Compare commits
1 Commits
feat/fleet
...
release/mo
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
cea1faff12 |
@@ -70,9 +70,6 @@ Skills, hooks, MCP, and plugins are force multipliers you MUST use when applicab
|
||||
## Missing core file
|
||||
|
||||
If `CONSTITUTION.md`, `AGENTS.md`, `SOUL.md`, or the runtime contract is missing, stop and report it.
|
||||
This agent-facing strictness is intentional and stricter than the launcher: the launcher injects
|
||||
`CONSTITUTION.md` tolerantly (skipping it if absent so pre-upgrade hosts keep working), but once a host
|
||||
is re-seeded a genuinely missing core file is a stop-and-report condition — not something to proceed past.
|
||||
|
||||
## Session Closure
|
||||
|
||||
|
||||
@@ -2,11 +2,8 @@
|
||||
|
||||
The irreducible, non-negotiable law for every Mosaic agent on every harness.
|
||||
|
||||
**Framework-owned.** This file is overwritten verbatim on every upgrade — do not edit it. There is
|
||||
**no `CONSTITUTION.local.md`**: hard gates are not locally overridable. A lower layer may only make
|
||||
behavior _stricter_, never relax or override a gate (see Precedence). Operator customization lives in
|
||||
other layers — `SOUL.md` / `USER.md` and the tighten-only overlays `STANDARDS.local.md` /
|
||||
`SOUL.local.md` / `USER.local.md` / `policy/*.md` (see `constitution/LAYER-MODEL.md`).
|
||||
**Framework-owned.** This file is overwritten verbatim on every upgrade — do not edit it. To change
|
||||
behavior, add a `.local.md` overlay or a `policy/` file (tighten-only; see `constitution/LAYER-MODEL.md`).
|
||||
Authored in **capability verbs**: where a gate names a capability ("structured reasoning", "queue
|
||||
guard"), the runtime adapter binds it to a concrete tool and states whether absence is a hard stop.
|
||||
|
||||
|
||||
@@ -6,8 +6,6 @@ MOSAIC_TMUX_SOCKET=${MOSAIC_TMUX_SOCKET:-mosaic-factory}
|
||||
MOSAIC_AGENT_RUNTIME=${MOSAIC_AGENT_RUNTIME:-pi}
|
||||
MOSAIC_AGENT_WORKDIR=${MOSAIC_AGENT_WORKDIR:-$HOME}
|
||||
MOSAIC_AGENT_COMMAND=${MOSAIC_AGENT_COMMAND:-}
|
||||
MOSAIC_HEARTBEAT_RUN_DIR=${MOSAIC_HEARTBEAT_RUN_DIR:-$HOME/.config/mosaic/fleet/run}
|
||||
MOSAIC_HEARTBEAT_INTERVAL=${MOSAIC_HEARTBEAT_INTERVAL:-15}
|
||||
|
||||
if [ -z "$AGENT_NAME" ]; then
|
||||
echo "ERROR: agent name argument or MOSAIC_AGENT_NAME is required" >&2
|
||||
@@ -98,55 +96,5 @@ else
|
||||
fi
|
||||
|
||||
mkdir -p "$MOSAIC_AGENT_WORKDIR"
|
||||
|
||||
# ── Launch the tmux session (no exec — we continue to wire the heartbeat) ────
|
||||
tmux -L "$MOSAIC_TMUX_SOCKET" new-session -d -s "$AGENT_NAME" -c "$MOSAIC_AGENT_WORKDIR" \
|
||||
exec tmux -L "$MOSAIC_TMUX_SOCKET" new-session -d -s "$AGENT_NAME" -c "$MOSAIC_AGENT_WORKDIR" \
|
||||
bash -c "$PANE_SHELL_SNIPPET"
|
||||
|
||||
# ── Resolve the pane PID (retry briefly to let the session initialise) ────────
|
||||
PANE_PID=""
|
||||
for _retry in 1 2 3 4 5; do
|
||||
PANE_PID=$(tmux -L "$MOSAIC_TMUX_SOCKET" list-panes \
|
||||
-t "=${AGENT_NAME}:0.0" -F '#{pane_pid}' 2>/dev/null || true)
