Compare commits

..

1 Commits

Author SHA1 Message Date
Hermes Agent
5c083763c8 feat(launch): force-load fleet-critical Pi skills + reconcile skill docs
All checks were successful
ci/woodpecker/pr/ci Pipeline was successful
ci/woodpecker/push/ci Pipeline was successful
Pi workers launched via `mosaic [yolo] pi` never loaded any skill because
buildPiSkillArgs emitted `--no-skills` whenever MOSAIC_PI_SKILL_MODE was
unset (the default everywhere), so maintained `~/.config/mosaic/tools/`
wrappers stayed invisible and workers improvised raw `tmux send-keys` /
`tea` / `gh`. An explicit `--skill` overrides `--no-skills` for that path,
so we now force-load a small fleet-critical set (default: `mosaic-tools`)
on every Pi launch regardless of mode — no full-catalog context bloat.

- launch.ts: add DEFAULT_PI_FORCE_SKILLS + forcedPiSkillArgs(); merge into
  every buildPiSkillArgs() return path (existsSync-guarded → no-op until the
  skill is synced). Override via MOSAIC_PI_FORCE_SKILLS (colon-separated;
  empty string disables).
- launch.spec.ts: deterministic 4th-param injection + force-load coverage.
- runtime/pi/RUNTIME.md: reconcile the "skills load natively" drift with the
  real default-off + force-load + MOSAIC_PI_SKILL_MODE behavior.
- templates/agent/**: fix stale `~/.config/mosaic/rails/` → `tools/` (60
  occurrences across 12 scaffold templates; `rails/` no longer exists).

Companion skill `mosaic-tools` ships in mosaic/agent-skills.
Follow-up (NOT auto-applied): live fleet needs `mosaic-sync-skills` +
launcher upgrade to pick up the new skill on running sessions.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QoYiBeKNh3BiYtAJS5Z587
2026-06-19 13:20:11 -05:00
13 changed files with 38 additions and 1242 deletions

View File

@@ -1,57 +0,0 @@
# Mosaic tmux Fleet PoC
This directory contains the first durable tmux-backed fleet primitives for the
Mosaic software-factory model.
The lifecycle model follows the organization-neutral AI Guide playbook
`mosaicstack/aiguide:playbooks/tmux-fleet.md` (commit `2a0b0b5`): a dedicated
holder owns the tmux server/socket; agent units join it and stop only their own
exact-match session.
## Layout
- `mosaic-tmux-holder.service` — user-mode holder that owns the named tmux server.
- `mosaic-agent@.service` — user-mode template for one reusable agent session.
- `test-fleet-units.sh` — validates unit syntax and required relationships.
The agent template calls:
```text
~/.config/mosaic/tools/fleet/start-agent-session.sh <agent-name>
```
which starts or reuses a tmux session on `MOSAIC_TMUX_SOCKET`.
## Local customization
Per-agent overrides live outside the package in:
```text
~/.config/mosaic/fleet/agents/<agent>.env
```
Example:
```dotenv
MOSAIC_TMUX_SOCKET=mosaic-factory
MOSAIC_AGENT_RUNTIME=claude
MOSAIC_AGENT_WORKDIR=/home/jarvis/src/mosaic-stack
# Optional escape hatch for PoC/canary agents:
# MOSAIC_AGENT_COMMAND=mosaic yolo claude
```
## Manual canary sequence
```bash
mkdir -p ~/.config/systemd/user ~/.config/mosaic/tools/fleet ~/.config/mosaic/fleet/agents
cp packages/mosaic/framework/systemd/user/mosaic-*.service ~/.config/systemd/user/
cp packages/mosaic/framework/tools/fleet/start-agent-session.sh ~/.config/mosaic/tools/fleet/
chmod +x ~/.config/mosaic/tools/fleet/start-agent-session.sh
systemctl --user daemon-reload
systemctl --user start mosaic-tmux-holder.service
systemctl --user start mosaic-agent@canary.service
tmux -L mosaic-factory ls
```
Do not use `tmux kill-server` without `-L mosaic-factory`; this pattern is meant
to avoid disturbing the user's default tmux server.

View File

@@ -1,20 +0,0 @@
[Unit]
Description=Mosaic tmux fleet agent %i
Documentation=https://git.mosaicstack.dev/mosaicstack/stack
Requires=mosaic-tmux-holder.service
After=mosaic-tmux-holder.service
PartOf=mosaic-tmux-holder.service
[Service]
Type=oneshot
RemainAfterExit=yes
Environment=MOSAIC_TMUX_SOCKET=mosaic-factory
Environment=MOSAIC_AGENT_NAME=%i
Environment=MOSAIC_AGENT_RUNTIME=pi
Environment=MOSAIC_AGENT_WORKDIR=%h
EnvironmentFile=-%h/.config/mosaic/fleet/agents/%i.env
ExecStart=/bin/bash %h/.config/mosaic/tools/fleet/start-agent-session.sh %i
ExecStop=-/bin/bash -lc 'tmux -L "${MOSAIC_TMUX_SOCKET:-mosaic-factory}" kill-session -t "=%i"'
[Install]
WantedBy=default.target

