fix(#1408): legacy-socket launch guard + seat launch.sh preference (#1409)
ci/woodpecker/push/publish Pipeline was canceled

Co-authored-by: veronica <[email protected]>
This commit was merged in pull request #1409.
This commit is contained in:
2026-08-25 00:49:27 +00:00
committed by orch-01
parent f45928c311
commit 8c292fb32f
3 changed files with 244 additions and 4 deletions
@@ -304,6 +304,17 @@ if [ "$MODE" = stop ]; then
exit 0 exit 0
fi fi
# #1408 hazard: a seat still living on the DEFAULT tmux socket is invisible to the
# declared-socket guard below, and launching over it creates a same-name duplicate that
# name-addressed comms delivery cannot tell apart. Refuse with a distinct code (76,
# after 75 broker-absent) so a cutover wave script can branch on "seat still on legacy
# socket" vs "already running" (0) vs "broker absent" (75). Stopping the legacy session
# belongs to the cutover procedure, never to this launcher.
if [ -n "$MOSAIC_TMUX_SOCKET" ] && tmux has-session -t "=${AGENT_NAME}" 2>/dev/null; then
echo "[fleet] FAIL_LAUNCH seat-on-legacy-socket: session '${AGENT_NAME}' exists on the DEFAULT tmux socket; stop it before launching on '${MOSAIC_TMUX_SOCKET}'." >&2
exit 76
fi
if _tmux has-session -t "=${AGENT_NAME}:0.0" 2>/dev/null; then if _tmux has-session -t "=${AGENT_NAME}:0.0" 2>/dev/null; then
echo "Mosaic agent session already running: $AGENT_NAME on socket ${MOSAIC_TMUX_SOCKET:-(default)}" echo "Mosaic agent session already running: $AGENT_NAME on socket ${MOSAIC_TMUX_SOCKET:-(default)}"
exit 0 exit 0
@@ -421,9 +432,22 @@ if [ "$MOSAIC_AGENT_RUNTIME" = claude ]; then
echo "WARNING: could not pre-trust workdir for claude agent $AGENT_NAME" >&2 echo "WARNING: could not pre-trust workdir for claude agent $AGENT_NAME" >&2
fi fi
LAUNCH_COMMAND=(mosaic yolo "$MOSAIC_AGENT_RUNTIME") # #1408 hazard: prefer the seat's own launch.sh when the brain provides one. It is the
if [ -n "$MOSAIC_AGENT_MODEL" ]; then LAUNCH_COMMAND+=(--model "$MOSAIC_AGENT_MODEL"); fi # path that binds the auth profile (CLAUDE_SECURESTORAGE_CONFIG_DIR) and seeds the seat
if [ -n "$MOSAIC_AGENT_REASONING" ]; then LAUNCH_COMMAND+=(--thinking "$MOSAIC_AGENT_REASONING"); fi # config; `mosaic yolo` relocates CLAUDE_CONFIG_DIR to the seat dir (launch.ts
# activeSeatDir/harnessEnv) but performs neither, so a yolo-launched seat points its
# config at a directory holding no credentials. The env -i allowlist below still
# applies: launch.sh reads its own launch.env.
SEAT_LAUNCH="${BRAIN_HOME}/fleet/agents/${AGENT_NAME}/launch.sh"
if [ -x "$SEAT_LAUNCH" ]; then
LAUNCH_COMMAND=("$SEAT_LAUNCH")
echo "[fleet] launch path: seat launch.sh ($SEAT_LAUNCH)"
else
LAUNCH_COMMAND=(mosaic yolo "$MOSAIC_AGENT_RUNTIME")
if [ -n "$MOSAIC_AGENT_MODEL" ]; then LAUNCH_COMMAND+=(--model "$MOSAIC_AGENT_MODEL"); fi
if [ -n "$MOSAIC_AGENT_REASONING" ]; then LAUNCH_COMMAND+=(--thinking "$MOSAIC_AGENT_REASONING"); fi
echo "[fleet] launch path: mosaic yolo (no executable seat launch.sh)"
fi
# The tmux holder owns a named server. Explicitly clear the pane environment # The tmux holder owns a named server. Explicitly clear the pane environment
# so server/session variables cannot cross the launch boundary; retain only # so server/session variables cannot cross the launch boundary; retain only