|
||||
[ -n "$PANE_PID" ] && break
|
||||
sleep 0.2
|
||||
done
|
||||
|
||||
# ── Spawn the heartbeat sidecar (detached, best-effort) ──────────────────────
|
||||
# The sidecar writes ~/.config/mosaic/fleet/run/<AGENT>.hb atomically while the
|
||||
# pane process is alive, then exits so the file goes stale (fleet ps shows stale
|
||||
# then PANE=dead). It is runtime-agnostic: it only cares about the pane PID.
|
||||
_start_heartbeat_sidecar() {
|
||||
local agent="$1"
|
||||
local pane_pid="$2"
|
||||
local run_dir="$3"
|
||||
local interval="$4"
|
||||
local hb_file="${run_dir}/${agent}.hb"
|
||||
|
||||
mkdir -p "$run_dir"
|
||||
|
||||
# Write the sidecar as a self-contained bash one-liner so it carries no
|
||||
# references to any variables from this script's environment.
|
||||
local sidecar_script
|
||||
sidecar_script=$(printf \
|
||||
'hb=%s; pid=%s; iv=%s; mkdir -p "$(dirname "$hb")"; while kill -0 "$pid" 2>/dev/null; do tmp="$hb.tmp.$$"; printf "ts=%%s\npid=%%s\nstatus=ok\n" "$(date +%%Y-%%m-%%dT%%H:%%M:%%S%%z)" "$pid" > "$tmp" && mv "$tmp" "$hb"; sleep "$iv"; done' \
|
||||
"$hb_file" "$pane_pid" "$interval")
|
||||
|
||||
# setsid + disown ensures the sidecar survives this script exiting.
|
||||
# stderr/stdout go to /dev/null; failures are non-fatal.
|
||||
if command -v setsid >/dev/null 2>&1; then
|
||||
setsid bash -c "$sidecar_script" </dev/null >/dev/null 2>&1 &
|
||||
else
|
||||
bash -c "$sidecar_script" </dev/null >/dev/null 2>&1 &
|
||||
fi
|
||||
disown $! 2>/dev/null || true
|
||||
}
|
||||
|
||||
if [ -n "$PANE_PID" ]; then
|
||||
# Guard: do not let sidecar startup failures abort the launcher (set -e).
|
||||
_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
|
||||
else
|
||||
echo "WARNING: could not resolve pane PID for $AGENT_NAME — heartbeat sidecar not started" >&2
|
||||
fi
|
||||
|
||||
@@ -50,10 +50,6 @@ grep -qF 'already running' /tmp/mosaic-start-agent-idempotent.out || fail "dupli
|
||||
# - Intercepts 'new-session' calls and records its arguments to a file.
|
||||
# - For 'has-session' calls, exits 1 (session does not exist) so the script
|
||||
# proceeds to launch instead of printing "already running".
|
||||
# - For 'list-panes' calls, returns empty so PANE_PID stays unset and the
|
||||
# heartbeat sidecar is NOT spawned (heartbeat is not the focus of this test;
|
||||
# test 6 and 7 cover that path). This prevents any real-filesystem side
|
||||
# effects or leaked background processes.
|
||||
# - For all other subcommands, exits 0.
|
||||
#
|
||||
# Assertions:
|
||||
@@ -64,8 +60,7 @@ grep -qF 'already running' /tmp/mosaic-start-agent-idempotent.out || fail "dupli
|
||||
FAKE_BIN=$(mktemp -d)
|
||||
FAKE_RUNTIME_BIN=$(mktemp -d)
|
||||
TMUX_ARGS_FILE=$(mktemp)
|
||||
HB_RUN_DIR3=$(mktemp -d)
|
||||
CLEANUP_DIRS+=("$FAKE_BIN" "$FAKE_RUNTIME_BIN" "$HB_RUN_DIR3")
|
||||
CLEANUP_DIRS+=("$FAKE_BIN" "$FAKE_RUNTIME_BIN")
|
||||
|
||||
# Write the fake tmux shim (uses only positional args, no sourced vars).
|
||||
cat > "$FAKE_BIN/tmux" <<SHIM
|
||||
@@ -79,11 +74,6 @@ if [ "\$subcmd" = "new-session" ]; then
|
||||
printf '%s\n' "\$@" > "$TMUX_ARGS_FILE"
|
||||
exit 0
|
||||
fi
|
||||
if [ "\$subcmd" = "list-panes" ]; then
|
||||
# Return empty: no sidecar spawned (heartbeat is not the focus of this test).
|
||||
echo ""
|
||||
exit 0
|
||||
fi
|
||||
exit 0
|
||||
SHIM
|
||||
chmod +x "$FAKE_BIN/tmux"
|
||||
@@ -99,7 +89,6 @@ MOSAIC_AGENT_WORKDIR="$WORKDIR3" \
|
||||
MOSAIC_AGENT_RUNTIME="pi" \
|
||||
MOSAIC_RUNTIME_BIN="$FAKE_RUNTIME_BIN" \
|
||||
MOSAIC_AGENT_COMMAND="mosaic yolo pi --model openai-codex/gpt-5.5:high" \
|
||||
MOSAIC_HEARTBEAT_RUN_DIR="$HB_RUN_DIR3" \
|
||||
"$START" "$AGENT3"
|
||||
|
||||
all_args=$(cat "$TMUX_ARGS_FILE" 2>/dev/null || true)
|
||||
@@ -123,8 +112,7 @@ echo "$all_args" | grep -qF "mosaic yolo pi --model openai-codex/gpt-5.5:high" |
|
||||
# ── Test 4: when no extra runtime-bin dirs exist, exec still appears ───────────
|
||||
TMUX_ARGS_FILE2=$(mktemp)
|
||||
FAKE_BIN2=$(mktemp -d)
|
||||
HB_RUN_DIR4=$(mktemp -d)
|
||||
CLEANUP_DIRS+=("$FAKE_BIN2" "$HB_RUN_DIR4")
|
||||
CLEANUP_DIRS+=("$FAKE_BIN2")
|
||||
|
||||
cat > "$FAKE_BIN2/tmux" <<SHIM2
|
||||
#!/usr/bin/env bash
|
||||
@@ -134,11 +122,6 @@ if [ "\$subcmd" = "new-session" ]; then
|
||||
printf '%s\n' "\$@" > "$TMUX_ARGS_FILE2"
