Compare commits

..

12 Commits

Author SHA1 Message Date
6a80378e73 fix(fleet): heartbeat consistency — honor MOSAIC_HOME + MOSAIC_HEARTBEAT_INTERVAL
Some checks failed
ci/woodpecker/push/ci Pipeline was successful
ci/woodpecker/pr/ci Pipeline was canceled
F3 milestone 1 — the two pre-existing HB bugs (from #584) flagged in the #590 review:
- writer (start-agent-session.sh): MOSAIC_HEARTBEAT_RUN_DIR now defaults to
  ${MOSAIC_HOME:-$HOME/.config/mosaic}/fleet/run, matching the path `fleet ps`
  reads (heartbeatPath uses the resolved mosaicHome). Fixes false "stale/unknown"
  HB on custom MOSAIC_HOME deployments.
- reader (fleet.ts): new heartbeatIntervalMs() honors MOSAIC_HEARTBEAT_INTERVAL
  (seconds); parseHeartbeat's freshness threshold now matches the writer's actual
  cadence instead of a hardcoded 15s. + vitest coverage.

Validated: custom-home writer dir == reader path; interval 30 -> 30000ms, unset
-> 15000ms; prettier clean.

Refs #542 #588

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-21 18:16:48 -05:00
31e7a4d25e docs(framework): P4.1 — fix stale install.sh comments + cmp-equal early-exit (#593)
Some checks are pending
ci/woodpecker/push/ci Pipeline is pending
ci/woodpecker/push/publish Pipeline is pending
Co-authored-by: Jason Woltje <jason@diversecanvas.com>
Co-committed-by: Jason Woltje <jason@diversecanvas.com>
2026-06-21 23:12:31 +00:00
ca19d57bba feat(fleet): config-type presets + AI-free init wizard (F1) (#591)
Some checks are pending
ci/woodpecker/push/ci Pipeline is pending
ci/woodpecker/push/publish Pipeline is pending
2026-06-21 23:07:41 +00:00
bb7d549080 feat(framework): P4 — upgrade-safe Constitution migration (both installers) (#590)
Some checks are pending
ci/woodpecker/push/ci Pipeline is pending
ci/woodpecker/push/publish Pipeline is pending
Co-authored-by: Jason Woltje <jason@diversecanvas.com>
Co-committed-by: Jason Woltje <jason@diversecanvas.com>
2026-06-21 23:03:48 +00:00
5bef2c35eb feat(fleet): fleet ps surfaces unmanaged socket sessions (#586)
Some checks failed
ci/woodpecker/push/ci Pipeline was canceled
ci/woodpecker/push/publish Pipeline was canceled
2026-06-21 22:37:34 +00:00
2849a8f9db chore(release): bump @mosaicstack/mosaic 0.0.35 -> 0.0.36 (#585)
All checks were successful
ci/woodpecker/push/ci Pipeline was successful
ci/woodpecker/push/publish Pipeline was successful
2026-06-21 21:46:15 +00:00
7ced5588c9 feat(fleet): launcher heartbeat sidecar — HB for all runtimes (pi/claude/codex) (#584)
Some checks failed
ci/woodpecker/push/ci Pipeline was successful
ci/woodpecker/push/publish Pipeline was canceled
2026-06-21 21:14:20 +00:00
afcbbb302f feat(fleet): auto-enable units on install + drift recognizes wrapped runtimes (#583)
Some checks failed
ci/woodpecker/push/ci Pipeline failed
ci/woodpecker/push/publish Pipeline was successful
2026-06-21 20:02:19 +00:00
c2c0b5fe8d chore(release): bump @mosaicstack/mosaic 0.0.34 -> 0.0.35 (#582)
All checks were successful
ci/woodpecker/push/ci Pipeline was successful
ci/woodpecker/push/publish Pipeline was successful
2026-06-21 18:59:39 +00:00
c9cfe36204 docs(framework): P3.1 fast-follow — governance wording + gate scope + bare-launch note (#577)
Some checks failed
ci/woodpecker/push/ci Pipeline was canceled
ci/woodpecker/push/publish Pipeline was canceled
Co-authored-by: Jason Woltje <jason@diversecanvas.com>
Co-committed-by: Jason Woltje <jason@diversecanvas.com>
2026-06-21 18:56:50 +00:00
fc90c89913 fix(fleet): durable runtime PATH for detached agent launch (#581)
All checks were successful
ci/woodpecker/push/ci Pipeline was successful
ci/woodpecker/push/publish Pipeline was successful
2026-06-21 17:30:40 +00:00
af2eede7a9 feat(fleet): Phase-2 observability — fleet ps + watch + send verify (#579)
All checks were successful
ci/woodpecker/push/ci Pipeline was successful
ci/woodpecker/push/publish Pipeline was successful
2026-06-21 04:23:51 +00:00
19 changed files with 1884 additions and 76 deletions

View File

@@ -115,6 +115,11 @@ Every artifact, starting Phase 2, MUST:
- Observation: **read-only default, opt-in takeover**.
- Multi-host: **designed-for from day one**; control plane **rides federation (W1)**.
- Delivery: **CLI-first now**, dogfood against the live stub fleet; webUI deferred to Phase 5.
- Runtimes: fleet agents default to **Codex / pi-on-Codex**; **Claude is reserved for Claude
Code only** (avoid alternate-harness API pricing). Validated durable recipe:
`mosaic yolo pi --model openai-codex/gpt-5.5:high`. Durable detached launch requires the
runtime-bin on PATH (baked into the pane command) + boot-survival (`enable` + linger),
which `fleet init` should automate.
## Assumptions (veto-able)

View File

@@ -73,3 +73,28 @@ with a second agent on `dragon-lin`.
tmux session-name fallback; the systemd/tmux env handoff needs a real fix.
- Next: rebase on merged main, open Phase-2 PR, dual-engine review, merge, close
`fleet-observability-1`. Defer launch-path + env-propagation fixes to Phase 3.
- 2026-06-21 (session 3): Phase-2 PR #579 merged (3 dual-engine rounds hardened
verify+watch). Then closed the launch-path question with Jason's input — CORRECTING
earlier findings:
- The ad-hoc launch deaths were NOT a fundamental TTY blocker: (a) codex was a stale
version (Jason updated it); (b) pi was misconfigured to Claude auth (Jason removed it;
default is now Codex). The REAL durable-launch bug is **PATH**: the detached tmux
launch shell is login+non-interactive, so it misses `~/.npm-global/bin` (added only in
`~/.bashrc`) -> `mosaic: command not found` (127) -> pane dies. tmux panes inherit the
tmux _server_ env, so PATH must be baked into the pane command.
- **Durable real-agent recipe (validated live on gpt-5.5, Claude-free):**
`mosaic yolo pi --model openai-codex/gpt-5.5:high` — pi tolerates detached tmux; a raw
interactive TUI (codex CLI) exits without an attached client. Status line confirmed
`(openai-codex) gpt-5.5 • high`.
- PATH fix landed in `start-agent-session.sh` (commit 32efc13, branch
feat/fleet-launch-path): derive runtime-bin prefix (MOSAIC_RUNTIME_BIN | npm prefix |
~/.npm-global/bin | ~/.local/bin), bake `export PATH=...; exec <cmd>` into the pane;
`exec` also fixes the drift false-positive. Live-tested under stripped PATH -> durable.
- Boot-survival: Jason ran `systemctl --user enable` (+ linger). TODO: auto-enable in
**fleet init** so operators never have to remember it (agentic-enhancement cycle).
- Future custom Pi harness build: pi cannot self-report its model (track
runtime/model/effort as fleet metadata); drift detection should recognize `node` as
pi's pane command (a node-wrapped pane can currently read as drift).
- Findings recorded in AI Guide playbooks/tmux-fleet.md (aiguide PR #7, merged).
- Policy: avoid Claude outside Claude Code (API pricing for alt-harness use) — fleet
runtimes default to Codex / pi-on-Codex; Claude stays in Claude Code only.

View File

@@ -70,6 +70,9 @@ 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

View File

@@ -2,8 +2,11 @@
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. To change
behavior, add a `.local.md` overlay or a `policy/` file (tighten-only; see `constitution/LAYER-MODEL.md`).
**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`).
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.

View File

@@ -0,0 +1,32 @@
version: 1
transport: tmux
tmux:
socket_name: mosaic-factory
holder_session: _holder
defaults:
working_directory: ~
runtimes:
claude:
reset_command: /clear
pi:
reset_command: /new
agents:
- name: orchestrator
runtime: claude
class: orchestrator
persistent_persona: true
- name: coder0
runtime: pi
class: implementer
model_hint: openai-codex/gpt-5.5:high
reset_between_tasks: true
- name: coder1
runtime: pi
class: implementer
model_hint: openai-codex/gpt-5.5:high
reset_between_tasks: true
- name: reviewer
runtime: pi
class: reviewer
model_hint: openai-codex/gpt-5.5:high
reset_between_tasks: true

View File

@@ -0,0 +1,22 @@
version: 1
transport: tmux
tmux:
socket_name: mosaic-factory
holder_session: _holder
defaults:
working_directory: ~
runtimes:
claude:
reset_command: /clear
pi:
reset_command: /new
agents:
- name: orchestrator
runtime: claude
class: orchestrator
persistent_persona: true
- name: generalist
runtime: pi
class: worker
model_hint: openai-codex/gpt-5.5:high
reset_between_tasks: true

View File

@@ -0,0 +1,32 @@
version: 1
transport: tmux
tmux:
socket_name: mosaic-factory
holder_session: _holder
defaults:
working_directory: ~
runtimes:
claude:
reset_command: /clear
pi:
reset_command: /new
agents:
- name: orchestrator
runtime: claude
class: orchestrator
persistent_persona: true
- name: coder0
runtime: pi
class: implementer
model_hint: openai-codex/gpt-5.5:high
reset_between_tasks: true
- name: researcher0
runtime: pi
class: researcher
model_hint: openai-codex/gpt-5.5:high
reset_between_tasks: true
- name: reviewer
runtime: pi
class: reviewer
model_hint: openai-codex/gpt-5.5:high
reset_between_tasks: true

