Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
 fred
|
5c35a250de | ||
|
fred
|
10a1f82031 | ||
|
fred
|
61a907a12f |
@@ -128,6 +128,14 @@ EOF
|
||||
sleep 30
|
||||
EOF
|
||||
chmod 700 "$AGENT_BIN/mosaic"
|
||||
# The launcher resolves the roster's runtime against PANE_PATH before it
|
||||
# spawns anything (#1241), so the runtime this projection names has to be
|
||||
# present here even though the fake `mosaic` above never execs it.
|
||||
cat > "$AGENT_BIN/pi" <<'EOF'
|
||||
#!/bin/sh
|
||||
sleep 30
|
||||
EOF
|
||||
chmod 700 "$AGENT_BIN/pi"
|
||||
server_environment_before=$(tmux -L "$TEST_SOCKET" show-environment -g | sort)
|
||||
server_sessions_before=$(tmux -L "$TEST_SOCKET" list-sessions | sort)
|
||||
if /usr/bin/env -i HOME="$HOLDER_HOME" PATH=/usr/bin:/bin MOSAIC_HOME="$AGENT_HOME" \
|
||||
|
||||
@@ -225,54 +225,6 @@ else
|
||||
warn "mosaic-ensure-sequential-thinking helper missing"
|
||||
fi
|
||||
|
||||
# Fleet transport binary (#1240).
|
||||
#
|
||||
# `mosaic fleet --help` reads "Manage the local Mosaic tmux fleet" and every
|
||||
# roster the CLI scaffolds sets `transport: tmux`, but nothing in the install
|
||||
# path provides tmux and, until now, nothing here noticed it was absent. On a
|
||||
# greenfield host that produced a fleet which installed clean, started clean,
|
||||
# and had no live seat; `mosaic fleet ps` was the operator's first and only
|
||||
# signal that anything was wrong.
|
||||
#
|
||||
# The roster's own `transport:` is read rather than assumed, so a host that
|
||||
# declares something other than tmux is told about the binary it actually
|
||||
# needs. Absent a roster the check still runs — `mosaic fleet init` will
|
||||
# scaffold a tmux fleet on this host, and finding out beforehand is the point.
|
||||
#
|
||||
# `tools/install.sh` carries a deliberately parallel check at the end of its
|
||||
# summary. The two are separate because the installer must be able to say this
|
||||
# before the framework's own scripts are guaranteed to be on disk; keep their
|
||||
# wording in step.
|
||||
fleet_declared_transport() {
|
||||
local roster="$MOSAIC_HOME/fleet/roster.yaml"
|
||||
local declared=""
|
||||
|
||||
if [[ -f "$roster" ]]; then
|
||||
declared="$(sed -n 's/^[[:space:]]*transport:[[:space:]]*//p' "$roster" | head -1 |
|
||||
tr -d '"'\''' | tr -d '\r' | awk '{print $1}')"
|
||||
fi
|
||||
|
||||
printf '%s\n' "${declared:-tmux}"
|
||||
}
|
||||
|
||||
check_fleet_transport() {
|
||||
local transport
|
||||
transport="$(fleet_declared_transport)"
|
||||
|
||||
if command -v "$transport" >/dev/null 2>&1; then
|
||||
pass "Fleet transport available: $transport"
|
||||
return
|
||||
fi
|
||||
|
||||
if [[ -f "$MOSAIC_HOME/fleet/roster.yaml" ]]; then
|
||||
warn "Fleet transport '$transport' is not installed — this host has a roster and no seat can launch. Install it (e.g. sudo apt-get install -y $transport), then 'mosaic fleet start'."
|
||||
else
|
||||
warn "Fleet transport '$transport' is not installed — 'mosaic fleet' cannot run seats here. Install it (e.g. sudo apt-get install -y $transport) before 'mosaic fleet init'."
|
||||
fi
|
||||
}
|
||||
|
||||
check_fleet_transport
|
||||
|
||||
# Legacy migration surfaces should no longer contain symlink trees.
|
||||
legacy_paths=(
|
||||
"$HOME/.claude/agent-guides"