@@ -0,0 +1,216 @@
#!/usr/bin/env bash
# CI-fit regression suite for the #1408 legacy-socket guard in
# start-agent-session.sh.
#
# Same hermeticity contract as test-agent-session-broker-preflight.sh: a fake
# tmux on PATH that scripts its own answers, a real unix socket in a tmpdir so
# the broker preflight passes, env -i with a fake HOME. No case depends on host
# state.
#
# The failure this suite is written down to catch: during a socket cutover a
# seat's session still lives on the DEFAULT tmux socket while the launcher
# targets the named one. The declared-socket has-session check cannot see the
# legacy session (measured 2026-08-24: rc=1, script proceeds), so launch
# creates a same-name duplicate — and comms delivery, which addresses sessions
# by NAME, cannot tell the two apart. The guard refuses with its own code
# (exit 76, after 75 broker-absent) BEFORE any tmux mutation.
#
# Cases:
# 1. legacy session present -> exit 76, message names seat-on-legacy-socket
# + both sockets' roles, and NO tmux session was created.
# 2. legacy session absent -> proceeds PAST the guard (the run then stops at
# a later precondition; asserted: exit != 76, stderr lacks the guard's
# code, proving the guard was not the refusal).
# 3. MOSAIC_TMUX_SOCKET empty (single-socket host) -> guard is inert: the
# default-socket probe must not fire at all.
#
# Sabotage control, run by the developer (not in-suite): remove the guard
# block, re-run — case 1 fails (exit is not 76), cases 2-3 still pass;
# restore byte-identically.
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
WORK_DIR="${MOSAIC_TEST_WORK_DIR:-$PWD/.mosaic-test-work/agent-session-legacy-socket-guard}"
FAKE_HOME="$WORK_DIR/home"
BIN_DIR="$WORK_DIR/bin"
SOCK_DIR="$WORK_DIR/sockets"
LOG_FILE="$WORK_DIR/tmux-calls.log"
LEGACY_FLAG="$WORK_DIR/legacy-session-present"
rm -rf "$WORK_DIR"
mkdir -p "$FAKE_HOME/.config/mosaic/fleet/agents" "$BIN_DIR" "$SOCK_DIR"
chmod 700 "$FAKE_HOME/.config/mosaic" "$FAKE_HOME/.config/mosaic/fleet/agents"
chmod 750 "$FAKE_HOME/.config/mosaic/fleet"
cat > "$FAKE_HOME/.config/mosaic/fleet/agents/lsguard-test.env.generated" <<'ENVEOF'
MOSAIC_AGENT_NAME=lsguard-test
MOSAIC_GIT_IDENTITY=lsguard-test
MOSAIC_AGENT_CLASS=worker
MOSAIC_AGENT_RUNTIME=pi
MOSAIC_AGENT_MODEL=
MOSAIC_AGENT_REASONING=
MOSAIC_AGENT_TOOL_POLICY=code
MOSAIC_AGENT_WORKDIR=/tmp
MOSAIC_TMUX_SOCKET=mosaic-fleet
ENVEOF
chmod 600 "$FAKE_HOME/.config/mosaic/fleet/agents/lsguard-test.env.generated"
# A projection with NO named socket, for case 3. Same file minus the socket line.
sed '/^MOSAIC_TMUX_SOCKET=/d; s/lsguard-test/lsguard-nosock/' \
"$FAKE_HOME/.config/mosaic/fleet/agents/lsguard-test.env.generated" \
> "$FAKE_HOME/.config/mosaic/fleet/agents/lsguard-nosock.env.generated"
echo 'MOSAIC_TMUX_SOCKET=' >> "$FAKE_HOME/.config/mosaic/fleet/agents/lsguard-nosock.env.generated"
chmod 600 "$FAKE_HOME/.config/mosaic/fleet/agents/lsguard-nosock.env.generated"