|
||||
exit 0
|
||||
fi
|
||||
if [ "\$subcmd" = "list-panes" ]; then
|
||||
# Return empty: no sidecar spawned (heartbeat is not the focus of this test).
|
||||
echo ""
|
||||
exit 0
|
||||
fi
|
||||
exit 0
|
||||
SHIM2
|
||||
chmod +x "$FAKE_BIN2/tmux"
|
||||
@@ -156,7 +139,6 @@ MOSAIC_AGENT_WORKDIR="$WORKDIR4" \
|
||||
MOSAIC_AGENT_RUNTIME="pi" \
|
||||
MOSAIC_RUNTIME_BIN="/nonexistent-dir-$$" \
|
||||
MOSAIC_AGENT_COMMAND="mosaic yolo pi" \
|
||||
MOSAIC_HEARTBEAT_RUN_DIR="$HB_RUN_DIR4" \
|
||||
"$START" "$AGENT4"
|
||||
|
||||
all_args4=$(cat "$TMUX_ARGS_FILE2" 2>/dev/null || true)
|
||||
@@ -179,8 +161,7 @@ echo "$all_args4" | grep -qF "mosaic yolo pi" || fail "pane command does not inc
|
||||
TMUX_ARGS_FILE5=$(mktemp)
|
||||
FAKE_BIN5=$(mktemp -d)
|
||||
FAKE_RUNTIME_BIN5=$(mktemp -d) # this dir IS on the launcher's PATH below
|
||||
HB_RUN_DIR5=$(mktemp -d)
|
||||
CLEANUP_DIRS+=("$FAKE_BIN5" "$FAKE_RUNTIME_BIN5" "$HB_RUN_DIR5")
|
||||
CLEANUP_DIRS+=("$FAKE_BIN5" "$FAKE_RUNTIME_BIN5")
|
||||
|
||||
cat > "$FAKE_BIN5/tmux" <<SHIM5
|
||||
#!/usr/bin/env bash
|
||||
@@ -190,11 +171,6 @@ if [ "\$subcmd" = "new-session" ]; then
|
||||
printf '%s\n' "\$@" > "$TMUX_ARGS_FILE5"
|
||||
exit 0
|
||||
fi
|
||||
if [ "\$subcmd" = "list-panes" ]; then
|
||||
# Return empty: no sidecar spawned (heartbeat is not the focus of this test).
|
||||
echo ""
|
||||
exit 0
|
||||
fi
|
||||
exit 0
|
||||
SHIM5
|
||||
chmod +x "$FAKE_BIN5/tmux"
|
||||
@@ -214,7 +190,6 @@ MOSAIC_AGENT_WORKDIR="$WORKDIR5" \
|
||||
MOSAIC_AGENT_RUNTIME="pi" \
|
||||
MOSAIC_RUNTIME_BIN="$FAKE_RUNTIME_BIN5" \
|
||||
MOSAIC_AGENT_COMMAND="mosaic yolo pi" \
|
||||
MOSAIC_HEARTBEAT_RUN_DIR="$HB_RUN_DIR5" \
|
||||
"$START" "$AGENT5"
|
||||
|
||||
all_args5=$(cat "$TMUX_ARGS_FILE5" 2>/dev/null || true)
|
||||
@@ -230,123 +205,4 @@ echo "$all_args5" | grep -qF "export PATH=" || \
|
||||
echo "$all_args5" | grep -qF "$FAKE_RUNTIME_BIN5" || \
|
||||
fail "test5: candidate dir (already on launcher PATH) was NOT baked into pane PATH — regression"