|
||||
|
||||
@@ -1,215 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
# Covers the #1240 fleet-transport checks in `mosaic-doctor` and in
|
||||
# `tools/install.sh`.
|
||||
#
|
||||
# Both checks answer the same question — "can a seat actually launch on this
|
||||
# host?" — from two different places, because the installer has to be able to
|
||||
# answer it before the framework's own scripts are guaranteed to be on disk.
|
||||
# Two implementations of one rule is exactly the shape that drifts, so this
|
||||
# harness drives BOTH, in one file, from the same table of cases.
|
||||
#
|
||||
# The functions are extracted from the shipped scripts rather than copied here.
|
||||
# A test that carries its own copy of the logic is a test that keeps passing
|
||||
# after the shipped copy changes — the failure mode this whole change is about.
|
||||
# Extraction is by exact function header and a closing brace in column one; if
|
||||
# either script is reshaped so that stops matching, the extraction yields
|
||||
# nothing and this fails loudly instead of silently measuring an empty string.
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR=$(cd -- "$(dirname -- "$0")" && pwd)
|
||||
DOCTOR="$SCRIPT_DIR/mosaic-doctor"
|
||||
# framework/tools/_scripts -> framework/tools -> framework -> mosaic -> packages -> repo
|
||||
INSTALLER=$(cd -- "$SCRIPT_DIR/../../../../.." && pwd)/tools/install.sh
|
||||
|
||||
fail() {
|
||||
echo "FAIL: $*" >&2
|
||||
exit 1
|
||||
}
|
||||
|
||||
[ -f "$DOCTOR" ] || fail "missing mosaic-doctor at $DOCTOR"
|
||||
[ -f "$INSTALLER" ] || fail "missing install.sh at $INSTALLER"
|
||||
|
||||
ROOT=$(mktemp -d)
|
||||
trap 'rm -rf "$ROOT"' EXIT
|
||||
|
||||
# The cases below run with PATH set to a directory that deliberately does not
|
||||
# contain a shell, and a PATH assignment on a command also governs how that
|
||||
# command is looked up — so bash has to be named absolutely or it becomes the
|
||||
# thing that is missing.
|
||||
BASH_BIN=$(command -v bash) || fail "host is missing 'bash'"
|
||||
|
||||
# A PATH containing exactly the utilities these functions use and nothing else.
|
||||
# The absent-transport cases are only meaningful on a PATH where the transport
|
||||
# is genuinely unresolvable, and this host (like most) has tmux in /usr/bin —
|
||||
# so the system path cannot be part of the path under test.
|
||||
FAKE_BIN="$ROOT/bin"
|
||||
mkdir -p "$FAKE_BIN"
|
||||
for utility in sed head tr awk; do
|
||||
utility_path=$(command -v "$utility") || fail "host is missing '$utility'"
|
||||
ln -s "$utility_path" "$FAKE_BIN/$utility"
|
||||
done
|
||||
|
||||
if PATH="$FAKE_BIN" command -v tmux >/dev/null 2>&1; then
|
||||
fail "'tmux' is resolvable on the minimal test path; absent-transport cases are not measurable"
|
||||
fi
|
||||
|
||||
# Extract a function by its exact header, up to a closing brace in column one.
|
||||
extract_function() {
|
||||
local source_file="$1"
|
||||
local function_name="$2"
|
||||
local destination="$3"
|
||||
|
||||
awk -v name="$function_name" '
|
||||
$0 == name "() {" { collecting = 1 }
|
||||
collecting { print }
|
||||
collecting && $0 == "}" { exit }
|
||||
' "$source_file" > "$destination"
|
||||
|
||||
grep -qF "$function_name() {" "$destination" ||
|
||||
fail "could not extract '$function_name' from $source_file — has it been renamed or reshaped?"
|
||||
# An unterminated extraction would be a syntax error the moment it is sourced,
|
||||
# but saying so here names the cause instead of leaving a bash parse error.
|
||||
bash -n "$destination" ||
|
||||
fail "extracted '$function_name' does not parse; the closing brace was probably not found"
|
||||
}
|
||||
|
||||
extract_function "$DOCTOR" fleet_declared_transport "$ROOT/doctor-declared.sh"
|
||||
extract_function "$DOCTOR" check_fleet_transport "$ROOT/doctor-check.sh"
|
||||
extract_function "$INSTALLER" check_fleet_transport "$ROOT/installer-check.sh"
|
||||
|
||||
# Build a MOSAIC_HOME, optionally with a roster declaring a transport.
|
||||
make_home() {
|
||||
local home="$ROOT/$1"
|
||||
local declared="${2-}"
|
||||
|
||||
rm -rf "$home"
|
||||
mkdir -p "$home"
|
||||
if [ -n "$declared" ]; then
|
||||
mkdir -p "$home/fleet"
|
||||
cat > "$home/fleet/roster.yaml" <<EOF
|
||||
version: 2
|
||||
generation: 1
|
||||
transport: $declared
|
||||
agents: []
|
||||
EOF
|
||||
fi
|
||||
printf '%s\n' "$home"