View File

@@ -0,0 +1,32 @@
version: 1
transport: tmux
tmux:
socket_name: mosaic-factory
holder_session: _holder
defaults:
working_directory: ~
runtimes:
claude:
reset_command: /clear
pi:
reset_command: /new
agents:
- name: orchestrator
runtime: claude
class: orchestrator
persistent_persona: true
- name: researcher0
runtime: pi
class: researcher
model_hint: openai-codex/gpt-5.5:high
reset_between_tasks: true
- name: researcher1
runtime: pi
class: researcher
model_hint: openai-codex/gpt-5.5:high
reset_between_tasks: true
- name: analyst
runtime: pi
class: analyst
model_hint: openai-codex/gpt-5.5:high
reset_between_tasks: true

View File

@@ -19,13 +19,23 @@ SOURCE_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
TARGET_DIR="${MOSAIC_HOME:-$HOME/.config/mosaic}"
INSTALL_MODE="${MOSAIC_INSTALL_MODE:-prompt}"
# Files/dirs preserved across upgrades (never overwritten).
# Files/dirs protected from rsync --delete during sync. NOTE: framework-owned
# entries (CONSTITUTION/AGENTS/STANDARDS) ARE re-applied afterward by
# reconcile_framework_files (overwrite + backup-once); the rest stay user-owned.
# User-created content in these paths survives rsync --delete.
PRESERVE_PATHS=("AGENTS.md" "SOUL.md" "USER.md" "TOOLS.md" "STANDARDS.md" "memory" "sources" "credentials")
PRESERVE_PATHS=("CONSTITUTION.md" "AGENTS.md" "SOUL.md" "USER.md" "TOOLS.md" "STANDARDS.md" "memory" "sources" "credentials")
# Framework-owned contract files: re-copied from defaults/ on every upgrade (the
# user must not edit them; a divergent copy is backed up once before overwrite).
# USER_SEEDED files are written once on first install, then owned by the user.
# Both lists are APPEND-FRIENDLY — add a new shipped framework file here and to the
# matching list in packages/mosaic/src/config/file-adapter.ts.
FRAMEWORK_OWNED=("CONSTITUTION.md" "AGENTS.md" "STANDARDS.md")
USER_SEEDED=("TOOLS.md")
# Current framework schema version — bump this when the layout changes.
# The migration system uses this to run upgrade steps.
FRAMEWORK_VERSION=2
FRAMEWORK_VERSION=3
# ─── colours ──────────────────────────────────────────────────────────────────
if [[ -t 1 ]]; then
@@ -40,6 +50,47 @@ warn() { echo -e " ${YELLOW}⚠${RESET} $1" >&2; }
fail() { echo -e " ${RED}${RESET} $1" >&2; }
step() { echo -e "\n${BOLD}$1${RESET}"; }
# ─── snapshot / restore (crash safety for upgrades) ──────────────────────────
SNAPSHOT_DIR=""
make_snapshot() {
is_existing_install || return 0
SNAPSHOT_DIR="$(mktemp -d "${TMPDIR:-/tmp}/mosaic-snapshot-XXXXXX")"
cp -a "$TARGET_DIR/." "$SNAPSHOT_DIR/" 2>/dev/null || true
}
restore_snapshot() {
[[ -n "$SNAPSHOT_DIR" && -d "$SNAPSHOT_DIR" ]] || return 0
fail "Install interrupted/failed — restoring previous state from snapshot"
rm -rf "$TARGET_DIR"; mkdir -p "$TARGET_DIR"
cp -a "$SNAPSHOT_DIR/." "$TARGET_DIR/" 2>/dev/null || true
}
cleanup_snapshot() { [[ -n "$SNAPSHOT_DIR" && -d "$SNAPSHOT_DIR" ]] && rm -rf "$SNAPSHOT_DIR"; SNAPSHOT_DIR=""; }
# Reconcile contract files after sync: framework-owned overwrite (backup-once),
# user-seeded seed-if-absent.
reconcile_framework_files() {
local defaults="$TARGET_DIR/defaults" f
[[ -d "$defaults" ]] || return 0
for f in "${FRAMEWORK_OWNED[@]}"; do
[[ -f "$defaults/$f" ]] || continue
# Already current — skip to avoid mtime churn.
if [[ -f "$TARGET_DIR/$f" ]] && cmp -s "$TARGET_DIR/$f" "$defaults/$f"; then
continue
fi
if [[ -f "$TARGET_DIR/$f" && ! -f "$TARGET_DIR/${f}.pre-constitution.bak" ]]; then
cp "$TARGET_DIR/$f" "$TARGET_DIR/${f}.pre-constitution.bak"
warn "$f is now framework-owned and was updated; your previous copy is saved as ${f}.pre-constitution.bak — re-apply intended changes as a .local overlay or policy/ file (see CONSTITUTION.md / constitution/LAYER-MODEL.md)."
fi
cp "$defaults/$f" "$TARGET_DIR/$f"
done
for f in "${USER_SEEDED[@]}"; do
[[ -f "$defaults/$f" ]] || continue
if [[ ! -f "$TARGET_DIR/$f" ]]; then
cp "$defaults/$f" "$TARGET_DIR/$f"
ok "Seeded $f from defaults"
fi
done
}
# ─── helpers ──────────────────────────────────────────────────────────────────
is_existing_install() {
@@ -113,11 +164,14 @@ sync_framework() {
fi
if command -v rsync >/dev/null 2>&1; then
local rsync_args=(-a --delete --exclude ".git" --exclude ".framework-version")
local rsync_args=(-a --delete --exclude ".git" --exclude ".framework-version" --exclude "*.pre-constitution.bak")
if [[ "$INSTALL_MODE" == "keep" ]]; then
# Anchor to the transfer root (leading /) so we preserve the TOP-LEVEL
# ~/.config/mosaic/<file> without also excluding defaults/<file> from sync
# (reconcile_framework_files needs the freshly-synced defaults/ copies).
for path in "${PRESERVE_PATHS[@]}"; do
rsync_args+=(--exclude "$path")
rsync_args+=(--exclude "/$path")
done
fi
@@ -137,7 +191,7 @@ sync_framework() {
done
fi
find "$TARGET_DIR" -mindepth 1 -maxdepth 1 ! -name ".git" ! -name ".framework-version" -exec rm -rf {} +
find "$TARGET_DIR" -mindepth 1 -maxdepth 1 ! -name ".git" ! -name ".framework-version" ! -name "*.pre-constitution.bak" -exec rm -rf {} +
cp -R "$SOURCE_DIR"/. "$TARGET_DIR"/
rm -rf "$TARGET_DIR/.git"
@@ -195,10 +249,15 @@ run_migrations() {
fi
fi
# ── Future migrations go here ──────────────────────────────────────────────
# if [[ "$from_version" -lt 3 ]]; then
# ...
# fi
# ── Migration: v2 → v3 (Constitution split) ───────────────────────────────
# CONSTITUTION.md / AGENTS.md / STANDARDS.md become framework-owned (overwritten
# on upgrade). reconcile_framework_files() has already run before this point: it
# backed up any user-edited copy to <file>.pre-constitution.bak and installed the
# new framework version. Nothing further to do here — the advisory was emitted at
# reconcile time. (STANDARDS.local.md composition lands with the overlay composer.)
if [[ "$from_version" -lt 3 ]]; then
ok "Migrated to the Constitution layout (framework-owned CONSTITUTION/AGENTS/STANDARDS)"
fi
}
# ═══════════════════════════════════════════════════════════════════════════════
@@ -216,29 +275,25 @@ else
ok "Install mode: overwrite"
fi
# Snapshot before any destructive file operation; restore on interrupt/failure.
make_snapshot
trap 'restore_snapshot' ERR INT TERM
sync_framework
# Ensure persistent directories exist
mkdir -p "$TARGET_DIR/memory"
mkdir -p "$TARGET_DIR/credentials"
# Seed defaults — copy framework contract files from defaults/ to framework
# root if not already present. These ship with sensible defaults but must
# never be overwritten once the user has customized them.
# Reconcile contract files from defaults/ into the framework root: framework-owned
# files (CONSTITUTION/AGENTS/STANDARDS) are overwritten every upgrade (a divergent
# copy is backed up once); user-seeded files (TOOLS) are written on first install only.
#
# This list must match the framework-contract whitelist in
# packages/mosaic/src/config/file-adapter.ts (FileConfigAdapter.syncFramework).
# SOUL.md and USER.md are intentionally NOT seeded here — they are generated
# by `mosaic init` from templates with user-supplied values.
DEFAULTS_DIR="$TARGET_DIR/defaults"
if [[ -d "$DEFAULTS_DIR" ]]; then
for default_file in CONSTITUTION.md AGENTS.md STANDARDS.md TOOLS.md; do
if [[ -f "$DEFAULTS_DIR/$default_file" ]] && [[ ! -f "$TARGET_DIR/$default_file" ]]; then
cp "$DEFAULTS_DIR/$default_file" "$TARGET_DIR/$default_file"
ok "Seeded $default_file from defaults"
fi
done
fi
reconcile_framework_files
# Ensure tool scripts are executable
find "$TARGET_DIR/tools" -name "*.sh" -exec chmod +x {} + 2>/dev/null || true
@@ -249,6 +304,18 @@ ok "Framework synced to $TARGET_DIR"
# Run migrations before post-install (migrations may remove old bin/ etc.)
run_migrations
# File-system phase complete and consistent — clear the restore trap.
trap - ERR INT TERM
cleanup_snapshot
# Testability / minimal-install hook: stop after the file-system phase, before any
# environment-touching post-install steps (runtime linking, MCP setup, skills, doctor).
if [[ "${MOSAIC_SYNC_ONLY:-0}" == "1" ]]; then
write_framework_version
ok "Sync-only mode: file phase complete"
exit 0
fi
step "Post-install tasks"
SCRIPTS="$TARGET_DIR/tools/_scripts"

View File

@@ -274,6 +274,13 @@ detect_existing_config
echo "[mosaic-init] Generating SOUL.md — agent identity contract"
echo ""
# Fail-closed persona: in non-interactive mode the agent NAME must be supplied
# explicitly (--name) — never silently ship an agent named "Assistant".
if [[ $NON_INTERACTIVE -eq 1 && -z "$AGENT_NAME" ]]; then
echo "[mosaic-init] ERROR: --name (agent name) is required in non-interactive mode." >&2
exit 1
fi
prompt_if_empty AGENT_NAME "What name should agents use" "Assistant"
prompt_if_empty ROLE_DESCRIPTION "Agent role description" "execution partner and visibility engine"