# Ownership identity the launcher validates before anything touches tmux:
# a 0600 uuid file plus a tmux global environment that matches it exactly.
mkdir -p "$FAKE_HOME/.config/mosaic/fleet/run"
chmod 750 "$FAKE_HOME/.config/mosaic/fleet/run"
OWNER_UUID="aaaaaaaa-aaaa-4aaa-8aaa-aaaaaaaaaaaa"
printf '%s' "$OWNER_UUID" > "$FAKE_HOME/.config/mosaic/fleet/run/holder-owner"
chmod 600 "$FAKE_HOME/.config/mosaic/fleet/run/holder-owner"
# The exact env block assert_owned_tmux_server expects; the socket value differs
# per case, so cases rewrite it via write_tmux_env before each run.
write_tmux_env() {
printf '%s\n' \
"HOME=$FAKE_HOME" \
'PATH=/usr/bin:/bin' \
"PWD=$FAKE_HOME" \
"MOSAIC_FLEET_OWNER=$OWNER_UUID" \
'MOSAIC_TMUX_HOLDER=_holder' \
"MOSAIC_TMUX_SOCKET=$1" > "$WORK_DIR/tmux-env"
}
# ─── Fake tmux ──────────────────────────────────────────────────────────────
# Scripted answers: a DEFAULT-socket has-session (argv carries no -L) answers
# by the flag file; every named-socket call succeeds (holder present, no
# existing session is fine for these cases since refusal happens first).
cat > "$BIN_DIR/tmux" <<SH
#!/usr/bin/env bash
printf 'tmux %s\n' "\$*" >> "$LOG_FILE"
if [[ "\$*" == *new-session* ]]; then
echo "TMUX-NEW-SESSION-INVOKED" >> "$LOG_FILE"
fi
if [[ "\$*" == *show-environment* ]]; then
cat "$WORK_DIR/tmux-env"
exit 0
fi
if [[ "\$*" == *has-session* ]]; then
# holder session always present; the seat's DEFAULT-socket presence is the
# flag file; the seat is never already-running on the NAMED socket.
[[ "\$*" == *_holder* ]] && exit 0
if [[ "\$1" == "-L" ]]; then exit 1; fi
[[ -e "$LEGACY_FLAG" ]] && exit 0 || exit 1
fi
exit 0
SH
chmod +x "$BIN_DIR/tmux"
for bin in mosaic pi claude; do
printf '#!/usr/bin/env bash\nexit 0\n' > "$BIN_DIR/$bin"
chmod +x "$BIN_DIR/$bin"