|
||||
|
||||
# ── Test 6: heartbeat sidecar — pane PID resolved + .hb file written ──────────
|
||||
#
|
||||
# Uses a real tmux session (same socket as test 1 which already has $AGENT) so
|
||||
# list-panes returns a real pane PID. We override MOSAIC_HEARTBEAT_RUN_DIR to
|
||||
# a temp dir and set a 1-second interval, then wait up to 3 s for the .hb file
|
||||
# to appear and check its content.
|
||||
|
||||
HB_RUN_DIR=$(mktemp -d)
|
||||
CLEANUP_DIRS+=("$HB_RUN_DIR")
|
||||
|
||||
# Re-use the session+agent created in Test 1 (still alive on $SOCKET / $AGENT).
|
||||
# We need to invoke the script for a NEW agent on the same socket to exercise
|
||||
# the heartbeat path with a real pane PID.
|
||||
AGENT6="agent6-$RANDOM"
|
||||
MOSAIC_TMUX_SOCKET="$SOCKET" \
|
||||
MOSAIC_AGENT_WORKDIR="$WORKDIR" \
|
||||
MOSAIC_AGENT_COMMAND='bash --noprofile --norc -i' \
|
||||
MOSAIC_HEARTBEAT_RUN_DIR="$HB_RUN_DIR" \
|
||||
MOSAIC_HEARTBEAT_INTERVAL="1" \
|
||||
"$START" "$AGENT6"
|
||||
|
||||
HB_FILE="$HB_RUN_DIR/${AGENT6}.hb"
|
||||
|
||||
# Wait up to 5 seconds for the heartbeat file to appear.
|
||||
_waited=0
|
||||
until [ -f "$HB_FILE" ] || [ "$_waited" -ge 5 ]; do
|
||||
sleep 0.5
|
||||
_waited=$((_waited + 1))
|
||||
done
|
||||
|
||||
[ -f "$HB_FILE" ] || fail "test6: heartbeat file not written at $HB_FILE within 5s"
|
||||
|
||||
hb_content=$(cat "$HB_FILE")
|
||||
echo "--- test 6: heartbeat file content ---"
|
||||
echo "$hb_content"
|
||||
echo "--- end test 6 ---"
|
||||
|
||||
# Verify required fields are present.
|
||||
echo "$hb_content" | grep -qE '^ts=[0-9]{4}-[0-9]{2}-[0-9]{2}T' || \
|
||||
fail "test6: heartbeat ts field missing or malformed"
|
||||
echo "$hb_content" | grep -qE '^pid=[0-9]+' || \
|
||||
fail "test6: heartbeat pid field missing or malformed"
|
||||
echo "$hb_content" | grep -qF 'status=ok' || \
|
||||
fail "test6: heartbeat status=ok missing"
|
||||
|
||||
# ── Test 7: heartbeat sidecar — targets correct .hb path per agent name ────────
|
||||
#
|
||||
# Uses the fake-tmux shim approach (like tests 3-5) to capture the sidecar
|
||||
# invocation without needing a real session. A fake setsid shim records its
|
||||
# arguments so we can assert the sidecar script targets the expected .hb path
|
||||
# and uses the configured interval.
|
||||
|
||||
FAKE_BIN7=$(mktemp -d)
|
||||
FAKE_RUNTIME_BIN7=$(mktemp -d)
|
||||
SETSID_ARGS_FILE=$(mktemp)
|
||||
HB_RUN_DIR7=$(mktemp -d)
|
||||
CLEANUP_DIRS+=("$FAKE_BIN7" "$FAKE_RUNTIME_BIN7" "$HB_RUN_DIR7")
|
||||
|
||||
AGENT7="my-fleet-agent-$RANDOM"
|
||||
INTERVAL7="42"
|
||||
|
||||
# Fake tmux: has-session → not found; new-session → ok; list-panes → known PID.
|
||||
cat > "$FAKE_BIN7/tmux" <<SHIM7
|
||||
#!/usr/bin/env bash
|
||||
subcmd="\$3"
|
||||
if [ "\$subcmd" = "has-session" ]; then exit 1; fi
|
||||
if [ "\$subcmd" = "new-session" ]; then exit 0; fi
|
||||
if [ "\$subcmd" = "list-panes" ]; then echo "88888"; exit 0; fi
|
||||
exit 0
|
||||
SHIM7
|
||||
chmod +x "$FAKE_BIN7/tmux"
|
||||
|
||||
# Fake setsid: capture the bash -c <script> argument for inspection, then
|
||||
# background an actual bash subshell so disown succeeds in the caller.
|
||||
cat > "$FAKE_BIN7/setsid" <<'SETSID_SHIM'