View File

@@ -6,6 +6,8 @@ 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:-${MOSAIC_HOME:-$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
@@ -26,5 +28,125 @@ if [ -z "$MOSAIC_AGENT_COMMAND" ]; then
MOSAIC_AGENT_COMMAND="mosaic yolo $MOSAIC_AGENT_RUNTIME"
fi
# ── Derive a runtime-bin PATH prefix ─────────────────────────────────────────
# Precedence:
# 1. $MOSAIC_RUNTIME_BIN (explicit override)
# 2. $(npm config get prefix)/bin (if npm is on PATH)
# 3. Fallbacks: $HOME/.npm-global/bin and $HOME/.local/bin
#
# Only directories that already exist are included. The prefix is baked into
# the pane command regardless of what the LAUNCHER process's $PATH contains,
# because the tmux pane inherits the tmux SERVER environment (not this script's
# environment). A dir on the launcher's PATH may be absent from the server PATH,
# so every existing candidate must always be included. Dedup within the
# constructed prefix avoids listing the same dir twice.
_build_runtime_bin_prefix() {
local candidates=()
if [ -n "${MOSAIC_RUNTIME_BIN:-}" ]; then
candidates+=("$MOSAIC_RUNTIME_BIN")
fi
if command -v npm >/dev/null 2>&1; then
local npm_prefix
npm_prefix=$(npm config get prefix 2>/dev/null) || true
if [ -n "$npm_prefix" ]; then
candidates+=("${npm_prefix}/bin")
fi
fi
candidates+=("$HOME/.npm-global/bin")
candidates+=("$HOME/.local/bin")
local prefix=""
for dir in "${candidates[@]}"; do
[ -d "$dir" ] || continue
if [ -z "$prefix" ]; then
prefix="$dir"
else
case ":${prefix}:" in
*":${dir}:"*) ;; # already in our prefix — skip
*) prefix="${prefix}:${dir}" ;;
esac
fi
done
printf '%s' "$prefix"
}
MOSAIC_RUNTIME_BIN_PREFIX=$(_build_runtime_bin_prefix)
# ── Build the pane command ────────────────────────────────────────────────────
# The pane command must:
# - Export the augmented PATH so the runtime binary is found.
# - exec the agent command so the runtime is the pane's foreground process
# (makes `fleet ps` pane_current_command check reliable; no DRIFT false-positive).
#
# Quoting strategy: single-quote the inner shell snippet so that variable
# references in MOSAIC_AGENT_COMMAND are NOT expanded here — they expand inside
# the pane shell. However, MOSAIC_RUNTIME_BIN_PREFIX and PATH must be expanded
# NOW (in this script) because the pane shell inherits the tmux server
# environment, not this script's env.
#
# We build the snippet as a double-quoted here-string embedded in a printf call
# to avoid nested quoting problems.
if [ -n "$MOSAIC_RUNTIME_BIN_PREFIX" ]; then
PANE_SHELL_SNIPPET="export PATH=\"${MOSAIC_RUNTIME_BIN_PREFIX}:\${PATH}\"; exec ${MOSAIC_AGENT_COMMAND}"
else
PANE_SHELL_SNIPPET="exec ${MOSAIC_AGENT_COMMAND}"
fi
mkdir -p "$MOSAIC_AGENT_WORKDIR"
exec tmux -L "$MOSAIC_TMUX_SOCKET" new-session -d -s "$AGENT_NAME" -c "$MOSAIC_AGENT_WORKDIR" "$MOSAIC_AGENT_COMMAND"
# ── Launch the tmux session (no exec — we continue to wire the heartbeat) ────
tmux -L "$MOSAIC_TMUX_SOCKET" new-session -d -s "$AGENT_NAME" -c "$MOSAIC_AGENT_WORKDIR" \
bash -c "$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

View File

@@ -6,13 +6,26 @@ START="$SCRIPT_DIR/start-agent-session.sh"
SOCKET="mosaic-agent-test-$RANDOM-$$"
AGENT="agent-$RANDOM"
WORKDIR=$(mktemp -d)
trap 'tmux -L "$SOCKET" kill-server >/dev/null 2>&1 || true; rm -rf "$WORKDIR"' EXIT
# Keep a single cleanup trap that accumulates resources.
CLEANUP_DIRS=("$WORKDIR")
CLEANUP_SOCKETS=("$SOCKET")
trap '_cleanup' EXIT
_cleanup() {
for s in "${CLEANUP_SOCKETS[@]:-}"; do
tmux -L "$s" kill-server >/dev/null 2>&1 || true
done
for d in "${CLEANUP_DIRS[@]:-}"; do
rm -rf "$d"
done
}
fail() {
echo "FAIL: $*" >&2
exit 1
}
# ── Test 1: basic session creation with workdir check ─────────────────────────
MOSAIC_TMUX_SOCKET="$SOCKET" \
MOSAIC_AGENT_WORKDIR="$WORKDIR" \
MOSAIC_AGENT_COMMAND='bash --noprofile --norc -i' \
@@ -22,6 +35,7 @@ tmux -L "$SOCKET" has-session -t "=$AGENT:0.0" || fail "agent session was not cr
actual_dir=$(tmux -L "$SOCKET" display-message -p -t "=$AGENT:0.0" '#{pane_current_path}')
[ "$actual_dir" = "$WORKDIR" ] || fail "agent workdir mismatch: $actual_dir"
# ── Test 2: idempotency (duplicate start prints 'already running') ─────────────
MOSAIC_TMUX_SOCKET="$SOCKET" \
MOSAIC_AGENT_WORKDIR="$WORKDIR" \
MOSAIC_AGENT_COMMAND='bash --noprofile --norc -i' \
@@ -29,4 +43,310 @@ MOSAIC_AGENT_COMMAND='bash --noprofile --norc -i' \
grep -qF 'already running' /tmp/mosaic-start-agent-idempotent.out || fail "duplicate start was not idempotent"
# ── Test 3: runtime-bin PATH prefix is baked into the pane command ────────────
#
# We capture the command the script would hand to tmux by injecting a fake
# 'tmux' shim into PATH. The shim:
# - 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:
# a) 'export PATH=' with the synthetic MOSAIC_RUNTIME_BIN prefix appears.
# b) 'exec' appears so the runtime replaces the wrapper shell.
# c) MOSAIC_AGENT_COMMAND with flags is forwarded intact.
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")
# Write the fake tmux shim (uses only positional args, no sourced vars).
cat > "$FAKE_BIN/tmux" <<SHIM
#!/usr/bin/env bash
# Fake tmux: record new-session args; report has-session as missing.
subcmd="\$3" # argv: tmux -L <socket> <subcmd> ...
if [ "\$subcmd" = "has-session" ]; then
exit 1 # session not found → script will attempt new-session
fi
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"
SOCKET3="mosaic-agent-test3-$RANDOM-$$"
AGENT3="agent3-$RANDOM"
WORKDIR3=$(mktemp -d)
CLEANUP_DIRS+=("$WORKDIR3")
PATH="$FAKE_BIN:$PATH" \
MOSAIC_TMUX_SOCKET="$SOCKET3" \
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 "$TMUX_ARGS_FILE" 2>/dev/null || true)
rm -f "$TMUX_ARGS_FILE"
echo "--- captured tmux new-session args ---"
echo "$all_args"
echo "--- end args ---"
# a) PATH prefix containing FAKE_RUNTIME_BIN must appear.
echo "$all_args" | grep -qF "export PATH=" || fail "pane command does not export PATH"
echo "$all_args" | grep -qF "$FAKE_RUNTIME_BIN" || fail "pane command does not include MOSAIC_RUNTIME_BIN in PATH prefix"
# b) exec must appear so the runtime replaces the wrapper shell.
echo "$all_args" | grep -qF "exec " || fail "pane command does not use exec"
# c) Full MOSAIC_AGENT_COMMAND (with flags) must be forwarded.
echo "$all_args" | grep -qF "mosaic yolo pi --model openai-codex/gpt-5.5:high" || \
fail "pane command does not forward MOSAIC_AGENT_COMMAND with flags intact"
# ── 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" "$HB_RUN_DIR4")
cat > "$FAKE_BIN2/tmux" <<SHIM2
#!/usr/bin/env bash
subcmd="\$3"
if [ "\$subcmd" = "has-session" ]; then exit 1; fi
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"
SOCKET4="mosaic-agent-test4-$RANDOM-$$"
AGENT4="agent4-$RANDOM"
WORKDIR4=$(mktemp -d)
CLEANUP_DIRS+=("$WORKDIR4")
# MOSAIC_RUNTIME_BIN points to a non-existent dir so prefix will be empty;
# .npm-global/bin and .local/bin may or may not exist but we just want exec.
PATH="$FAKE_BIN2:$PATH" \
MOSAIC_TMUX_SOCKET="$SOCKET4" \
MOSAIC_AGENT_WORKDIR="$WORKDIR4" \
MOSAIC_AGENT_RUNTIME="pi" \
MOSAIC_RUNTIME_BIN="/nonexistent-dir-$$" \
MOSAIC_AGENT_COMMAND="mosaic yolo pi" \
MOSAIC_HEARTBEAT_RUN_DIR="$HB_RUN_DIR4" \
"$START" "$AGENT4"
all_args4=$(cat "$TMUX_ARGS_FILE2" 2>/dev/null || true)
rm -f "$TMUX_ARGS_FILE2"
rm -rf "$WORKDIR4"
echo "$all_args4" | grep -qF "exec " || fail "pane command (no prefix dirs) does not use exec"
echo "$all_args4" | grep -qF "mosaic yolo pi" || fail "pane command does not include agent command when no prefix"
# ── Test 5: candidate dir already in LAUNCHER $PATH is still baked into pane ──
#
# Regression guard for the bug where _build_runtime_bin_prefix() used to skip
# a candidate because it was already present in the launcher process's $PATH.
# That check was wrong: the pane inherits the tmux SERVER environment, not the
# launcher's env. Even if a dir is on the launcher's PATH it must always be
# baked into the pane's PATH export.
#
# We prove this by setting PATH to include FAKE_RUNTIME_BIN5 (the candidate),
# then asserting the generated new-session command still exports it.
TMUX_ARGS_FILE5=$(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")
cat > "$FAKE_BIN5/tmux" <<SHIM5
#!/usr/bin/env bash
subcmd="\$3"
if [ "\$subcmd" = "has-session" ]; then exit 1; fi
if [ "\$subcmd" = "new-session" ]; then
printf '%s\n' "\$@" > "$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 "$FAKE_BIN5/tmux"
SOCKET5="mosaic-agent-test5-$RANDOM-$$"
AGENT5="agent5-$RANDOM"
WORKDIR5=$(mktemp -d)
CLEANUP_DIRS+=("$WORKDIR5")
CLEANUP_SOCKETS+=("$SOCKET5")
# FAKE_RUNTIME_BIN5 is deliberately placed on the LAUNCHER PATH so that the
# old (buggy) code would have skipped it. The correct code must still include
# it in the pane PATH export.
PATH="$FAKE_BIN5:$FAKE_RUNTIME_BIN5:$PATH" \
MOSAIC_TMUX_SOCKET="$SOCKET5" \
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)
rm -f "$TMUX_ARGS_FILE5"
rm -rf "$WORKDIR5"
echo "--- test 5: launcher-PATH candidate must still appear in pane export ---"
echo "$all_args5"
echo "--- end test 5 args ---"
echo "$all_args5" | grep -qF "export PATH=" || \
fail "test5: pane command does not export PATH when candidate is on launcher 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"