done
# Real socket so the #1292 broker preflight passes and the run reaches the guard.
# Same idiom as the broker-preflight suite: AF_UNIX binds cap at 108 path bytes,
# so the socket lives at a SHORT /tmp path held by a detached python holder (a
# foreground bind would close on exit; -S on a closed-but-unlinked path fails).
LIVE_SOCK="/tmp/mosaic-lsguard-$RANDOM-$$.sock"
trap 'rm -f "$LIVE_SOCK"' EXIT
rm -f "$LIVE_SOCK"
cat > "$SOCK_DIR/holder.py" <<'PY'
import socket, sys, time
path = sys.argv[1]
s = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM)
s.bind(path)
s.listen(1)
time.sleep(120)
PY
python3 "$SOCK_DIR/holder.py" "$LIVE_SOCK" >/dev/null 2>"$SOCK_DIR/holder.err" &
for _ in $(seq 1 50); do
[ -S "$LIVE_SOCK" ] && break
sleep 0.1
done
[ -S "$LIVE_SOCK" ] || { echo "FAIL: could not create live socket" >&2; exit 1; }
run_session_script() {
local agent="$1"; shift
(
cd "$WORK_DIR"
env -i HOME="$FAKE_HOME" PATH="$BIN_DIR:/usr/bin:/bin" \
GIT_CONFIG_GLOBAL=/dev/null GIT_CONFIG_SYSTEM=/dev/null \
MOSAIC_HOME="$FAKE_HOME/.config/mosaic" \
MOSAIC_LEASE_BROKER_SOCKET="$LIVE_SOCK" \
"$@" \
bash "$SCRIPT_DIR/start-agent-session.sh" "$agent"
)
}
fail=0
assert() {
local desc="$1" expected="$2" actual="$3"
[[ "$expected" == "$actual" ]] || { echo "FAIL: $desc — expected '$expected', got '$actual'" >&2; fail=1; }
}
assert_contains() {
local desc="$1" haystack="$2" needle="$3"
[[ "$haystack" == *"$needle"* ]] || { echo "FAIL: $desc — missing '$needle'" >&2; fail=1; }
}
assert_not_contains() {
local desc="$1" haystack="$2" needle="$3"
if [[ "$haystack" == *"$needle"* ]]; then
echo "FAIL: $desc — must not contain '$needle'" >&2
fail=1
fi
return 0
}
# ─── 1. Legacy session present → exit 76, no tmux mutation. ─────────────────
write_tmux_env "mosaic-fleet"
: > "$LOG_FILE"; touch "$LEGACY_FLAG"
stderr_file="$WORK_DIR/stderr-1.tmp"
set +e
run_session_script lsguard-test >/dev/null 2>"$stderr_file"
rc=$?
set -e
err=$(cat "$stderr_file")
assert "legacy present exit code" "76" "$rc"
assert_contains "names the failure" "$err" "FAIL_LAUNCH seat-on-legacy-socket"
assert_contains "names the agent" "$err" "lsguard-test"
assert_contains "names the target socket" "$err" "mosaic-fleet"
assert_not_contains "no session created" "$(cat "$LOG_FILE")" "TMUX-NEW-SESSION-INVOKED"
# ─── 2. Legacy session absent → guard is not the refusal. ───────────────────
write_tmux_env "mosaic-fleet"
: > "$LOG_FILE"; rm -f "$LEGACY_FLAG"
stderr_file="$WORK_DIR/stderr-2.tmp"
set +e
run_session_script lsguard-test >/dev/null 2>"$stderr_file"
rc=$?
set -e
err=$(cat "$stderr_file")
if [[ "$rc" == "76" ]]; then
echo "FAIL: legacy absent must not exit 76" >&2; fail=1
fi
assert_not_contains "guard code absent from stderr" "$err" "seat-on-legacy-socket"
# ─── 3. Empty MOSAIC_TMUX_SOCKET → guard inert, no default-socket probe. ────
write_tmux_env ""
: > "$LOG_FILE"; touch "$LEGACY_FLAG" # even with a legacy session present
stderr_file="$WORK_DIR/stderr-3.tmp"
set +e
run_session_script lsguard-nosock >/dev/null 2>"$stderr_file"
rc=$?
set -e
err=$(cat "$stderr_file")
if [[ "$rc" == "76" ]]; then
echo "FAIL: empty socket must never exit 76 (single-socket host)" >&2; fail=1
fi
assert_not_contains "guard code absent on single-socket host" "$err" "seat-on-legacy-socket"
rm -f "$LEGACY_FLAG"
if [[ "$fail" -ne 0 ]]; then
echo "start-agent-session legacy-socket guard regression FAILED" >&2
exit 1
fi
echo "start-agent-session legacy-socket guard regression passed"
+1 -1
View File
@@ -25,7 +25,7 @@
"lint": "eslint src", "lint": "eslint src",
"typecheck": "tsc --noEmit", "typecheck": "tsc --noEmit",
"test": "vitest run --passWithNoTests && pnpm run test:framework-shell", "test": "vitest run --passWithNoTests && pnpm run test:framework-shell",
