exchange, for transient files that must not enter git history.
mkdir -p /exchange/files 2>/dev/null || true

# ── Claude Code ──────────────────────────────────────────────────────────────
# Without this the loop prompt is handed to `exec` as a command, and the whole
# markdown file is tried as a filename: exit 126, "File name too long".
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 ] && [ "$1" = "bash" ]; then
    set --
  fi
  # ── Resume across a restart ────────────────────────────────────────────────
  #
  # The container restarts automatically now, and a restart that opens a BLANK
  # session throws away everything the agent knew.
  #
  # 🔴 RESUME BY SESSION ID, NOT BY `--continue`. Measured on the decoder
  # 2026-09-01: `--continue` resolves through `~/.claude.json`'s per-project
  # `history` / `lastSessionId`, and those are written at a GRACEFUL SHUTDOWN --
  # mid-session the live file has both as `None`. A container that is OOM-killed
  # or `docker rm -f`ed never writes them, which is exactly the case this exists
  # for, so `--continue` answered "No conversation found to continue" with the
  # transcripts sitting in the volume beside it.
  #
  # The TRANSCRIPTS are durable and named by session id. Claude Code has not
  # started yet here, so the newest is the previous run's.
  #
  # The /loop prompt is still passed so the loop is RE-ARMED rather than merely
  # restored -- a resumed conversation with no wake-up scheduled answers once
  # and stops, which looks like resuming and is not.
  SYLPH_STAMP="$HOME/.claude/.sylph-last-start"
  SYLPH_RESUME=0
  SYLPH_SESSION=""
  SYLPH_PROJ="$HOME/.claude/projects/$(printf '%s' "$PWD" | sed 's#/#-#g')"
  if [ -d "$SYLPH_PROJ" ]; then
    _newest=$(ls -1t "$SYLPH_PROJ"/*.jsonl 2>/dev/null | head -1)
    if [ -n "$_newest" ]; then
      SYLPH_SESSION=$(basename "$_newest" .jsonl)
      SYLPH_RESUME=1
    fi
  fi
  # 🔴 A POISONED TRANSCRIPT MUST NOT CRASH-LOOP. Restarted under two minutes
  # after the last start, we are already looping: continuing back into whatever
  # killed us is the one thing guaranteed not to help.
  if [ "$SYLPH_RESUME" = "1" ] && [ -f "$SYLPH_STAMP" ]; then
    _last=$(cat "$SYLPH_STAMP" 2>/dev/null || echo 0)
    _now=$(date +%s)
    if [ $((_now - _last)) -lt 120 ]; then
      SYLPH_RESUME=0
      echo "[entrypoint] restarted <120s after the last start -- restart loop"
      echo "[entrypoint]   suspected; starting FRESH rather than continuing"
    fi
  fi
  mkdir -p "$HOME/.claude" 2>/dev/null || true
  date +%s > "$SYLPH_STAMP" 2>/dev/null || true

  if [ "$SYLPH_RESUME" = "1" ] && [ "$#" -eq 1 ]; then
    set -- "$1

⚠️ YOU WERE RESTARTED, and this session was resumed — your context is intact,
but the process that was running when it died is gone. Before anything else:

1. \`git -C /work status\`. Whatever you had in progress is still in the tree,
   UNCOMMITTED. Commit it and \`push-work\` before starting anything new.
2. Any build, test, export or Godot run you had going did NOT finish. Do not
   read its absence as a result.
3. The likeliest cause is an OOM kill — this container is capped at 4 GB.
   \`CARGO_BUILD_JOBS\` is now set for you in the environment; do not raise it,
   and prefer \`build-export\` / \`build-reference-cli\` over a raw
   \`cargo build --release\`, which bypasses the wrapper's job cap. That is what
   killed the decoder's run on 2026-09-01."
    echo "[entrypoint] resuming session ${SYLPH_SESSION%%-*}… with a restart notice"
  fi
  # Tell the gate-answering wrapper to stand down: a resumed session cannot
  # show a first-run gate, and on 2026-09-04 its single-word patterns matched
  # the /loop prompt itself and typed "2" and "1" into a live session.
  [ "$SYLPH_RESUME" = "1" ] && export SYLPH_SKIP_GATES=1
  [ "$SYLPH_RESUME" = "1" ] && set -- --resume "$SYLPH_SESSION" "$@"

  # Remote Control registers the session with the account so the agent can be
  # reached from claude.ai -- the point of a detached run being that nobody is
  # sitting in front of it. The name is passed EXPLICITLY: the flag's value is
  # optional, so a bare --remote-control swallows the /loop prompt after it.
  if [ "${SYLPH_REMOTE:-1}" != "0" ]; then
    set -- --remote-control "${SYLPH_REMOTE_NAME:-sylpheed-port}" "$@"
    echo "[entrypoint] Remote Control as '${SYLPH_REMOTE_NAME:-sylpheed-port}'"
  fi
  # claude-autonomous wraps `claude --dangerously-skip-permissions` in a pty and
  # answers the one-time first-run gates. The Bypass Permissions disclaimer has
  # no config key that skips it, so unattended it hangs forever.
  set -- claude-autonomous "$@"
  echo "[entrypoint] starting Claude Code in $(pwd)"
fi

exec "$@"