View File

@@ -0,0 +1,67 @@
#!/usr/bin/env bash
# test-install-migration.sh — fixture matrix for the v2→v3 (Constitution) upgrade
# migration in install.sh. Runs the installer against throwaway MOSAIC_HOME dirs
# with MOSAIC_SYNC_ONLY=1 (file phase only — no environment-touching post-install)
# and asserts the framework-owned-overwrite + user-preserve + backup semantics.
#
# Mirrors the TS fixture suite in packages/mosaic/src/config/file-adapter.test.ts;
# both installers MUST behave identically.
#
# Usage: bash test-install-migration.sh
set -uo pipefail
FW="$(cd "$(dirname "${BASH_SOURCE[0]}")/../../.." && pwd)" # packages/mosaic/framework
INSTALL="$FW/install.sh"
DEFA="$FW/defaults"
pass=0; fail=0
chk() { if eval "$2"; then echo "$1"; pass=$((pass + 1)); else echo "$1"; fail=$((fail + 1)); fi; }
run() { MOSAIC_HOME="$1" MOSAIC_INSTALL_MODE="$2" MOSAIC_SYNC_ONLY=1 bash "$INSTALL" >/dev/null 2>&1; }
echo "install.sh v2→v3 migration fixture matrix:"
# F1 — fresh install
T1=$(mktemp -d); run "$T1" overwrite
chk "F1 fresh: CONSTITUTION/AGENTS/STANDARDS/TOOLS seeded" \
"[ -f '$T1/CONSTITUTION.md' ] && [ -f '$T1/AGENTS.md' ] && [ -f '$T1/STANDARDS.md' ] && [ -f '$T1/TOOLS.md' ]"
chk "F1 fresh: AGENTS == shipped default" "cmp -s '$T1/AGENTS.md' '$DEFA/AGENTS.md'"
chk "F1 fresh: framework-version stamped 3" "[ \"\$(cat '$T1/.framework-version' 2>/dev/null)\" = 3 ]"
# F2 — legacy install with a user-edited AGENTS.md (the sanctioned pre-constitution customization)
T2=$(mktemp -d); mkdir -p "$T2/credentials"
printf '# user-edited AGENTS pre-constitution\n' > "$T2/AGENTS.md"
printf '# my persona\n' > "$T2/SOUL.md"
printf 'token\n' > "$T2/credentials/c.json"
echo 2 > "$T2/.framework-version"
run "$T2" keep
chk "F2 legacy-edited: AGENTS overwritten to framework version" "cmp -s '$T2/AGENTS.md' '$DEFA/AGENTS.md'"
chk "F2 legacy-edited: prior AGENTS saved to .pre-constitution.bak" \
"grep -q 'user-edited AGENTS pre-constitution' '$T2/AGENTS.md.pre-constitution.bak'"
chk "F2 legacy-edited: SOUL.md preserved" "grep -q 'my persona' '$T2/SOUL.md'"
chk "F2 legacy-edited: credentials preserved" "grep -q token '$T2/credentials/c.json'"
chk "F2 legacy-edited: CONSTITUTION.md installed" "[ -f '$T2/CONSTITUTION.md' ]"
run "$T2" keep
chk "F2 idempotent: .pre-constitution.bak preserved across a 2nd upgrade" \
"grep -q 'user-edited AGENTS pre-constitution' '$T2/AGENTS.md.pre-constitution.bak'"
# F3 — user-tuned STANDARDS.md
T3=$(mktemp -d); printf '# tuned standards\n' > "$T3/STANDARDS.md"; printf '# persona\n' > "$T3/SOUL.md"; echo 2 > "$T3/.framework-version"
run "$T3" keep
chk "F3 tuned-standard: STANDARDS overwritten" "cmp -s '$T3/STANDARDS.md' '$DEFA/STANDARDS.md'"
chk "F3 tuned-standard: tuned copy backed up" "grep -q 'tuned standards' '$T3/STANDARDS.md.pre-constitution.bak'"
# F4 — unattended / no TTY (stdin closed): must complete without hanging, default to keep
T4=$(mktemp -d); printf '# persona\n' > "$T4/SOUL.md"; printf '# old\n' > "$T4/AGENTS.md"; echo 2 > "$T4/.framework-version"
MOSAIC_HOME="$T4" MOSAIC_SYNC_ONLY=1 bash "$INSTALL" </dev/null >/dev/null 2>&1
chk "F4 no-TTY: completed, AGENTS updated" "cmp -s '$T4/AGENTS.md' '$DEFA/AGENTS.md'"
# F5 — failure path must not corrupt existing data (invalid mode rejected before any file op)
T5=$(mktemp -d); mkdir -p "$T5/credentials"; printf '# orig\n' > "$T5/SOUL.md"; printf 'keepme\n' > "$T5/credentials/c.json"; echo 2 > "$T5/.framework-version"
MOSAIC_HOME="$T5" MOSAIC_INSTALL_MODE=bogus MOSAIC_SYNC_ONLY=1 bash "$INSTALL" >/dev/null 2>&1; rc=$?
chk "F5 failure: invalid mode rejected (nonzero exit)" "[ $rc -ne 0 ]"
chk "F5 failure: SOUL + credentials intact" "grep -q orig '$T5/SOUL.md' && grep -q keepme '$T5/credentials/c.json'"
rm -rf "$T1" "$T2" "$T3" "$T4" "$T5"
echo
echo "RESULT: $pass passed, $fail failed"
[ "$fail" -eq 0 ]

View File

@@ -12,7 +12,7 @@
# 2. STRUCTURAL (private $HOME default in *.sh) — scanned everywhere EXCEPT examples/,
# because worked example overlays/personas legitimately show placeholder paths.
#
# File types: *.md, *.sh, *.ps1, *.json, and the extensionless CLI scripts under
# File types: *.md, *.sh, *.ps1, *.json, *.yml/*.yaml, *.toml, *.env, *.service, and the CLI scripts under
# tools/_scripts/. Excludes node_modules/ and this gate file.
#
# NOTE: '\bPDA\b' intentionally matches "PDA-friendly" (the contamination removed in P2);
@@ -39,7 +39,7 @@ cd "$FRAMEWORK_ROOT" || { echo "FRAMEWORK_ROOT not found: $FRAMEWORK_ROOT" >&2;
# Identity scope = ALL shipped text files (examples/ INCLUDED).
_files_identity() {
find . -type f \
\( -name '*.md' -o -name '*.sh' -o -name '*.ps1' -o -name '*.json' -o -path '*/tools/_scripts/*' \) \
\( -name '*.md' -o -name '*.sh' -o -name '*.ps1' -o -name '*.json' -o -name '*.yml' -o -name '*.yaml' -o -name '*.toml' -o -name '*.env' -o -name '*.service' -o -path '*/tools/_scripts/*' \) \
-not -path '*/node_modules/*' -not -path "./$SELF_REL" -print0
}
# Structural scope = shipped scripts, examples/ EXCLUDED.
@@ -53,9 +53,15 @@ _selftest() {
local tmp; tmp="$(mktemp -d)" || return 1
printf 'contact jason.woltje at jarvis-brain (PDA-friendly)\n' > "$tmp/planted.md"
printf 'X="${VAR:-$HOME/src/whatever/x.json}"\n' > "$tmp/planted.sh"
printf 'name: jason-woltje\n' > "$tmp/planted.yaml"
printf '[Service]\nUser=jarvis\n' > "$tmp/planted.service"
local rc=0
grep -qIEi "$DENYLIST" "$tmp/planted.md" || { echo "✗ SELF-TEST: identity denylist regex broken" >&2; rc=1; }
grep -qIE "$STRUCTURAL_SH" "$tmp/planted.sh" || { echo "✗ SELF-TEST: structural regex broken" >&2; rc=1; }
# Prove the identity scan covers the config formats it claims to (yaml/service/etc).
local n_ext
n_ext=$(find "$tmp" -type f \( -name '*.yaml' -o -name '*.service' \) -print0 | xargs -0 -r grep -lIEi "$DENYLIST" 2>/dev/null | wc -l)
[[ "$n_ext" -eq 2 ]] || { echo "✗ SELF-TEST: identity scan does not cover .yaml/.service extensions" >&2; rc=1; }
rm -rf "$tmp"; return $rc
}
_selftest || exit 2

View File

@@ -1,6 +1,6 @@
{
"name": "@mosaicstack/mosaic",
"version": "0.0.34",
"version": "0.0.36",
"repository": {
"type": "git",
"url": "https://git.mosaicstack.dev/mosaicstack/stack.git",