"test:framework-shell": "bash framework/tools/quality/scripts/check-test-enumeration.sh && bash framework/tools/quality/scripts/test-check-test-enumeration.sh && python3 framework/tools/quality/scripts/test-framework-drift-check.py && bash framework/tools/quality/scripts/test-framework-drift-doctor.sh && bash framework/systemd/user/test-fleet-units.sh && python3 src/lease-broker/daemon_deadline_unittest.py && python3 src/lease-broker/normative_fragments_unittest.py && python3 src/lease-broker/promotion_binding_unittest.py && python3 src/lease-broker/promotion_trigger_unittest.py && python3 src/lease-broker/receipt_challenge_unittest.py && python3 src/lease-broker/context_recovery_unittest.py && python3 src/lease-broker/recovery_runtime_unittest.py && python3 src/lease-broker/recovery_b1_adversarial_unittest.py && python3 src/lease-broker/receipt_observer_client_unittest.py && python3 src/lease-broker/invariant_r_unittest.py && python3 src/lease-broker/framework_skill_portability_unittest.py && python3 src/lease-broker/revoke_noop_unittest.py && python3 src/mutator-gate/runtime_tools_unittest.py && python3 src/mutator-gate/runtime_launch_guard_unittest.py && python3 src/mutator-gate/version_coupling_unittest.py && python3 framework/tools/lease-broker/check-runtime-launches.py --root ../.. && bash framework/tools/codex/test-pr-diff-context.sh && bash framework/tools/qa/test-deps-preflight.sh && bash framework/tools/git/test-pr-edit.sh && bash framework/tools/git/test-pr-create-fallback-default-base.sh && bash framework/tools/git/test-pr-review-gitea-comment.sh && bash framework/tools/git/test-pr-review-repo-host-override.sh && bash framework/tools/git/test-ci-queue-wait-no-status.sh && bash framework/tools/git/test-ci-queue-wait-branch-absent.sh && bash framework/tools/git/test-ci-queue-wait-tristate.sh && bash framework/tools/git/test-ci-queue-wait-github-checks.sh && bash framework/tools/git/test-ci-queue-wait-no-ci-expected.sh && bash framework/tools/git/test-pr-merge-queue-branch.sh && bash framework/tools/git/test-pr-merge-no-ci-expected.sh && bash framework/tools/git/test-pr-merge-fork-ci-status.sh && bash framework/tools/git/test-pr-merge-head-pin.sh && bash framework/tools/git/test-pr-merge-message-field.sh && bash framework/tools/git/test-git-credential-mosaic.sh && bash framework/tools/git/test-gitea-token-identity.sh && bash framework/tools/git/test-explain-diagnostic-status-neutral.sh && bash framework/tools/git/test-detect-platform-outside-repo.sh && bash framework/tools/woodpecker/test-terminal-green-contract.sh && bash framework/tools/_scripts/test-install-ordering-guard.sh && bash framework/tools/_scripts/test-mosaic-init-rce.sh && bash framework/tools/tmux/agent-send.test.sh && bash framework/tools/wake/test-wake-store-ack.sh && bash framework/tools/wake/test-wake-store-enqueue-race.sh && bash framework/tools/wake/test-wake-digest-hmac.sh && bash framework/tools/wake/test-wake-digest-quarantine.sh && bash framework/tools/wake/test-wake-detector.sh && bash framework/tools/wake/test-wake-fn-oracle.sh && bash framework/tools/wake/test-wake-reconcile.sh && bash framework/tools/wake/test-wake-beacon.sh && bash framework/tools/wake/test-wake-preimage.sh && bash framework/tools/wake/test-wake-install.sh && bash framework/tools/glpi/test-list-http-status.sh && bash framework/tools/orchestrator/test-board-roll.sh && bash framework/tools/woodpecker/test-ci-wait-exit-matrix.sh && bash framework/tools/_scripts/test-fleet-transport-check.sh && bash framework/tools/_scripts/test-brain-home-check.sh && bash framework/tools/_scripts/test-structure-anchor-check.sh && bash framework/tools/fleet/test-agent-session-broker-preflight.sh" "test:framework-shell": "bash framework/tools/quality/scripts/check-test-enumeration.sh && bash