|
||||
}
|
||||
|
||||
# Run the doctor's check against a given home and path, capturing which
|
||||
# reporter the check chose. The real `pass` prints only under `--verbose` and
|
||||
# the real `warn` always prints; these stubs make both unconditional on
|
||||
# purpose, because what is under test is the severity the check selects, not
|
||||
# whether the default verbosity happens to show it. A check that warned where
|
||||
# it should pass would otherwise be invisible here.
|
||||
run_doctor_check() {
|
||||
local home="$1"
|
||||
local path="$2"
|
||||
|
||||
MOSAIC_HOME="$home" PATH="$path" "$BASH_BIN" --noprofile --norc -c '
|
||||
set -euo pipefail
|
||||
warn() { echo "[WARN] $*"; }
|
||||
pass() { echo "[OK] $*"; }
|
||||
MOSAIC_HOME="$1"
|
||||
source "$2"
|
||||
source "$3"
|
||||
check_fleet_transport
|
||||
' _ "$home" "$ROOT/doctor-declared.sh" "$ROOT/doctor-check.sh" 2>&1
|
||||
}
|
||||
|
||||
run_installer_check() {
|
||||
local home="$1"
|
||||
local path="$2"
|
||||
|
||||
MOSAIC_HOME="$home" PATH="$path" "$BASH_BIN" --noprofile --norc -c '
|
||||
set -euo pipefail
|
||||
warn() { echo "[WARN] $*"; }
|
||||
C="" RESET=""
|
||||
MOSAIC_HOME="$1"
|
||||
source "$2"
|
||||
check_fleet_transport
|
||||
' _ "$home" "$ROOT/installer-check.sh" 2>&1
|
||||
}
|
||||
|
||||
# A transport that exists. Named tmux because that is what the default roster
|
||||
# declares; the binary never runs, it only has to resolve.
|
||||
PRESENT_BIN="$ROOT/present-bin"
|
||||
mkdir -p "$PRESENT_BIN"
|
||||
printf '#!/usr/bin/env bash\nexit 0\n' > "$PRESENT_BIN/tmux"
|
||||
chmod +x "$PRESENT_BIN/tmux"
|
||||
PATH_WITH_TMUX="$PRESENT_BIN:$FAKE_BIN"
|
||||
|
||||
# ── absent, no roster ────────────────────────────────────────────────────────
|
||||
# Nothing has been configured yet, so the honest thing to point at is `init`.
|
||||
home=$(make_home no-roster)
|
||||
|
||||
output=$(run_doctor_check "$home" "$FAKE_BIN")
|
||||
echo "$output" | grep -qF '[WARN]' || fail "doctor did not warn when tmux was absent"
|
||||
echo "$output" | grep -qF 'tmux' || fail "doctor warning did not name the transport"
|
||||
echo "$output" | grep -qF 'mosaic fleet init' || fail "doctor did not point a rosterless host at init"
|
||||
|
||||
output=$(run_installer_check "$home" "$FAKE_BIN")
|
||||
echo "$output" | grep -qF '[WARN]' || fail "installer did not warn when tmux was absent"
|
||||
echo "$output" | grep -qF 'reports success and no seat comes up' ||
|
||||
fail "installer warning did not say what the missing transport actually breaks"
|
||||
|
||||
# ── absent, roster present ───────────────────────────────────────────────────
|
||||
# A configured fleet that cannot launch is a stronger statement than a
|
||||
# hypothetical one, and the message says so.
|
||||
home=$(make_home with-roster tmux)
|
||||
|
||||
output=$(run_doctor_check "$home" "$FAKE_BIN")
|
||||
echo "$output" | grep -qF '[WARN]' || fail "doctor did not warn with a roster present and tmux absent"
|
||||
echo "$output" | grep -qF 'roster' || fail "doctor did not mention the roster it found"
|
||||
echo "$output" | grep -qF 'mosaic fleet start' || fail "doctor did not point a configured host at start"
|
||||
|
||||
# ── present ──────────────────────────────────────────────────────────────────
|
||||
# Silence from the installer, and a pass (not a warning) from the audit.
|
||||
for home_name in no-roster with-roster; do
|
||||
home="$ROOT/$home_name"
|
||||
|
||||
output=$(run_doctor_check "$home" "$PATH_WITH_TMUX")
|
||||
if echo "$output" | grep -qF '[WARN]'; then
|
||||
fail "doctor warned about the transport while tmux was present ($home_name)"
|
||||
fi
|
||||
echo "$output" | grep -qF '[OK]' || fail "doctor did not record a pass with tmux present ($home_name)"
|
||||
|
||||
output=$(run_installer_check "$home" "$PATH_WITH_TMUX")
|
||||
if [ -n "$output" ]; then
|
||||
fail "installer was not silent with tmux present ($home_name): $output"