View File

@@ -10,11 +10,17 @@ import {
buildAgentWatchCreateViewerCommand,
buildAgentWatchKillViewerCommand,
buildAgentVerifyAcceptedCommand,
buildEnableLingerCommand,
buildFleetServiceCommand,
buildSystemdEnableCommand,
buildSystemdShowCommand,
buildTmuxListPanesCommand,
buildTmuxListSessionsCommand,
classifySendResult,
countOrchestrators,
detectDrift,
enableFleetUnits,
FLEET_PROFILES,
generateAgentEnv,
getDefaultOperatorSourceLabel,
getDefaultTenantAndHost,
@@ -24,14 +30,20 @@ import {
loadFleetRoster,
mergeAgentEnv,
parseHeartbeat,
parseInitProfile,
parseSystemdShow,
parseTmuxListPanes,
parseTmuxListSessions,
registerFleetCommand,
resolveFleetPaths,
resolvePresetFilename,
RUNTIME_ACCEPTABLE_COMMANDS,
VERIFY_DEFAULT_TIMEOUT_MS,
VERIFY_POLL_INTERVAL_MS,
type AgentPsRow,
type CommandRunner,
type FleetProfile,
type FleetRoster,
type InteractiveRunner,
type SleepFn,
} from './fleet.js';
@@ -839,6 +851,23 @@ describe('fleet ps — heartbeat parsing', () => {
expect(hb.health).toBe('unknown');
expect(hb.ts).toBeNull();
});
it('honors MOSAIC_HEARTBEAT_INTERVAL for the freshness threshold', () => {
const prev = process.env.MOSAIC_HEARTBEAT_INTERVAL;
try {
// A 60s-old beat is STALE at the default 15s interval (3x15 = 45s)...
const ts = new Date(NOW - 60_000).toISOString();
const content = `ts=${ts}\npid=1\nstatus=ok\n`;
delete process.env.MOSAIC_HEARTBEAT_INTERVAL;
expect(parseHeartbeat(content, NOW).health).toBe('stale');
// ...but HEALTHY when the operator widened the interval to 30s (3x30 = 90s).
process.env.MOSAIC_HEARTBEAT_INTERVAL = '30';
expect(parseHeartbeat(content, NOW).health).toBe('healthy');
} finally {
if (prev === undefined) delete process.env.MOSAIC_HEARTBEAT_INTERVAL;
else process.env.MOSAIC_HEARTBEAT_INTERVAL = prev;
}
});
});
describe('fleet ps — systemd show parsing', () => {
@@ -909,6 +938,118 @@ 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', () => {
@@ -957,6 +1098,10 @@ describe('fleet ps — JSON output shape (FR-6)', () => {
exitCode: 0,
};
}
if (fullArgs.includes('list-sessions')) {
// Only the roster agent session on the socket (no unmanaged sessions)
return { stdout: 'canary-pi\n', stderr: '', exitCode: 0 };
}
return { stdout: '', stderr: '', exitCode: 0 };
};
@@ -1000,11 +1145,15 @@ describe('fleet ps — JSON output shape (FR-6)', () => {
expect(row.runtime).toBe('pi');
expect(row.systemdActive).toBe('active');
expect(row.systemdEnabled).toBe('disabled');
// managed/source fields for roster agents
expect(row.managed).toBe(true);
expect(row.source).toBe('roster');
});
});
describe('fleet ps — command sequences issued', () => {
it('issues systemd show + tmux list-panes per agent', async () => {
it('issues systemd show + tmux list-panes per agent, then list-sessions for socket discovery', async () => {
const home = await mkdtemp(join(tmpdir(), 'mosaic-fleet-'));
const rosterPath = join(home, 'fleet', 'roster.yaml');
await mkdir(join(home, 'fleet'), { recursive: true });
@@ -1018,6 +1167,10 @@ describe('fleet ps — command sequences issued', () => {
const calls: string[][] = [];
const runner: CommandRunner = async (command, args) => {
calls.push([command, ...args]);
if ([command, ...args].join(' ').includes('list-sessions')) {
// Only the roster agent — no unmanaged sessions
return { stdout: 'coder0\n', stderr: '', exitCode: 0 };
}
return {
stdout: 'ActiveState=inactive\nSubState=dead\nUnitFileState=enabled\n',
stderr: '',
@@ -1038,6 +1191,7 @@ describe('fleet ps — command sequences issued', () => {
expect(calls).toEqual([
buildSystemdShowCommand('coder0'),
buildTmuxListPanesCommand('coder0', 'mosaic-factory'),
buildTmuxListSessionsCommand('mosaic-factory'),
]);
} finally {
console.log = origLog;
@@ -1046,6 +1200,258 @@ describe('fleet ps — command sequences issued', () => {
});
});
describe('buildTmuxListSessionsCommand', () => {
it('builds exact list-sessions command with session_name format', () => {
expect(buildTmuxListSessionsCommand('mosaic-factory')).toEqual([
'tmux',
'-L',
'mosaic-factory',
'list-sessions',
'-F',
'#{session_name}',
]);
});
it('uses DEFAULT_SOCKET_NAME when socket is omitted', () => {
const cmd = buildTmuxListSessionsCommand();
expect(cmd[2]).toBe('mosaic-factory');
});
});
describe('parseTmuxListSessions', () => {
it('splits newline-delimited session names', () => {
expect(parseTmuxListSessions('canary-pi\n_holder\nsome-adhoc\n')).toEqual([
'canary-pi',
'_holder',
'some-adhoc',
]);
});
it('returns empty array for blank output', () => {
expect(parseTmuxListSessions('')).toEqual([]);
expect(parseTmuxListSessions(' \n \n')).toEqual([]);
});
it('trims whitespace from each line', () => {
expect(parseTmuxListSessions(' canary-pi \n some-adhoc \n')).toEqual([
'canary-pi',
'some-adhoc',
]);
});
});
describe('fleet ps — unmanaged socket sessions', () => {
it('includes unmanaged session row flagged UNMANAGED and excludes _holder', async () => {
const home = await mkdtemp(join(tmpdir(), 'mosaic-fleet-'));
const rosterPath = join(home, 'fleet', 'roster.yaml');
await mkdir(join(home, 'fleet'), { recursive: true });
await writeFile(
rosterPath,
[
'version: 1',
'transport: tmux',
'agents:',
' - name: canary-pi',
' runtime: pi',
' class: canary',
].join('\n'),
);
const nowMs = Date.now();
const activityEpoch = Math.floor((nowMs - 10_000) / 1000);
const runner: CommandRunner = async (command, args) => {
const full = [command, ...args].join(' ');
if (full.includes('list-sessions')) {
// Socket has: canary-pi (roster), _holder (excluded), some-adhoc (unmanaged)
return { stdout: 'canary-pi\n_holder\nsome-adhoc\n', stderr: '', exitCode: 0 };
}
if (full.includes('list-panes')) {
return { stdout: `99999 bash 0 ${activityEpoch}\n`, stderr: '', exitCode: 0 };
}
if (full.includes('systemctl') && full.includes('show')) {
return {
stdout: 'ActiveState=inactive\nSubState=dead\nUnitFileState=unknown\n',
stderr: '',
exitCode: 0,
};
}
return { stdout: '', stderr: '', exitCode: 0 };
};
const lines: string[] = [];
const origLog = console.log;
console.log = (msg: string) => {
lines.push(msg);
};
const program = new Command();
program.exitOverride();
registerFleetCommand(program, { runner, mosaicHome: home });
try {
await program.parseAsync(['node', 'mosaic', 'fleet', 'ps', '--json']);
} finally {
console.log = origLog;
await rm(home, { recursive: true, force: true });
}
const json = JSON.parse(lines.join('')) as AgentPsRow[];
expect(Array.isArray(json)).toBe(true);
// Should have 2 rows: canary-pi (roster) + some-adhoc (unmanaged); _holder excluded
expect(json).toHaveLength(2);
// Roster agent comes first
const rosterRow = json[0]!;
expect(rosterRow.name).toBe('canary-pi');
expect(rosterRow.managed).toBe(true);
expect(rosterRow.source).toBe('roster');
// Unmanaged session comes second
const unmanagedRow = json[1]!;
expect(unmanagedRow.name).toBe('some-adhoc');
expect(unmanagedRow.managed).toBe(false);
expect(unmanagedRow.source).toBe('socket');
expect(unmanagedRow.runtime).toBe('unknown');
// _holder must not appear
expect(json.map((r) => r.name)).not.toContain('_holder');
// tenant_id and host must be present on unmanaged rows
expect(typeof unmanagedRow.tenant_id).toBe('string');
expect(unmanagedRow.tenant_id.length).toBeGreaterThan(0);
expect(typeof unmanagedRow.host).toBe('string');
expect(unmanagedRow.host.length).toBeGreaterThan(0);
// driftFlag must be false for unmanaged (no roster runtime to compare)
expect(unmanagedRow.driftFlag).toBe(false);
});
it('shows UNMANAGED flag in table output for unmanaged sessions', async () => {
const home = await mkdtemp(join(tmpdir(), 'mosaic-fleet-'));
const rosterPath = join(home, 'fleet', 'roster.yaml');
await mkdir(join(home, 'fleet'), { recursive: true });
await writeFile(
rosterPath,
[
'version: 1',
'transport: tmux',
'agents:',
' - name: canary-pi',
' runtime: pi',
' class: canary',
].join('\n'),
);
const runner: CommandRunner = async (command, args) => {
const full = [command, ...args].join(' ');
if (full.includes('list-sessions')) {
return { stdout: 'canary-pi\nsome-adhoc\n', stderr: '', exitCode: 0 };
}
if (full.includes('list-panes')) {
return { stdout: '0 bash 1 0\n', stderr: '', exitCode: 0 };
}
if (full.includes('systemctl') && full.includes('show')) {
return {
stdout: 'ActiveState=inactive\nSubState=dead\nUnitFileState=unknown\n',
stderr: '',
exitCode: 0,
};
}
return { stdout: '', stderr: '', exitCode: 0 };
};
const lines: string[] = [];
const origLog = console.log;
console.log = (msg: string) => {
lines.push(msg);
};
const program = new Command();
program.exitOverride();
registerFleetCommand(program, { runner, mosaicHome: home });
try {
await program.parseAsync(['node', 'mosaic', 'fleet', 'ps']);
} finally {
console.log = origLog;
await rm(home, { recursive: true, force: true });
}
const tableOutput = lines.join('\n');
// some-adhoc row must appear with UNMANAGED flag
expect(tableOutput).toMatch(/some-adhoc/);
expect(tableOutput).toMatch(/UNMANAGED/);
// canary-pi roster row must not have UNMANAGED
const rosterLine = lines.find((l) => l.includes('canary-pi'));
expect(rosterLine).toBeDefined();
expect(rosterLine).not.toMatch(/UNMANAGED/);
});
it('gracefully shows only roster rows when list-sessions fails (socket missing)', async () => {
const home = await mkdtemp(join(tmpdir(), 'mosaic-fleet-'));
const rosterPath = join(home, 'fleet', 'roster.yaml');
await mkdir(join(home, 'fleet'), { recursive: true });
await writeFile(
rosterPath,
[
'version: 1',
'transport: tmux',
'agents:',
' - name: canary-pi',
' runtime: pi',
' class: canary',
].join('\n'),
);