framework/tools/quality/scripts/test-check-test-enumeration.sh && python3 framework/tools/quality/scripts/test-framework-drift-check.py && bash framework/tools/quality/scripts/test-framework-drift-doctor.sh && bash framework/systemd/user/test-fleet-units.sh && python3 src/lease-broker/daemon_deadline_unittest.py && python3 src/lease-broker/normative_fragments_unittest.py && python3 src/lease-broker/promotion_binding_unittest.py && python3 src/lease-broker/promotion_trigger_unittest.py && python3 src/lease-broker/receipt_challenge_unittest.py && python3 src/lease-broker/context_recovery_unittest.py && python3 src/lease-broker/recovery_runtime_unittest.py && python3 src/lease-broker/recovery_b1_adversarial_unittest.py && python3 src/lease-broker/receipt_observer_client_unittest.py && python3 src/lease-broker/invariant_r_unittest.py && python3 src/lease-broker/framework_skill_portability_unittest.py && python3 src/lease-broker/revoke_noop_unittest.py && python3 src/mutator-gate/runtime_tools_unittest.py && python3 src/mutator-gate/runtime_launch_guard_unittest.py && python3 src/mutator-gate/version_coupling_unittest.py && python3 framework/tools/lease-broker/check-runtime-launches.py --root ../.. && bash framework/tools/codex/test-pr-diff-context.sh && bash framework/tools/qa/test-deps-preflight.sh && bash framework/tools/git/test-pr-edit.sh && bash framework/tools/git/test-pr-create-fallback-default-base.sh && bash framework/tools/git/test-pr-review-gitea-comment.sh && bash framework/tools/git/test-pr-review-repo-host-override.sh && bash framework/tools/git/test-ci-queue-wait-no-status.sh && bash framework/tools/git/test-ci-queue-wait-branch-absent.sh && bash framework/tools/git/test-ci-queue-wait-tristate.sh && bash framework/tools/git/test-ci-queue-wait-github-checks.sh && bash framework/tools/git/test-ci-queue-wait-no-ci-expected.sh && bash framework/tools/git/test-pr-merge-queue-branch.sh && bash framework/tools/git/test-pr-merge-no-ci-expected.sh && bash framework/tools/git/test-pr-merge-fork-ci-status.sh && bash framework/tools/git/test-pr-merge-head-pin.sh && bash framework/tools/git/test-pr-merge-message-field.sh && bash framework/tools/git/test-git-credential-mosaic.sh && bash framework/tools/git/test-gitea-token-identity.sh && bash framework/tools/git/test-explain-diagnostic-status-neutral.sh && bash framework/tools/git/test-detect-platform-outside-repo.sh && bash framework/tools/woodpecker/test-terminal-green-contract.sh && bash framework/tools/_scripts/test-install-ordering-guard.sh && bash framework/tools/_scripts/test-mosaic-init-rce.sh && bash framework/tools/tmux/agent-send.test.sh && bash framework/tools/wake/test-wake-store-ack.sh && bash framework/tools/wake/test-wake-store-enqueue-race.sh && bash framework/tools/wake/test-wake-digest-hmac.sh && bash framework/tools/wake/test-wake-digest-quarantine.sh && bash framework/tools/wake/test-wake-detector.sh && bash framework/tools/wake/test-wake-fn-oracle.sh && bash framework/tools/wake/test-wake-reconcile.sh && bash framework/tools/wake/test-wake-beacon.sh && bash framework/tools/wake/test-wake-preimage.sh && bash framework/tools/wake/test-wake-install.sh && bash framework/tools/glpi/test-list-http-status.sh && bash framework/tools/orchestrator/test-board-roll.sh && bash framework/tools/woodpecker/test-ci-wait-exit-matrix.sh && bash framework/tools/_scripts/test-fleet-transport-check.sh && bash framework/tools/_scripts/test-brain-home-check.sh && bash framework/tools/_scripts/test-structure-anchor-check.sh && bash framework/tools/fleet/test-agent-session-broker-preflight.sh && bash framework/tools/fleet/test-agent-session-legacy-socket-guard.sh"
}, },
"dependencies": { "dependencies": {
"@mosaicstack/brain": "workspace:*", "@mosaicstack/brain": "workspace:*",