|
||||
fi
|
||||
done
|
||||
|
||||
# ── the roster declares something other than tmux ────────────────────────────
|
||||
# The roster is read, not assumed. A host that declares a different transport
|
||||
# is told about the binary it actually needs, and never about tmux — being sent
|
||||
# to install the wrong package is worse than no advice at all.
|
||||
home=$(make_home other-transport zellij)
|
||||
|
||||
output=$(run_doctor_check "$home" "$PATH_WITH_TMUX")
|
||||
echo "$output" | grep -qF 'zellij' || fail "doctor ignored the roster's declared transport"
|
||||
if echo "$output" | grep -qF 'tmux'; then
|
||||
fail "doctor named tmux for a host whose roster declares zellij"
|
||||
fi
|
||||
|
||||
output=$(run_installer_check "$home" "$PATH_WITH_TMUX")
|
||||
echo "$output" | grep -qF 'zellij' || fail "installer ignored the roster's declared transport"
|
||||
if echo "$output" | grep -qF 'tmux'; then
|
||||
fail "installer named tmux for a host whose roster declares zellij"
|
||||
fi
|
||||
|
||||
# ── a quoted or trailing-comment transport value ─────────────────────────────
|
||||
# YAML permits both and neither is exotic; a check that installs `tmux"` or
|
||||
# reads `tmux # default` as a binary name would send the operator nowhere.
|
||||
home=$(make_home quoted-transport '"tmux" # the only transport today')
|
||||
|
||||
output=$(run_doctor_check "$home" "$PATH_WITH_TMUX")
|
||||
echo "$output" | grep -qF '[OK] Fleet transport available: tmux' ||
|
||||
fail "doctor did not parse a quoted/commented transport value: $output"
|
||||
|
||||
output=$(run_installer_check "$home" "$PATH_WITH_TMUX")
|
||||
if [ -n "$output" ]; then
|
||||
fail "installer did not parse a quoted/commented transport value: $output"
|
||||
fi
|
||||
|
||||
echo "ok - fleet transport checks (mosaic-doctor + install.sh)"
|
||||
@@ -286,6 +286,36 @@ _build_runtime_bin_prefix() {
|
||||
MOSAIC_RUNTIME_BIN_PREFIX=$(_build_runtime_bin_prefix)
|
||||
PANE_PATH=${MOSAIC_RUNTIME_BIN_PREFIX:+${MOSAIC_RUNTIME_BIN_PREFIX}:}/usr/local/bin:/usr/bin:/bin
|
||||
|
||||
# #1241. The pane runs `mosaic yolo <runtime>` under PANE_PATH with a cleared
|
||||
# environment. A binary missing from *that* path is a pane that dies in under a
|
||||
# second, inside a session nobody is attached to, with its diagnostic scrolled
|
||||
# into a pane tmux then destroys. Resolve both here, before any effect, where
|
||||
# the failure is still attributable to the thing that caused it.
|
||||
#
|
||||
# `mosaic yolo <runtime>` runs checkRuntime(runtime) and the binary it looks for
|
||||
# is named exactly like the runtime, so resolving the runtime name is the same
|
||||
# question the pane will ask a moment later — asked while an operator can still
|
||||
# see the answer.
|
||||
_resolve_in_pane_path() {
|
||||
PATH="$PANE_PATH" command -v -- "$1" 2>/dev/null
|
||||
}
|
||||
|
||||
# Exit 69 (EX_UNAVAILABLE): the seat cannot be provided. Distinguished from the
|
||||
# 64 (EX_USAGE) rejections above, which mean the projection itself was bad —
|
||||
# here the data is fine and the host is not ready. Callers tell the individual
|
||||
# cases apart by `code=`, the same way fail_env's many codes share exit 64.
|
||||
fail_launch() {
|
||||
local code="$1"
|
||||
shift
|
||||
echo "ERROR: agent launch aborted: code=${code} agent=${AGENT_NAME} $*" >&2
|
||||
exit 69
|
||||
}
|
||||
|
||||
for required_binary in mosaic "$MOSAIC_AGENT_RUNTIME"; do
|
||||
_resolve_in_pane_path "$required_binary" >/dev/null ||
|
||||
fail_launch missing-binary "'${required_binary}' is not on the pane PATH (${PANE_PATH})"
|
||||
done
|
||||
|
||||
_ensure_claude_workdir_trusted() {
|
||||
local workdir="$1"