const runner: CommandRunner = async (command, args) => {
const full = [command, ...args].join(' ');
if (full.includes('list-sessions')) {
// Simulate socket missing
return { stdout: '', stderr: 'no server running on /tmp/...', exitCode: 1 };
}
if (full.includes('list-panes')) {
return { stdout: '12345 pi 0 0\n', stderr: '', exitCode: 0 };
}
if (full.includes('systemctl') && full.includes('show')) {
return {
stdout: 'ActiveState=inactive\nSubState=dead\nUnitFileState=enabled\n',
stderr: '',
exitCode: 0,
};
}
return { stdout: '', stderr: '', exitCode: 0 };
};
const lines: string[] = [];
const origLog = console.log;
console.log = (msg: string) => {
lines.push(msg);
};
const program = new Command();
program.exitOverride();
registerFleetCommand(program, { runner, mosaicHome: home });
try {
// Must not throw
await expect(
program.parseAsync(['node', 'mosaic', 'fleet', 'ps', '--json']),
).resolves.toBeDefined();
} finally {
console.log = origLog;
await rm(home, { recursive: true, force: true });
}
const json = JSON.parse(lines.join('')) as AgentPsRow[];
// Only roster agent visible; no crash
expect(json).toHaveLength(1);
expect(json[0]!.name).toBe('canary-pi');
expect(json[0]!.managed).toBe(true);
});
});
describe('agent watch', () => {
it('builds exact grouped-viewer creation command', () => {
expect(
@@ -1748,3 +2154,270 @@ describe('agent send --verify', () => {
expect(VERIFY_DEFAULT_TIMEOUT_MS).toBe(6_000);
});
});
// ---------------------------------------------------------------------------
// Fleet Phase F1: config-type presets + AI-free init wizard
// ---------------------------------------------------------------------------
describe('fleet preset rosters', () => {
const examplesDir = resolve(process.cwd(), 'framework', 'fleet', 'examples');
it.each(['general', 'coding', 'research', 'hybrid'] as FleetProfile[])(
'%s preset: loads via loadFleetRoster and has exactly one orchestrator',
async (preset) => {
const rosterPath = join(examplesDir, `${preset}.yaml`);
const roster = await loadFleetRoster(rosterPath);
expect(countOrchestrators(roster)).toBe(1);
expect(roster.agents.find((a) => a.name === 'orchestrator')).toBeDefined();
},
);
it('general preset: orchestrator + one generalist worker', async () => {
const roster = await loadFleetRoster(join(examplesDir, 'general.yaml'));
expect(roster.agents.map((a) => a.name)).toEqual(['orchestrator', 'generalist']);
expect(roster.agents.find((a) => a.name === 'orchestrator')?.runtime).toBe('claude');
expect(roster.agents.find((a) => a.name === 'generalist')?.runtime).toBe('pi');
});
it('coding preset: orchestrator + coder0 + coder1 + reviewer', async () => {
const roster = await loadFleetRoster(join(examplesDir, 'coding.yaml'));
expect(roster.agents.map((a) => a.name)).toEqual([
'orchestrator',
'coder0',
'coder1',
'reviewer',
]);
});
it('research preset: orchestrator + researcher0 + researcher1 + analyst', async () => {
const roster = await loadFleetRoster(join(examplesDir, 'research.yaml'));
expect(roster.agents.map((a) => a.name)).toEqual([
'orchestrator',
'researcher0',
'researcher1',
'analyst',
]);
});
it('hybrid preset: orchestrator + coder0 + researcher0 + reviewer', async () => {
const roster = await loadFleetRoster(join(examplesDir, 'hybrid.yaml'));
expect(roster.agents.map((a) => a.name)).toEqual([
'orchestrator',
'coder0',
'researcher0',
'reviewer',
]);
});
it('worker agents in new presets use pi runtime with model_hint openai-codex/gpt-5.5:high', async () => {
for (const preset of ['general', 'coding', 'research', 'hybrid'] as FleetProfile[]) {
const roster = await loadFleetRoster(join(examplesDir, `${preset}.yaml`));
const workers = roster.agents.filter((a) => a.name !== 'orchestrator');
for (const worker of workers) {
expect(worker.runtime).toBe('pi');
expect(worker.modelHint).toBe('openai-codex/gpt-5.5:high');
}
}
});
it('orchestrator in new presets uses claude runtime with persistent_persona', async () => {
for (const preset of ['general', 'coding', 'research', 'hybrid'] as FleetProfile[]) {
const roster = await loadFleetRoster(join(examplesDir, `${preset}.yaml`));
const orch = roster.agents.find((a) => a.name === 'orchestrator');
expect(orch?.runtime).toBe('claude');
expect(orch?.persistentPersona).toBe(true);
}
});
it('new presets are sanitized: no operator identity tokens', async () => {
for (const preset of ['general', 'coding', 'research', 'hybrid'] as FleetProfile[]) {
const text = await readFile(join(examplesDir, `${preset}.yaml`), 'utf8');
expect(text).not.toMatch(/jarvis|jason|woltje/i);
// working_directory must not reference ~/src or /home
expect(text).not.toMatch(/~\/src|\/home\//);
}
});
});
describe('parseInitProfile', () => {
it('accepts all six fleet profiles', () => {
expect(parseInitProfile('general')).toBe('general');
expect(parseInitProfile('coding')).toBe('coding');
expect(parseInitProfile('research')).toBe('research');
expect(parseInitProfile('hybrid')).toBe('hybrid');
expect(parseInitProfile('minimal')).toBe('minimal');
expect(parseInitProfile('local-canary')).toBe('local-canary');
});
it('rejects unknown profiles with a message listing all valid names', () => {
expect(() => parseInitProfile('typo')).toThrow('Unsupported fleet profile');
expect(() => parseInitProfile('typo')).toThrow('general');
expect(() => parseInitProfile('typo')).toThrow('coding');
});
it('FLEET_PROFILES contains all six valid profile names', () => {
expect(FLEET_PROFILES).toContain('general');
expect(FLEET_PROFILES).toContain('coding');
expect(FLEET_PROFILES).toContain('research');
expect(FLEET_PROFILES).toContain('hybrid');
expect(FLEET_PROFILES).toContain('minimal');
expect(FLEET_PROFILES).toContain('local-canary');
});
});
describe('resolvePresetFilename', () => {
it.each(FLEET_PROFILES)('maps %s to %s.yaml', (profile) => {
expect(resolvePresetFilename(profile)).toBe(`${profile}.yaml`);
});
});
describe('fleet init wizard', () => {
let cleanup: string | undefined;
afterEach(async () => {
if (cleanup) {
await rm(cleanup, { recursive: true, force: true });
cleanup = undefined;
}
});
it('defaults to general when stdin is not a TTY and no --profile is given', async () => {
cleanup = await tempDir();
const rosterPath = join(cleanup, 'fleet', 'roster.yaml');
const frameworkRoot = resolve(process.cwd(), 'framework');
const stderrMessages: string[] = [];
const stderrSpy = vi.spyOn(process.stderr, 'write').mockImplementation((msg) => {
stderrMessages.push(String(msg));
return true;
});
const program = new Command();
program.exitOverride();
// isStdinTTY: false simulates non-interactive environment
registerFleetCommand(program, { frameworkRoot, mosaicHome: cleanup, isStdinTTY: false });
try {
await program.parseAsync([
'node',
'mosaic',
'fleet',
'--roster',
rosterPath,
'init',
'--write',
]);
const content = await readFile(rosterPath, 'utf8');
// Should have written the general preset
expect(content).toContain('name: orchestrator');
expect(content).toContain('name: generalist');
// Stderr should explain the fallback
expect(stderrMessages.join('')).toMatch(/defaulting to fleet profile "general"/);
} finally {
stderrSpy.mockRestore();
}
});
it('uses --profile to select preset without wizard (non-TTY path)', async () => {
cleanup = await tempDir();
const rosterPath = join(cleanup, 'fleet', 'roster.yaml');
const frameworkRoot = resolve(process.cwd(), 'framework');
const program = new Command();
program.exitOverride();
registerFleetCommand(program, { frameworkRoot, mosaicHome: cleanup, isStdinTTY: false });
try {
await program.parseAsync([
'node',
'mosaic',
'fleet',
'--roster',
rosterPath,
'init',
'--profile',
'coding',
'--write',
]);
const content = await readFile(rosterPath, 'utf8');
expect(content).toContain('name: coder0');
expect(content).toContain('name: reviewer');
} finally {
// cleanup handled by afterEach
}
});
it('written roster has exactly one orchestrator agent (countOrchestrators validation)', async () => {
cleanup = await tempDir();
const frameworkRoot = resolve(process.cwd(), 'framework');
for (const preset of ['general', 'coding', 'research', 'hybrid'] as FleetProfile[]) {
const rosterPath = join(cleanup, `${preset}-roster.yaml`);
const program = new Command();
program.exitOverride();
registerFleetCommand(program, { frameworkRoot, mosaicHome: cleanup, isStdinTTY: false });
await program.parseAsync([
'node',
'mosaic',
'fleet',
'--roster',
rosterPath,
'init',
'--profile',
preset,
'--write',
]);
const roster = await loadFleetRoster(rosterPath);
expect(countOrchestrators(roster)).toBe(1);
}
});
it('re-init with --write and existing roster requires --force (R8 idempotency)', async () => {
cleanup = await tempDir();
const rosterPath = join(cleanup, 'fleet', 'roster.yaml');
const frameworkRoot = resolve(process.cwd(), 'framework');
const program = new Command();
program.exitOverride();
registerFleetCommand(program, { frameworkRoot, mosaicHome: cleanup, isStdinTTY: false });
// First write
await program.parseAsync([
'node',
'mosaic',
'fleet',
'--roster',
rosterPath,
'init',
'--profile',
'general',
'--write',
]);
// Second write without --force must fail
await expect(
program.parseAsync([
'node',
'mosaic',
'fleet',
'--roster',
rosterPath,
'init',
'--profile',
'general',
'--write',
]),
).rejects.toThrow('Fleet roster already exists');
// With --force must succeed
await program.parseAsync([
'node',
'mosaic',
'fleet',
'--roster',
rosterPath,
'init',
'--profile',
'coding',
'--write',
'--force',
]);
const content = await readFile(rosterPath, 'utf8');
expect(content).toContain('name: coder0');
});
});