|
||||
#!/usr/bin/env bash
|
||||
# argv: setsid bash -c <sidecar_script>
|
||||
# Record the full argument list to the capture file, then exit cleanly.
|
||||
printf '%s\0' "$@" > __SETSID_ARGS_FILE__
|
||||
exit 0
|
||||
SETSID_SHIM
|
||||
# Patch the placeholder with the real capture-file path (avoids heredoc expansion issues).
|
||||
sed -i "s|__SETSID_ARGS_FILE__|${SETSID_ARGS_FILE}|g" "$FAKE_BIN7/setsid"
|
||||
chmod +x "$FAKE_BIN7/setsid"
|
||||
|
||||
SOCKET7="mosaic-agent-test7-$RANDOM-$$"
|
||||
WORKDIR7=$(mktemp -d)
|
||||
CLEANUP_DIRS+=("$WORKDIR7")
|
||||
|
||||
PATH="$FAKE_BIN7:$PATH" \
|
||||
MOSAIC_TMUX_SOCKET="$SOCKET7" \
|
||||
MOSAIC_AGENT_WORKDIR="$WORKDIR7" \
|
||||
MOSAIC_AGENT_RUNTIME="pi" \
|
||||
MOSAIC_RUNTIME_BIN="$FAKE_RUNTIME_BIN7" \
|
||||
MOSAIC_AGENT_COMMAND="mosaic yolo pi" \
|
||||
MOSAIC_HEARTBEAT_RUN_DIR="$HB_RUN_DIR7" \
|
||||
MOSAIC_HEARTBEAT_INTERVAL="$INTERVAL7" \
|
||||
"$START" "$AGENT7"
|
||||
|
||||
# Give the background setsid shim a moment to finish writing the capture file.
|
||||
sleep 0.5
|
||||
|
||||
setsid_args=$(cat "$SETSID_ARGS_FILE" 2>/dev/null | tr '\0' '\n' || true)
|
||||
rm -f "$SETSID_ARGS_FILE"
|
||||
rm -rf "$WORKDIR7"
|
||||
|
||||
echo "--- test 7: captured setsid args ---"
|
||||
echo "$setsid_args"
|
||||
echo "--- end test 7 ---"
|
||||
|
||||
# The sidecar script (bash -c <script>) must reference the correct .hb path.
|
||||
expected_hb="${HB_RUN_DIR7}/${AGENT7}.hb"
|
||||
echo "$setsid_args" | grep -qF "$expected_hb" || \
|
||||
fail "test7: sidecar script does not reference correct .hb path ($expected_hb)"
|
||||
|
||||
# The sidecar script must use the configured interval.
|
||||
echo "$setsid_args" | grep -qF "$INTERVAL7" || \
|
||||
fail "test7: sidecar script does not reference configured interval ($INTERVAL7)"
|
||||
|
||||
echo "ok - start-agent-session"
|
||||
|
||||
@@ -12,7 +12,7 @@
|
||||
# 2. STRUCTURAL (private $HOME default in *.sh) — scanned everywhere EXCEPT examples/,
|
||||
# because worked example overlays/personas legitimately show placeholder paths.
|
||||
#
|
||||
# File types: *.md, *.sh, *.ps1, *.json, *.yml/*.yaml, *.toml, *.env, *.service, and the CLI scripts under
|
||||
# File types: *.md, *.sh, *.ps1, *.json, and the extensionless CLI scripts under
|
||||
# tools/_scripts/. Excludes node_modules/ and this gate file.
|
||||
#
|
||||
# NOTE: '\bPDA\b' intentionally matches "PDA-friendly" (the contamination removed in P2);
|
||||
@@ -39,7 +39,7 @@ cd "$FRAMEWORK_ROOT" || { echo "FRAMEWORK_ROOT not found: $FRAMEWORK_ROOT" >&2;
|
||||
# Identity scope = ALL shipped text files (examples/ INCLUDED).
|
||||
_files_identity() {
|
||||
find . -type f \
|
||||
\( -name '*.md' -o -name '*.sh' -o -name '*.ps1' -o -name '*.json' -o -name '*.yml' -o -name '*.yaml' -o -name '*.toml' -o -name '*.env' -o -name '*.service' -o -path '*/tools/_scripts/*' \) \
|
||||
\( -name '*.md' -o -name '*.sh' -o -name '*.ps1' -o -name '*.json' -o -path '*/tools/_scripts/*' \) \