|
||||
local resolved
|
||||
@@ -384,6 +414,19 @@ if [ -n "$PANE_PID" ]; then
|
||||
_start_heartbeat_sidecar "$AGENT_NAME" "$PANE_PID" \
|
||||
"$MOSAIC_HEARTBEAT_RUN_DIR" "$MOSAIC_HEARTBEAT_INTERVAL" || \
|
||||
echo "WARNING: heartbeat sidecar could not be started for $AGENT_NAME" >&2
|
||||
elif _tmux has-session -t "=${AGENT_NAME}:0.0" 2>/dev/null; then
|
||||
# #1241. Session present, no pane PID after a second of retries. Whatever this
|
||||
# is, it is not a seat an operator can use, so it is not a success either.
|
||||
fail_launch pane-pid-unresolved \
|
||||
"tmux reports the session but no pane PID after 5 attempts"
|
||||
else
|
||||
echo "WARNING: could not resolve pane PID for $AGENT_NAME — heartbeat sidecar not started" >&2
|
||||
# #1241. This branch used to print a WARNING about the heartbeat sidecar and
|
||||
# exit 0. It is not a heartbeat problem: tmux destroys a session when its pane
|
||||
# command exits, so an absent session one second after new-session means the
|
||||
# runtime died on startup. Reporting it as success is what let `fleet start`
|
||||
# return 0 over three dead panes — the launcher knew, and said the wrong thing
|
||||
# at the wrong severity to the wrong layer.
|
||||
fail_launch pane-did-not-survive \
|
||||
"the pane exited immediately and tmux destroyed the session;" \
|
||||
"run 'mosaic yolo ${MOSAIC_AGENT_RUNTIME}' in ${MOSAIC_AGENT_WORKDIR} to see why"
|
||||
fi
|
||||
|
||||
@@ -23,8 +23,26 @@ index=0
|
||||
if [ "${args[0]:-}" = -L ]; then index=2; fi
|
||||
case "${args[$index]:-}" in
|
||||
has-session)
|
||||
# The holder always answers. MOSAIC_TEST_HELD_SESSIONS lets a case add
|
||||
# other targets that should answer too — without it there is no way to
|
||||
# model "tmux still reports the session" for a non-holder agent, and the
|
||||
# launcher's pane-pid-unresolved branch is unreachable from this harness.
|
||||
#
|
||||
# A listed target answers only AFTER new-session, because the launcher asks
|
||||
# this question twice about the same name: once before launching, where a
|
||||
# yes means "already running, nothing to do, exit 0", and once after, where
|
||||
# a yes means "the session survived". A shim that answered yes to both
|
||||
# would short-circuit at the first and never reach the branch under test —
|
||||
# it would look like coverage and measure the idempotency path instead.
|
||||
for argument in "${args[@]}"; do
|
||||
[ "$argument" = '=_holder:0.0' ] && exit 0
|
||||
case " ${MOSAIC_TEST_HELD_SESSIONS:-} " in
|
||||
*" $argument "*)
|
||||
if tr '\0' '\n' < "${MOSAIC_TEST_TMUX_CALLS:?}" | grep -qxF new-session; then
|
||||
exit 0
|
||||
fi
|
||||
;;
|
||||
esac
|
||||
done
|
||||
exit 1
|
||||
;;
|
||||
@@ -62,6 +80,30 @@ env -0 > "${MOSAIC_HOME:?}/fleet/pane-environment"
|
||||
SHIM
|
||||
chmod +x "$FAKE_BIN/mosaic"
|
||||
|
||||
# The runtime the rosters below name. The launcher resolves it against PANE_PATH
|
||||
# before spawning (#1241), so it has to exist somewhere the pane would find it —
|
||||
# not merely on the launcher's own PATH.
|
||||
printf '#!/usr/bin/env bash\nexit 0\n' > "$FAKE_BIN/pi"
|
||||
chmod +x "$FAKE_BIN/pi"
|
||||
|
||||
# PANE_PATH is derived partly from `npm config get prefix`. Left to the real npm
|
||||
# it would splice whatever the host has installed into the path under test, and
|
||||
# the missing-binary cases below would pass or fail by accident of the machine.
|
||||
cat > "$FAKE_BIN/npm" <<'SHIM'
|
||||
#!/usr/bin/env bash
|
||||
printf '%s\n' "${MOSAIC_TEST_NPM_PREFIX:-/nonexistent}"
|
||||
SHIM
|
||||
chmod +x "$FAKE_BIN/npm"