View File

@@ -4,6 +4,7 @@ import { homedir, hostname, userInfo } from 'node:os';
import { dirname, join, resolve } from 'node:path';
import { fileURLToPath } from 'node:url';
import { spawn } from 'node:child_process';
import * as readline from 'node:readline';
import type { Command } from 'commander';
import YAML from 'yaml';
@@ -41,6 +42,11 @@ export interface FleetCommandDeps {
sleepFn?: SleepFn;
mosaicHome?: string;
frameworkRoot?: string;
/**
* Injectable TTY check for `fleet init` wizard. Defaults to process.stdin.isTTY.
* Tests stub this to simulate interactive or non-interactive environments.
*/
isStdinTTY?: boolean;
}
interface RawFleetRoster {
@@ -210,6 +216,93 @@ 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,
@@ -275,6 +368,16 @@ export function buildAgentTailCommand(
// ---------------------------------------------------------------------------
export const HEARTBEAT_INTERVAL_MS = 15_000;
/**
* Heartbeat interval in ms, honoring MOSAIC_HEARTBEAT_INTERVAL (seconds) so the
* `fleet ps` freshness threshold matches the writer sidecar's actual cadence
* (start-agent-session.sh). Falls back to HEARTBEAT_INTERVAL_MS (15s).
*/
export function heartbeatIntervalMs(): number {
const sec = Number.parseInt(process.env.MOSAIC_HEARTBEAT_INTERVAL ?? '', 10);
return Number.isFinite(sec) && sec > 0 ? sec * 1000 : HEARTBEAT_INTERVAL_MS;
}
export const HEARTBEAT_HEALTHY_MULTIPLIER = 3;
export interface HeartbeatInfo {
@@ -302,6 +405,10 @@ export interface AgentPsRow {
driftFlag: boolean;
/** active but UnitFileState=disabled */
bootEnableWarning: boolean;
/** true = came from roster; false = found on socket but not in roster */
managed: boolean;
/** "roster" = defined in roster.yaml; "socket" = discovered via tmux list-sessions */
source: 'roster' | 'socket';
}
/**
@@ -344,6 +451,26 @@ export function buildTmuxListPanesCommand(
];
}
/**
* Returns the tmux list-sessions command to enumerate all sessions on a socket.
* Format: `tmux -L <socket> list-sessions -F '#{session_name}'`
* Used to discover ad-hoc sessions that are not in the roster.
*/
export function buildTmuxListSessionsCommand(socketName = DEFAULT_SOCKET_NAME): string[] {
return ['tmux', '-L', socketName, 'list-sessions', '-F', '#{session_name}'];
}
/**
* Parse the output of `tmux list-sessions -F '#{session_name}'` into an array of session names.
* Returns an empty array on empty/blank output.
*/
export function parseTmuxListSessions(output: string): string[] {
return output
.split('\n')
.map((line) => line.trim())
.filter((line) => line.length > 0);
}
/**
* Returns the heartbeat file path for an agent.
*/
@@ -379,7 +506,7 @@ export function parseHeartbeat(content: string | null, nowMs = Date.now()): Hear
status = val;
}
}
const thresholdMs = HEARTBEAT_INTERVAL_MS * HEARTBEAT_HEALTHY_MULTIPLIER;
const thresholdMs = heartbeatIntervalMs() * HEARTBEAT_HEALTHY_MULTIPLIER;
let health: 'healthy' | 'stale' | 'unknown' = 'unknown';
let ageMs: number | null = null;
if (ts !== null) {
@@ -437,32 +564,41 @@ 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 canonical command for the
* checking if the pane command doesn't match a known acceptable command for the
* roster's declared runtime.
*
* Known canonical commands per runtime:
* claude → claude
* codex → codex
* opencode → opencode
* pi → pi
* 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
*
* 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 knownCommands: Record<string, string[]> = {
claude: ['claude'],
codex: ['codex'],
opencode: ['opencode'],
pi: ['pi'],
};
const expected = knownCommands[rosterRuntime];
if (!expected) return false;
return !expected.includes(paneCommand);
const acceptable = RUNTIME_ACCEPTABLE_COMMANDS[rosterRuntime];
if (!acceptable) return false;
return !acceptable.includes(paneCommand);
}
/**
@@ -679,19 +815,42 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
cmd
.command('init')
.description('Initialize a local fleet roster')
.option('--profile <name>', 'Roster profile: minimal or local-canary', 'minimal')
.option(
'--profile <name>',
`Roster profile: ${FLEET_PROFILES.join(', ')} (skips interactive wizard)`,
)
.option('--write', 'Write the roster to Mosaic home')
.option('--force', 'Overwrite an existing roster when used with --write')
.action(async (opts: { profile: string; write?: boolean; force?: boolean }) => {
.action(async (opts: { profile?: string; write?: boolean; force?: boolean }) => {
const commandOpts = cmd.opts<{ mosaicHome: string; roster?: string }>();
const activePaths = resolveFleetPaths(commandOpts.mosaicHome);
const profile = parseInitProfile(opts.profile);
const source = join(frameworkRoot, 'fleet', 'examples', `${profile}.yaml`);
let profile: FleetProfile;
if (opts.profile !== undefined) {
// Explicit --profile flag: validate and use it (non-interactive path).
profile = parseInitProfile(opts.profile);
} else {
// No --profile: use wizard when stdin is a TTY, else default to 'general'.
const isTTY = deps.isStdinTTY ?? process.stdin.isTTY ?? false;
if (isTTY) {
profile = await promptFleetProfile();
} else {
process.stderr.write(
'Note: stdin is not a TTY; defaulting to fleet profile "general". ' +
'Use --profile <name> to select a different preset.\n',
);
profile = 'general';
}
}
const source = join(frameworkRoot, 'fleet', 'examples', resolvePresetFilename(profile));
const content = await readFile(source, 'utf8');
if (!opts.write) {
console.log(content.trimEnd());
return;
}
const destination = commandOpts.roster ?? activePaths.rosterPath;
if (!opts.force && (await canRead(destination))) {
throw new Error(
@@ -700,18 +859,44 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
}
await mkdir(dirname(destination), { recursive: true });
await writeFile(destination, content);
console.log(`Wrote fleet roster: ${destination}`);
// Validate: exactly one orchestrator required (R5) — friendly summary on success.
const written = await loadFleetRoster(destination);
const orchCount = countOrchestrators(written);
if (orchCount !== 1) {
process.stderr.write(
`Warning: fleet roster at ${destination} has ${orchCount} orchestrator agent(s) (expected exactly 1).\n`,
);
console.log(
`Initialized ${profile} fleet: ${written.agents.length} agent(s). Next: mosaic fleet install`,
);
} else {
const workerCount = written.agents.length - 1;
console.log(
`Initialized ${profile} fleet: 1 orchestrator + ${workerCount} agent(s). Next: mosaic fleet install`,
);
}
});
cmd
.command('install')
.description('Install local fleet tools and user systemd units')
.action(async () => installFleet(cmd, frameworkRoot));
.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);
});
cmd
.command('install-systemd')
.description('Install local fleet tools and user systemd units')
.action(async () => installFleet(cmd, frameworkRoot));
.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);
});
for (const action of ['start', 'stop', 'restart'] as const) {
cmd
@@ -791,7 +976,9 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
cmd
.command('ps')
.description('Show real-time status for all roster agents (systemd + tmux + heartbeat)')
.description(
'Show real-time status for all roster agents and unmanaged socket sessions (systemd + tmux + heartbeat)',
)
.option('--json', 'Print JSON array')
.action(async (opts: { json?: boolean }) => {
const commandOpts = cmd.opts<{ mosaicHome: string; roster?: string }>();
@@ -802,6 +989,9 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
const rows: AgentPsRow[] = [];
// Build the set of roster agent names for quick lookup when filtering socket sessions.
const rosterAgentNames = new Set(roster.agents.map((a) => a.name));
for (const agent of roster.agents) {
// systemd show
const showResult = await runner(...splitCommand(buildSystemdShowCommand(agent.name)));
@@ -842,9 +1032,75 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
heartbeat: hb,
driftFlag,
bootEnableWarning,
managed: true,
source: 'roster',
});
}
// Enumerate all live sessions on the socket to surface unmanaged (ad-hoc) sessions.
// If list-sessions fails (socket not up), silently skip — show roster rows only.
try {
const listSessionsResult = await runner(
...splitCommand(buildTmuxListSessionsCommand(roster.tmux.socketName)),
);
if (listSessionsResult.exitCode === 0) {
const socketSessions = parseTmuxListSessions(listSessionsResult.stdout);
const holderSession = roster.tmux.holderSession;
for (const sessionName of socketSessions) {
// Skip roster agents (already in rows) and the holder session (infrastructure).
if (rosterAgentNames.has(sessionName) || sessionName === holderSession) {
continue;
}
// tmux list-panes for pane info
const panesResult = await runner(
...splitCommand(buildTmuxListPanesCommand(sessionName, roster.tmux.socketName)),
);
const paneInfo = parseTmuxListPanes(panesResult.stdout, nowMs);
// heartbeat — try reading the .hb file using the same path convention
const hbFile = heartbeatPath(sessionName, activePaths.mosaicHome);
let hbContent: string | null = null;
try {
hbContent = await readFile(hbFile, 'utf8');
} catch {
hbContent = null;
}
const hb = parseHeartbeat(hbContent, nowMs);
// systemd — check if mosaic-agent@<name>.service exists (usually inactive for ad-hoc)
const showResult = await runner(...splitCommand(buildSystemdShowCommand(sessionName)));
const sysInfo = parseSystemdShow(showResult.stdout);
const bootEnableWarning =
sysInfo.ActiveState === 'active' && sysInfo.UnitFileState === 'disabled';
rows.push({
name: sessionName,
tenant_id,
host,
// runtime unknown — not in roster
runtime: 'unknown',
systemdActive: sysInfo.ActiveState,
systemdEnabled: sysInfo.UnitFileState,
paneAlive: !paneInfo.dead,
panePid: paneInfo.pid,
paneCommand: paneInfo.command,
idleSeconds: paneInfo.idleSeconds,
heartbeat: hb,
// No roster runtime to compare — drift is not meaningful for unmanaged sessions
driftFlag: false,
bootEnableWarning,
managed: false,
source: 'socket',
});
}
}
} catch {
// list-sessions failed (socket missing or permission error) — show roster rows only
}
if (opts.json) {
console.log(JSON.stringify(rows, null, 2));
return;
@@ -876,6 +1132,7 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
? `${Math.round(row.heartbeat.ageMs / 1000)}s/${row.heartbeat.health}`
: `unknown`;
const flags: string[] = [];
if (!row.managed) flags.push('UNMANAGED');
if (row.driftFlag) flags.push('DRIFT');
if (row.bootEnableWarning) flags.push('BOOT-ENABLE');
@@ -1466,11 +1723,96 @@ function splitCommand(command: string[]): [string, string[]] {
return [bin, args];
}
function parseInitProfile(profile: string): 'minimal' | 'local-canary' {
if (profile === 'minimal' || profile === 'local-canary') {
return profile;
/** All supported fleet profile names. */
export type FleetProfile =
| 'general'
| 'coding'
| 'research'
| 'hybrid'
| 'minimal'
| 'local-canary';
/** The list of all valid fleet profile names, for wizard menus and error messages. */
export const FLEET_PROFILES: readonly FleetProfile[] = [
'general',
'coding',
'research',
'hybrid',
'minimal',
'local-canary',
];
/**
* Maps a fleet profile name to its example YAML filename (without the path).
* Pure function — testable without I/O.
*/
export function resolvePresetFilename(profile: FleetProfile): string {
return `${profile}.yaml`;
}
/**
* Validate and normalise a fleet profile name string.
* Throws with a clear message on unknown values.
*/
export function parseInitProfile(profile: string): FleetProfile {
if ((FLEET_PROFILES as readonly string[]).includes(profile)) {
return profile as FleetProfile;
}
throw new Error(`Unsupported fleet profile "${profile}". Use: minimal, local-canary.`);
throw new Error(`Unsupported fleet profile "${profile}". Use: ${FLEET_PROFILES.join(', ')}.`);
}
/**
* Count orchestrator agents in a parsed roster.
* Returns the count; callers assert === 1.
*/
export function countOrchestrators(roster: FleetRoster): number {
return roster.agents.filter((a) => a.className === 'orchestrator').length;
}
/**
* Prompt interactively for a fleet profile via stdin readline.
* AI-free: no LLM calls — pure readline menu.
* Resolves with the chosen profile string, or rejects on I/O error.
*/
function promptFleetProfile(): Promise<FleetProfile> {
return new Promise((resolve, reject) => {
const rl = readline.createInterface({ input: process.stdin, output: process.stdout });
const menu = [
'',
'Choose a fleet configuration type:',
' 1) general — orchestrator + generalist worker',
' 2) coding — orchestrator + coder0 + coder1 + reviewer',
' 3) research — orchestrator + researcher0 + researcher1 + analyst',
' 4) hybrid — orchestrator + coder0 + researcher0 + reviewer',
' 5) minimal — single canary-pi agent (no orchestrator)',
' 6) local-canary — legacy canary preset with lead + coder + reviewer',
'',
].join('\n');
process.stdout.write(menu);
rl.question('Enter number or name [1]: ', (answer) => {
rl.close();
const trimmed = answer.trim();
// Map numeric shortcut → name
const byNumber: Record<string, FleetProfile> = {
'1': 'general',
'2': 'coding',
'3': 'research',
'4': 'hybrid',
'5': 'minimal',
'6': 'local-canary',
'': 'general', // default on empty enter
};
if (trimmed in byNumber) {
resolve(byNumber[trimmed]!);
return;
}
try {
resolve(parseInitProfile(trimmed));
} catch (err) {
reject(err);
}
});
});
}
function writeCommandOutput(result: CommandResult): void {