|
||||
-not -path '*/node_modules/*' -not -path "./$SELF_REL" -print0
|
||||
}
|
||||
# Structural scope = shipped scripts, examples/ EXCLUDED.
|
||||
|
||||
@@ -10,14 +10,11 @@ import {
|
||||
buildAgentWatchCreateViewerCommand,
|
||||
buildAgentWatchKillViewerCommand,
|
||||
buildAgentVerifyAcceptedCommand,
|
||||
buildEnableLingerCommand,
|
||||
buildFleetServiceCommand,
|
||||
buildSystemdEnableCommand,
|
||||
buildSystemdShowCommand,
|
||||
buildTmuxListPanesCommand,
|
||||
classifySendResult,
|
||||
detectDrift,
|
||||
enableFleetUnits,
|
||||
generateAgentEnv,
|
||||
getDefaultOperatorSourceLabel,
|
||||
getDefaultTenantAndHost,
|
||||
@@ -31,12 +28,10 @@ import {
|
||||
parseTmuxListPanes,
|
||||
registerFleetCommand,
|
||||
resolveFleetPaths,
|
||||
RUNTIME_ACCEPTABLE_COMMANDS,
|
||||
VERIFY_DEFAULT_TIMEOUT_MS,
|
||||
VERIFY_POLL_INTERVAL_MS,
|
||||
type AgentPsRow,
|
||||
type CommandRunner,
|
||||
type FleetRoster,
|
||||
type InteractiveRunner,
|
||||
type SleepFn,
|
||||
} from './fleet.js';
|
||||
@@ -914,118 +909,6 @@ describe('fleet ps — drift detection', () => {
|
||||
it('does NOT flag drift when pane command is null (pane dead)', () => {
|
||||
expect(detectDrift('pi', null)).toBe(false);
|
||||
});
|
||||
|
||||
it('does NOT flag drift when pane=node for wrapped pi agent (mosaic yolo pi)', () => {
|
||||
expect(detectDrift('pi', 'node')).toBe(false);
|
||||
});
|
||||
|
||||
it('does NOT flag drift when pane=node for wrapped codex agent (mosaic yolo codex)', () => {
|
||||
expect(detectDrift('codex', 'node')).toBe(false);
|
||||
});
|
||||
|
||||
it('flags drift when pane=python3 for pi runtime (canary-pi dogfood regression guard)', () => {
|
||||
expect(detectDrift('pi', 'python3')).toBe(true);
|
||||
});
|
||||
|
||||
it('does NOT flag drift when pane=python3 for dogfood runtime', () => {
|
||||
expect(detectDrift('dogfood', 'python3')).toBe(false);
|
||||
});
|
||||
|
||||
it('flags drift for unknown pane command on known runtime', () => {
|
||||
expect(detectDrift('claude', 'bash')).toBe(true);
|
||||
});
|
||||
|
||||
it('RUNTIME_ACCEPTABLE_COMMANDS is exported and contains expected entries', () => {
|
||||
expect(RUNTIME_ACCEPTABLE_COMMANDS['pi']).toContain('node');
|
||||
expect(RUNTIME_ACCEPTABLE_COMMANDS['pi']).not.toContain('python3');
|
||||
expect(RUNTIME_ACCEPTABLE_COMMANDS['dogfood']).toContain('python3');
|
||||
expect(RUNTIME_ACCEPTABLE_COMMANDS['codex']).toContain('node');
|
||||
});
|
||||
});
|
||||
|
||||
describe('fleet install — auto-enable units for boot-survival', () => {
|
||||
it('buildSystemdEnableCommand and buildEnableLingerCommand return correct command arrays', () => {
|
||||
expect(buildSystemdEnableCommand('mosaic-tmux-holder.service')).toEqual([
|
||||
'systemctl',
|
||||
'--user',
|
||||
'enable',
|
||||
'mosaic-tmux-holder.service',
|
||||
]);
|
||||
expect(buildEnableLingerCommand('testuser')).toEqual(['loginctl', 'enable-linger', 'testuser']);
|
||||
});
|
||||
|
||||
it('enables holder and each agent unit via injected runner after install', async () => {
|
||||
const minimalRoster: FleetRoster = {
|
||||
version: 1,
|
||||
transport: 'tmux',
|
||||
tmux: { socketName: 'mosaic-factory', holderSession: '_holder' },
|
||||
defaults: { workingDirectory: '~/src' },
|
||||
runtimes: { codex: { resetCommand: '/clear' } },
|
||||
agents: [{ name: 'coder0', runtime: 'codex', className: 'worker' }],
|
||||
};
|
||||
|
||||
const calls: string[][] = [];
|
||||
const runner: CommandRunner = async (command, args) => {
|
||||
calls.push([command, ...args]);
|
||||
return { stdout: '', stderr: '', exitCode: 0 };
|
||||
};
|
||||
|
||||
await enableFleetUnits(runner, minimalRoster, {});
|
||||
|
||||
expect(calls).toContainEqual(['systemctl', '--user', 'enable', 'mosaic-tmux-holder.service']);
|
||||
expect(calls).toContainEqual(['systemctl', '--user', 'enable', 'mosaic-agent@coder0.service']);
|
||||
});
|
||||
|
||||
it('install still succeeds when systemctl enable returns non-zero (non-fatal)', async () => {
|
||||
const minimalRoster: FleetRoster = {
|
||||
version: 1,
|
||||
transport: 'tmux',
|
||||
tmux: { socketName: 'mosaic-factory', holderSession: '_holder' },
|
||||
defaults: { workingDirectory: '~/src' },
|
||||
runtimes: { codex: { resetCommand: '/clear' } },
|
||||
agents: [{ name: 'coder0', runtime: 'codex', className: 'worker' }],
|
||||
};
|
||||
|
||||
const calls: string[][] = [];
|
||||
const runner: CommandRunner = async (command, args) => {
|
||||
calls.push([command, ...args]);
|
||||
// Simulate systemctl enable failure
|
||||
if (command === 'systemctl' && args.includes('enable')) {
|
||||
return { stdout: '', stderr: 'Unit not found', exitCode: 1 };
|
||||
}
|
||||
return { stdout: '', stderr: '', exitCode: 0 };
|
||||
};
|
||||
|
||||
// Must NOT reject/throw even when enable calls fail