|
||||
|
||||
# PANE_PATH always ends in the system path. A host that installs these there can
|
||||
# not measure the missing-binary cases at all, and a green run would mean
|
||||
# nothing — so say so instead of passing.
|
||||
for host_binary in mosaic pi; do
|
||||
if PATH=/usr/local/bin:/usr/bin:/bin command -v "$host_binary" >/dev/null 2>&1; then
|
||||
fail "host provides '$host_binary' in the system path; missing-binary cases are not measurable here"
|
||||
fi
|
||||
done
|
||||
|
||||
write_generated() {
|
||||
local home="$1"
|
||||
local agent="$2"
|
||||
@@ -81,6 +123,19 @@ MOSAIC_TMUX_SOCKET=mosaic-test
|
||||
EOF
|
||||
chmod 600 "$home/fleet/agents/$agent.env.generated"
|
||||
mkdir -p "$home/work"
|
||||
install_pane_binaries "$home"
|
||||
}
|
||||
|
||||
# `$PANE_HOME/.npm-global/bin` is one of the prefixes the launcher folds into
|
||||
# PANE_PATH, so this is the pane's own view of "installed", distinct from the
|
||||
# launcher's PATH. Tests that need a binary *absent* remove it from here.
|
||||
install_pane_binaries() {
|
||||
local pane_home="$1"
|
||||
mkdir -p "$pane_home/.npm-global/bin"
|
||||
local binary
|
||||
for binary in mosaic pi; do
|
||||
ln -sf "$FAKE_BIN/$binary" "$pane_home/.npm-global/bin/$binary"
|
||||
done
|
||||
}
|
||||
|
||||
run_start() {
|
||||
@@ -88,6 +143,7 @@ run_start() {
|
||||
local agent="$2"
|
||||
HOME="$home" PATH="$FAKE_BIN:$PATH" MOSAIC_TEST_TMUX_CALLS="$TMUX_CALLS" \
|
||||
MOSAIC_TEST_PANE_PID="${MOSAIC_TEST_PANE_PID:-}" \
|
||||
MOSAIC_TEST_HELD_SESSIONS="${MOSAIC_TEST_HELD_SESSIONS:-}" \
|
||||
MOSAIC_TEST_HOME="$home" \
|
||||
MOSAIC_TEST_FLEET_OWNER=123e4567-e89b-12d3-a456-426614174000 \
|
||||
MOSAIC_HOME="$home" "$START" "$agent"
|
||||
@@ -98,7 +154,10 @@ run_start() {
|
||||
HOME_VALID="$ROOT/valid"
|
||||
AGENT_VALID="coder0"
|
||||
write_generated "$HOME_VALID" "$AGENT_VALID"
|
||||
run_start "$HOME_VALID" "$AGENT_VALID"
|
||||
# A live pane PID is part of what "valid launch" means. Until #1241 this case
|
||||
# ran with none, so the suite's one success path was itself a dead pane the
|
||||
# launcher reported as fine.
|
||||
MOSAIC_TEST_PANE_PID=$$ run_start "$HOME_VALID" "$AGENT_VALID"
|
||||
valid_args=$(tr '\0' '\n' < "$TMUX_CALLS")
|
||||
echo "$valid_args" | grep -qF new-session || fail "valid generated projection did not reach tmux"
|
||||
echo "$valid_args" | grep -qF 'mosaic' || fail "fixed mosaic launcher command missing"
|
||||
@@ -245,6 +304,13 @@ PANE_BASH_ENV="$ROOT/pane-boundary.bash-env"
|
||||
printf 'MOSAIC_RUNTIME_BIN=%s\n' "$FAKE_BIN" > \
|
||||
"$HOME_PANE_BOUNDARY/fleet/agents/coder-pane-boundary.env.local"
|
||||
chmod 600 "$HOME_PANE_BOUNDARY/fleet/agents/coder-pane-boundary.env.local"