View File

@@ -99,11 +99,8 @@ describe('FileConfigAdapter.syncFramework — defaults seeding', () => {
);
});
it('preserves existing contract files — never overwrites user customization', async () => {
// Also plant a root-level AGENTS.md in sourceDir so that `syncDirectory`
// itself (not just the seed loop) has something to try to overwrite.
// Without this, the test would silently pass even if preserve semantics
// were broken in syncDirectory.
it('overwrites framework-owned files (backup-once) but preserves user-seeded files', async () => {
// Plant a root-level AGENTS.md in sourceDir so syncDirectory's preserve is exercised.
writeFileSync(join(fixture.sourceDir, 'AGENTS.md'), '# shipped AGENTS from source root\n');
writeFileSync(join(fixture.mosaicHome, 'TOOLS.md'), '# user-customized TOOLS\n');
@@ -112,18 +109,50 @@ describe('FileConfigAdapter.syncFramework — defaults seeding', () => {
const adapter = new FileConfigAdapter(fixture.mosaicHome, fixture.sourceDir);
await adapter.syncFramework('keep');
// User-seeded TOOLS.md is preserved.
expect(readFileSync(join(fixture.mosaicHome, 'TOOLS.md'), 'utf-8')).toBe(
'# user-customized TOOLS\n',
);
expect(readFileSync(join(fixture.mosaicHome, 'AGENTS.md'), 'utf-8')).toBe(
// Framework-owned AGENTS.md is overwritten from defaults/ ...
expect(readFileSync(join(fixture.mosaicHome, 'AGENTS.md'), 'utf-8')).toBe('# AGENTS default\n');
// ... and the user's prior copy is backed up exactly once.
expect(readFileSync(join(fixture.mosaicHome, 'AGENTS.md.pre-constitution.bak'), 'utf-8')).toBe(
'# user-customized AGENTS\n',
);
// And the missing contract file still gets seeded.
// Framework-owned STANDARDS.md (absent) gets installed.
expect(readFileSync(join(fixture.mosaicHome, 'STANDARDS.md'), 'utf-8')).toContain(
'# STANDARDS default',
);
});
it('backs up a divergent framework-owned file only once (idempotent across re-sync)', async () => {
writeFileSync(join(fixture.mosaicHome, 'AGENTS.md'), '# user-customized AGENTS\n');
const adapter = new FileConfigAdapter(fixture.mosaicHome, fixture.sourceDir);
await adapter.syncFramework('keep'); // 1st: backup created, AGENTS overwritten
await adapter.syncFramework('keep'); // 2nd: AGENTS already == default, no new backup
expect(readFileSync(join(fixture.mosaicHome, 'AGENTS.md.pre-constitution.bak'), 'utf-8')).toBe(
'# user-customized AGENTS\n',
);
});
it('preserves SOUL.md and credentials through a framework-owned overwrite', async () => {
writeFileSync(join(fixture.mosaicHome, 'SOUL.md'), '# my persona\n');
writeFileSync(join(fixture.mosaicHome, 'AGENTS.md'), '# user-customized AGENTS\n');
mkdirSync(join(fixture.mosaicHome, 'credentials'), { recursive: true });
writeFileSync(join(fixture.mosaicHome, 'credentials', 'c.json'), 'token\n');
const adapter = new FileConfigAdapter(fixture.mosaicHome, fixture.sourceDir);
await adapter.syncFramework('keep');
expect(readFileSync(join(fixture.mosaicHome, 'SOUL.md'), 'utf-8')).toBe('# my persona\n');
expect(readFileSync(join(fixture.mosaicHome, 'credentials', 'c.json'), 'utf-8')).toBe(
'token\n',
);
expect(readFileSync(join(fixture.mosaicHome, 'AGENTS.md'), 'utf-8')).toBe('# AGENTS default\n');
});
it('is a no-op for seeding when defaults/ dir does not exist', async () => {
rmSync(fixture.defaultsDir, { recursive: true });

View File

@@ -13,12 +13,17 @@ import { join } from 'node:path';
* This list must match the explicit seed loop in
* packages/mosaic/framework/install.sh.
*/
export const DEFAULT_SEED_FILES = [
'CONSTITUTION.md',
'AGENTS.md',
'STANDARDS.md',
'TOOLS.md',
] as const;
// Framework-owned contract files: re-copied from defaults/ on every upgrade (a
// divergent existing copy is backed up once to <file>.pre-constitution.bak first).
// MUST match FRAMEWORK_OWNED in packages/mosaic/framework/install.sh (append-friendly).
export const FRAMEWORK_OWNED_FILES = ['CONSTITUTION.md', 'AGENTS.md', 'STANDARDS.md'] as const;
// User-seeded contract files: written once on first install, then owned by the user.
// MUST match USER_SEEDED in packages/mosaic/framework/install.sh.
export const USER_SEEDED_FILES = ['TOOLS.md'] as const;
// Union, retained for callers/tests that assert the full seed set on a fresh install.
export const DEFAULT_SEED_FILES = [...FRAMEWORK_OWNED_FILES, ...USER_SEEDED_FILES] as const;
import type { ConfigService, ConfigSection, ResolvedConfig } from './config-service.js';
import type { SoulConfig, UserConfig, ToolsConfig, InstallAction } from '../types.js';
import { soulSchema, userSchema, toolsSchema } from './schemas.js';
@@ -159,6 +164,7 @@ export class FileConfigAdapter implements ConfigService {
const preservePaths =
action === 'keep' || action === 'reconfigure'
? [
'CONSTITUTION.md',
'AGENTS.md',
'SOUL.md',
'USER.md',
@@ -175,10 +181,10 @@ export class FileConfigAdapter implements ConfigService {
excludeGit: true,
});
// Copy framework-contract files (AGENTS.md, STANDARDS.md, TOOLS.md)
// from framework/defaults/ into the mosaic home root if they don't
// exist yet. These are written on first install only and are never
// overwritten afterwards — the user may have customized them.
// Reconcile framework-contract files from framework/defaults/ into the mosaic
// home root: framework-owned files (CONSTITUTION/AGENTS/STANDARDS) are overwritten
// every upgrade (backup-once); user-seeded files (TOOLS) are written on first
// install only. Mirrors reconcile_framework_files() in install.sh.
//
// SOUL.md and USER.md are deliberately NOT seeded here. They are
// generated from templates by the soul/user wizard stages with
@@ -186,7 +192,22 @@ export class FileConfigAdapter implements ConfigService {
// identity flow and leak placeholder content into the mosaic home.
const defaultsDir = join(this.sourceDir, 'defaults');
if (existsSync(defaultsDir)) {
for (const entry of DEFAULT_SEED_FILES) {
// Framework-owned: overwrite from defaults/ every sync; back up a divergent
// existing copy ONCE to <file>.pre-constitution.bak before the first overwrite.
for (const entry of FRAMEWORK_OWNED_FILES) {
const src = join(defaultsDir, entry);
const dest = join(this.mosaicHome, entry);
if (!existsSync(src) || !statSync(src).isFile()) continue;
// Already current — skip to avoid mtime churn.
if (existsSync(dest) && readFileSync(src).equals(readFileSync(dest))) continue;
const bak = `${dest}.pre-constitution.bak`;
if (existsSync(dest) && !existsSync(bak)) {
copyFileSync(dest, bak);
}
copyFileSync(src, dest);
}
// User-seeded: write only if absent.
for (const entry of USER_SEEDED_FILES) {
const src = join(defaultsDir, entry);
const dest = join(this.mosaicHome, entry);
if (existsSync(dest)) continue;