|
||||
await expect(enableFleetUnits(runner, minimalRoster, {})).resolves.toBeUndefined();
|
||||
|
||||
// The enable attempt must have been made
|
||||
expect(calls.some((c) => c.includes('enable'))).toBe(true);
|
||||
});
|
||||
|
||||
it('--no-enable skips all systemctl enable and loginctl linger calls', async () => {
|
||||
const minimalRoster: FleetRoster = {
|
||||
version: 1,
|
||||
transport: 'tmux',
|
||||
tmux: { socketName: 'mosaic-factory', holderSession: '_holder' },
|
||||
defaults: { workingDirectory: '~/src' },
|
||||
runtimes: { codex: { resetCommand: '/clear' } },
|
||||
agents: [{ name: 'coder0', runtime: 'codex', className: 'worker' }],
|
||||
};
|
||||
|
||||
const calls: string[][] = [];
|
||||
const runner: CommandRunner = async (command, args) => {
|
||||
calls.push([command, ...args]);
|
||||
return { stdout: '', stderr: '', exitCode: 0 };
|
||||
};
|
||||
|
||||
await enableFleetUnits(runner, minimalRoster, { enable: false });
|
||||
|
||||
// No calls should include 'enable'
|
||||
expect(calls.every((c) => !c.includes('enable'))).toBe(true);
|
||||
// No loginctl calls at all
|
||||
expect(calls.every((c) => c[0] !== 'loginctl')).toBe(true);
|
||||
});
|
||||
});
|
||||
|
||||
describe('fleet ps — tenant and host', () => {
|
||||
|
||||
@@ -210,93 +210,6 @@ export function buildFleetServiceCommand(action: FleetServiceAction, agentName?:
|
||||
return ['systemctl', '--user', action, service];
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns the systemctl --user enable command for a given unit.
|
||||
* Used by the install auto-enable step to persist units across reboots.
|
||||
*/
|
||||
export function buildSystemdEnableCommand(unit: string): string[] {
|
||||
return ['systemctl', '--user', 'enable', unit];
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns the loginctl enable-linger command for a given user.
|
||||
* Linger allows user systemd services to survive logout.
|
||||
*/
|
||||
export function buildEnableLingerCommand(user: string): string[] {
|
||||
return ['loginctl', 'enable-linger', user];
|
||||
}
|
||||
|
||||
/**
|
||||
* Enable fleet units for boot-survival after install.
|
||||
* Non-fatal: if systemctl enable returns non-zero, a warning is printed and we continue.
|
||||
* If opts.enable === false (--no-enable flag), the whole step is skipped.
|
||||
*/
|
||||
export async function enableFleetUnits(
|
||||
runner: CommandRunner,
|
||||
roster: FleetRoster,
|
||||
opts: { enable?: boolean },
|
||||
): Promise<void> {
|
||||
if (opts.enable === false) {
|
||||
return;
|
||||
}
|
||||
try {
|
||||
let succeeded = 0;
|
||||
let failed = 0;
|
||||
|
||||
const holderResult = await runner(
|
||||
...splitCommand(buildSystemdEnableCommand('mosaic-tmux-holder.service')),
|
||||
);
|
||||
if (holderResult.exitCode === 0) {
|
||||
succeeded++;
|
||||
} else {
|
||||
failed++;
|
||||
process.stderr.write(
|
||||
`Warning: could not enable mosaic-tmux-holder.service: ${holderResult.stderr || holderResult.stdout || 'non-zero exit'}\n`,
|
||||
);
|
||||
}
|
||||
|
||||
for (const agent of roster.agents) {
|
||||
const unit = `mosaic-agent@${agent.name}.service`;
|
||||
const result = await runner(...splitCommand(buildSystemdEnableCommand(unit)));
|
||||
if (result.exitCode === 0) {
|
||||
succeeded++;
|
||||
} else {
|
||||
failed++;
|
||||
process.stderr.write(
|
||||
`Warning: could not enable ${unit}: ${result.stderr || result.stdout || 'non-zero exit'}\n`,
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
if (succeeded > 0) {
|
||||
console.log(`Enabled ${succeeded} unit(s) for boot-survival.`);
|
||||
}
|
||||
if (failed > 0) {
|
||||
process.stderr.write(
|
||||
`Warning: ${failed} unit(s) could not be enabled (systemctl unavailable?). Run manually if needed.\n`,
|
||||
);
|
||||
}
|
||||
|
||||
// Best-effort linger
|
||||
let username: string;
|
||||
try {
|
||||
username = userInfo().username;
|
||||
} catch {
|
||||
username = process.env['USER'] ?? process.env['LOGNAME'] ?? 'unknown';
|
||||
}
|
||||
const lingerResult = await runner(...splitCommand(buildEnableLingerCommand(username)));
|
||||
if (lingerResult.exitCode !== 0) {
|
||||
process.stderr.write(
|
||||
`Hint: run 'loginctl enable-linger ${username}' as root to survive logout.\n`,
|
||||
);
|
||||
}
|
||||
} catch (err) {
|
||||
process.stderr.write(
|
||||
`Warning: auto-enable step failed unexpectedly: ${err instanceof Error ? err.message : String(err)}\n`,
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
export function buildAgentSendCommand(
|
||||
paths: FleetPaths,
|
||||
agentName: string,
|
||||
@@ -524,41 +437,32 @@ export function parseTmuxListPanes(
|
||||
return { pid, command, dead, idleSeconds };
|
||||
}
|
||||
|
||||
/**
|
||||
* Maps each known runtime to the set of acceptable pane commands.