|
||||
# This case does not go through run_start, so its pane binaries come from
|
||||
# MOSAIC_RUNTIME_BIN=$FAKE_BIN in the env.local written above — not from the
|
||||
# symlinks install_pane_binaries planted under the generated home, which this
|
||||
# launcher never consults because HOME here is the trusted parent. That is a
|
||||
# legitimate resolution path, but it means dropping MOSAIC_RUNTIME_BIN from
|
||||
# this case on the belief that the symlinks cover it would break the #1241
|
||||
# binary check rather than exercise it.
|
||||
LD_PRELOAD='/not/loaded/by-clean-bootstrap.so' \
|
||||
BASH_ENV="$PANE_BASH_ENV" \
|
||||
MOSAIC_UNTRUSTED_SENTINEL='must-not-reach-pane' \
|
||||
@@ -258,6 +324,7 @@ PATH="$PANE_STALE_PATH" \
|
||||
"MOSAIC_TEST_HOME=$PANE_TRUSTED_HOME" \
|
||||
MOSAIC_TEST_FLEET_OWNER=123e4567-e89b-12d3-a456-426614174000 \
|
||||
MOSAIC_TEST_EXECUTE_PANE=1 \
|
||||
"MOSAIC_TEST_PANE_PID=$$" \
|
||||
"$START" coder-pane-boundary
|
||||
pane_args=$(tr '\0' '\n' < "$TMUX_CALLS")
|
||||
echo "$pane_args" | grep -qxF "HOME=$PANE_TRUSTED_HOME" || \
|
||||
@@ -392,6 +459,75 @@ echo "$interaction_policy_args" | grep -qF 'new-session' && \
|
||||
echo "$output" | grep -qF 'operator interaction service requires runtime pi' || \
|
||||
fail "interaction pinned-policy check did not follow strict parsing"
|
||||
|
||||
# #1241. The pane runs `mosaic yolo <runtime>` against PANE_PATH. A binary
|
||||
# missing from that path is a launch failure, and it has to be named before the
|
||||
# session is created — after it, the diagnostic dies with the pane.
|
||||
assert_missing_pane_binary_rejected() {
|
||||
local binary="$1"
|
||||
local home="$ROOT/missing-$binary"
|
||||
local agent="coder-missing-$binary"
|
||||
write_generated "$home" "$agent"
|
||||
rm -f "$home/.npm-global/bin/$binary"
|
||||
|
||||
: > "$TMUX_CALLS"
|
||||
local output
|
||||
if output=$(MOSAIC_TEST_PANE_PID=$$ run_start "$home" "$agent" 2>&1); then
|
||||
fail "launch succeeded with '$binary' absent from the pane PATH"
|
||||
fi
|
||||
echo "$output" | grep -qF 'code=missing-binary' || fail "missing '$binary' diagnostic missing"
|
||||
echo "$output" | grep -qF "'$binary'" || fail "missing-binary diagnostic did not name $binary"
|
||||
if tr '\0' '\n' < "$TMUX_CALLS" | grep -qF new-session; then
|
||||
fail "launcher created a session it knew would die ($binary absent)"
|
||||
fi
|
||||
}
|
||||
|
||||
assert_missing_pane_binary_rejected mosaic
|
||||
assert_missing_pane_binary_rejected pi
|
||||
|
||||
# #1241. tmux destroys a session when its pane command exits, so no pane PID a
|
||||
# second after new-session means the runtime died on startup. This used to be a
|
||||
# WARNING about the heartbeat sidecar followed by exit 0 — three layers above it
|
||||
# then reported a fleet that was not running.
|
||||
: > "$TMUX_CALLS"
|
||||
HOME_DEAD_PANE="$ROOT/dead-pane"
|
||||
write_generated "$HOME_DEAD_PANE" "coder-dead-pane"
|
||||
if output=$(MOSAIC_TEST_PANE_PID='' run_start "$HOME_DEAD_PANE" coder-dead-pane 2>&1); then
|
||||
fail "launcher reported success over a pane that did not survive"
|
||||
fi
|
||||
echo "$output" | grep -qF 'code=pane-did-not-survive' || fail "dead-pane diagnostic missing"
|
||||
if echo "$output" | grep -qiF 'heartbeat'; then
|
||||
fail "dead pane is still being reported as a heartbeat-sidecar problem"
|
||||
fi
|
||||
tr '\0' '\n' < "$TMUX_CALLS" | grep -qF new-session || \
|
||||
fail "dead-pane case did not reach the launch it is measuring"
|
||||
|
||||
# #1241, the other way a pane fails. Above, tmux destroyed the session and
|
||||
# has-session said so. Here the session is still there and no PID comes back
|
||||
# after the retries — a different fault (the pane is alive but unusable, or
|
||||
# tmux is answering inconsistently) that an operator has to be told apart from
|
||||
# a runtime that died on startup.
|
||||
#
|
||||
# This case exists because the branch that handles it shipped with nothing able
|
||||
# to reach it: the shim answered has-session only for the holder, so every
|
||||
# non-holder agent landed in the session-is-gone branch no matter what. A
|
||||
# defensive branch nothing exercises is the same shape as the bug this whole
|
||||
# change is about, one layer down.
|
||||
: > "$TMUX_CALLS"
|
||||
HOME_NO_PID="$ROOT/pane-no-pid"
|
||||
write_generated "$HOME_NO_PID" "coder-no-pid"
|
||||
if output=$(MOSAIC_TEST_PANE_PID='' MOSAIC_TEST_HELD_SESSIONS='=coder-no-pid:0.0' \
|
||||
run_start "$HOME_NO_PID" coder-no-pid 2>&1); then
|
||||
fail "launcher reported success over a session with no resolvable pane PID"
|
||||
fi
|
||||
echo "$output" | grep -qF 'code=pane-pid-unresolved' || \
|
||||
fail "session-present/no-PID was not reported as pane-pid-unresolved: $output"
|
||||
if echo "$output" | grep -qF 'code=pane-did-not-survive'; then
|
||||
fail "a session tmux still reports was diagnosed as a destroyed session"
|
||||
fi
|
||||
if echo "$output" | grep -qiF 'heartbeat'; then
|
||||
fail "an unresolvable pane PID is still being reported as a heartbeat-sidecar problem"
|
||||
fi
|
||||
|
||||
# Exact stop derives the socket exclusively from the validated generated
|
||||
# projection and ignores an ambient socket supplied by the caller.
|
||||
: > "$TMUX_CALLS"
|
||||
|
||||
@@ -25,7 +25,7 @@
|
||||
"lint": "eslint src",
|
||||
"typecheck": "tsc --noEmit",
|
||||
"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 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/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-review-gitea-comment.sh && bash framework/tools/git/test-pr-review-repo-host-override.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-pr-merge-queue-branch.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/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/_scripts/test-fleet-transport-check.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"
|
||||
"test:framework-shell": "bash framework/tools/quality/scripts/check-test-enumeration.sh && bash framework/tools/quality/scripts/test-check-test-enumeration.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/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-review-gitea-comment.sh && bash framework/tools/git/test-pr-review-repo-host-override.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-pr-merge-queue-branch.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/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"
|
||||
},
|
||||
"dependencies": {
|
||||
"@mosaicstack/brain": "workspace:*",
|
||||
|
||||
@@ -309,43 +309,6 @@ require_cmd() {
|
||||
fi
|
||||
}
|
||||
|
||||
# Fleet transport binary (#1240).
|
||||
#
|
||||
# `mosaic fleet --help` reads "Manage the local Mosaic tmux fleet" and every
|
||||
# roster the CLI scaffolds sets `transport: tmux`, but nothing in this script
|
||||
# provides tmux and, until now, nothing in it mentioned tmux at all. A
|
||||
# greenfield host came out of this installer able to install a fleet, start a
|
||||
# fleet, and run no seat — the operator's first signal was `mosaic fleet ps`.
|
||||
#
|
||||
# Not a `require_cmd`: tmux is required by the fleet, not by mosaic. Plenty of
|
||||
# hosts install this to run `mosaic claude` and will never scaffold a roster,
|
||||
# and failing their install over a binary they do not need would be wrong. It
|
||||
# is a warning that names precisely what it blocks.
|
||||
#
|
||||
# `tools/_scripts/mosaic-doctor` carries a deliberately parallel check, so the
|
||||
# same host state gets the same answer from an audit as from an install. They
|
||||
# are separate implementations because this one has to work before the
|
||||
# framework's scripts are guaranteed to be on disk; keep their wording in step.
|
||||
check_fleet_transport() {
|
||||
local transport=tmux
|
||||
local roster="$MOSAIC_HOME/fleet/roster.yaml"
|
||||
local declared=""
|
||||
|
||||
if [[ -f "$roster" ]]; then
|
||||
declared="$(sed -n 's/^[[:space:]]*transport:[[:space:]]*//p' "$roster" | head -1 |
|
||||
tr -d '"'\''' | tr -d '\r' | awk '{print $1}')"
|
||||
[[ -n "$declared" ]] && transport="$declared"
|
||||
fi
|
||||
|
||||
command -v "$transport" &>/dev/null && return 0
|
||||
|
||||
warn "Fleet transport '$transport' is not installed."
|
||||
echo " The Mosaic fleet runs its agent seats inside $transport. Without it,"
|
||||
echo " ${C}mosaic fleet start${RESET} reports success and no seat comes up."
|
||||
echo " Install it before using the fleet, e.g. ${C}sudo apt-get install -y $transport${RESET}"
|
||||
echo " (this does not affect ${C}mosaic claude${RESET} or the other single-runtime commands)."
|
||||
}
|
||||
|
||||
installed_cli_version() {
|
||||
local json
|
||||
json="$(npm ls -g --depth=0 --json --prefix="$PREFIX" 2>/dev/null)" || true
|
||||
@@ -907,11 +870,6 @@ if [[ "$FLAG_CHECK" == "false" ]]; then
|
||||
ok "Done."
|
||||
fi
|
||||
|
||||
# Fleet readiness (#1240). Runs in both normal and --check mode: "what is the
|
||||
# state of this host" is exactly the question --check is asked, and a host that
|
||||
# cannot run a seat should not have to discover it from `fleet ps`.
|
||||
check_fleet_transport
|
||||
|
||||
} # end main
|
||||
|
||||
main "$@"
|
||||
|
||||
Reference in New Issue
Block a user