|
||||
* A pane running any of these commands for the given runtime is NOT considered drifted.
|
||||
* Runtimes launched via `mosaic yolo` wrap in node, so 'node' is acceptable for most.
|
||||
* The dogfood runtime accepts python3/python (the canary-pi dogfood stub).
|
||||
*/
|
||||
export const RUNTIME_ACCEPTABLE_COMMANDS: Record<string, readonly string[]> = {
|
||||
claude: ['claude', 'node'],
|
||||
codex: ['codex', 'node'],
|
||||
opencode: ['opencode', 'node'],
|
||||
pi: ['pi', 'node'],
|
||||
dogfood: ['python3', 'python'],
|
||||
};
|
||||
|
||||
/**
|
||||
* Determine if there is a runtime drift: roster says one runtime but the pane
|
||||
* is actually running something from a different runtime. We detect this by
|
||||
* checking if the pane command doesn't match a known acceptable command for the
|
||||
* checking if the pane command doesn't match a known canonical command for the
|
||||
* roster's declared runtime.
|
||||
*
|
||||
* Known acceptable commands per runtime (see RUNTIME_ACCEPTABLE_COMMANDS):
|
||||
* claude → claude, node (node covers mosaic yolo wrapper)
|
||||
* codex → codex, node
|
||||
* opencode → opencode, node
|
||||
* pi → pi, node (python3 still flags drift for canary-pi dogfood stub)
|
||||
* dogfood → python3, python
|
||||
* Known canonical commands per runtime:
|
||||
* claude → claude
|
||||
* codex → codex
|
||||
* opencode → opencode
|
||||
* pi → pi
|
||||
*
|
||||
* If the pane is running something else (e.g., python3/dogfood-agent.py) for
|
||||
* an agent whose roster runtime is "pi", that's a drift.
|
||||
*/
|
||||
export function detectDrift(rosterRuntime: string, paneCommand: string | null): boolean {
|
||||
if (!paneCommand) return false;
|
||||
const acceptable = RUNTIME_ACCEPTABLE_COMMANDS[rosterRuntime];
|
||||
if (!acceptable) return false;
|
||||
return !acceptable.includes(paneCommand);
|
||||
const knownCommands: Record<string, string[]> = {
|
||||
claude: ['claude'],
|
||||
codex: ['codex'],
|
||||
opencode: ['opencode'],
|
||||
pi: ['pi'],
|
||||
};
|
||||
const expected = knownCommands[rosterRuntime];
|
||||
if (!expected) return false;
|
||||
return !expected.includes(paneCommand);
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -802,22 +706,12 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
|
||||
cmd
|
||||
.command('install')
|
||||
.description('Install local fleet tools and user systemd units')
|
||||
.option('--no-enable', 'Skip enabling units for boot-survival')
|
||||
.action(async (opts: { enable?: boolean }) => {
|
||||
await installFleet(cmd, frameworkRoot);
|
||||
const roster = await loadRosterForCommand(cmd);
|
||||
await enableFleetUnits(runner, roster, opts);
|
||||
});
|
||||
.action(async () => installFleet(cmd, frameworkRoot));
|
||||
|
||||
cmd
|
||||
.command('install-systemd')
|
||||
.description('Install local fleet tools and user systemd units')
|
||||
.option('--no-enable', 'Skip enabling units for boot-survival')
|
||||
.action(async (opts: { enable?: boolean }) => {
|
||||
await installFleet(cmd, frameworkRoot);
|
||||
const roster = await loadRosterForCommand(cmd);
|
||||
await enableFleetUnits(runner, roster, opts);
|
||||
});
|
||||
.action(async () => installFleet(cmd, frameworkRoot));
|
||||
|
||||
for (const action of ['start', 'stop', 'restart'] as const) {
|
||||
cmd
|
||||
|
||||
Reference in New Issue
Block a user