View File

@@ -1,15 +0,0 @@
[Unit]
Description=Mosaic tmux fleet holder
Documentation=https://git.mosaicstack.dev/mosaicstack/stack
After=default.target
[Service]
Type=oneshot
RemainAfterExit=yes
Environment=MOSAIC_TMUX_SOCKET=mosaic-factory
Environment=MOSAIC_TMUX_HOLDER=_holder
ExecStart=/bin/bash -lc 'tmux -L "$MOSAIC_TMUX_SOCKET" has-session -t "=${MOSAIC_TMUX_HOLDER}:0.0" 2>/dev/null || tmux -L "$MOSAIC_TMUX_SOCKET" new-session -d -s "$MOSAIC_TMUX_HOLDER" "while true; do sleep 3600; done"'
ExecStop=-/bin/bash -lc 'tmux -L "$MOSAIC_TMUX_SOCKET" kill-server'
[Install]
WantedBy=default.target

View File

@@ -1,30 +0,0 @@
#!/usr/bin/env bash
set -euo pipefail
SCRIPT_DIR=$(cd -- "$(dirname -- "$0")" && pwd)
HOLDER="$SCRIPT_DIR/mosaic-tmux-holder.service"
AGENT="$SCRIPT_DIR/mosaic-agent@.service"
fail() {
echo "FAIL: $*" >&2
exit 1
}
[ -f "$HOLDER" ] || fail "missing mosaic-tmux-holder.service"
[ -f "$AGENT" ] || fail "missing mosaic-agent@.service"
grep -qF 'ExecStart=' "$HOLDER" || fail "holder has no ExecStart"
grep -qF 'tmux -L' "$HOLDER" || fail "holder does not use named tmux socket"
grep -qF '_holder' "$HOLDER" || fail "holder session is not explicit"
grep -qF 'Requires=mosaic-tmux-holder.service' "$AGENT" || fail "agent does not require holder"
grep -qF 'start-agent-session.sh' "$AGENT" || fail "agent unit does not call start-agent-session.sh"
grep -qF 'kill-session -t "=%i"' "$AGENT" || fail "agent stop does not exact-match its session"
if command -v systemd-analyze >/dev/null 2>&1; then
systemd-analyze verify --user "$HOLDER" "$AGENT" >/tmp/mosaic-fleet-systemd-verify.log 2>&1 || {
cat /tmp/mosaic-fleet-systemd-verify.log >&2
fail "systemd-analyze verify failed"
}
fi
echo "ok - fleet systemd unit templates"

View File

@@ -1,30 +0,0 @@
#!/usr/bin/env bash
set -euo pipefail
AGENT_NAME=${1:-${MOSAIC_AGENT_NAME:-}}
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=${MOSAIC_AGENT_COMMAND:-}
if [ -z "$AGENT_NAME" ]; then
echo "ERROR: agent name argument or MOSAIC_AGENT_NAME is required" >&2
exit 64
fi
if ! command -v tmux >/dev/null 2>&1; then
echo "ERROR: tmux is required" >&2
exit 69
fi
if tmux -L "$MOSAIC_TMUX_SOCKET" has-session -t "=${AGENT_NAME}:0.0" 2>/dev/null; then
echo "Mosaic agent session already running: $AGENT_NAME on socket $MOSAIC_TMUX_SOCKET"
exit 0
fi
if [ -z "$MOSAIC_AGENT_COMMAND" ]; then
MOSAIC_AGENT_COMMAND="mosaic yolo $MOSAIC_AGENT_RUNTIME"
fi
mkdir -p "$MOSAIC_AGENT_WORKDIR"
exec tmux -L "$MOSAIC_TMUX_SOCKET" new-session -d -s "$AGENT_NAME" -c "$MOSAIC_AGENT_WORKDIR" "$MOSAIC_AGENT_COMMAND"

View File

@@ -1,32 +0,0 @@
#!/usr/bin/env bash
set -euo pipefail
SCRIPT_DIR=$(cd -- "$(dirname -- "$0")" && pwd)
START="$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
fail() {
echo "FAIL: $*" >&2
exit 1
}
MOSAIC_TMUX_SOCKET="$SOCKET" \
MOSAIC_AGENT_WORKDIR="$WORKDIR" \
MOSAIC_AGENT_COMMAND='bash --noprofile --norc -i' \
"$START" "$AGENT"
tmux -L "$SOCKET" has-session -t "=$AGENT:0.0" || fail "agent session was not created"
actual_dir=$(tmux -L "$SOCKET" display-message -p -t "=$AGENT:0.0" '#{pane_current_path}')
[ "$actual_dir" = "$WORKDIR" ] || fail "agent workdir mismatch: $actual_dir"
MOSAIC_TMUX_SOCKET="$SOCKET" \
MOSAIC_AGENT_WORKDIR="$WORKDIR" \
MOSAIC_AGENT_COMMAND='bash --noprofile --norc -i' \
"$START" "$AGENT" >/tmp/mosaic-start-agent-idempotent.out
grep -qF 'already running' /tmp/mosaic-start-agent-idempotent.out || fail "duplicate start was not idempotent"
echo "ok - start-agent-session"

View File

@@ -31,12 +31,9 @@ Prepends the preamble automatically (auto-detecting your own `host:session`) and
delivers reliably to local OR remote panes.
```bash
# Local target (same host, default tmux server)
# Local target (same host)
agent-send.sh -s <dst_session> -m "message"
# Local target on a Mosaic fleet socket
agent-send.sh -L mosaic-factory -s '=coder0' -m "message"
# Remote target (over ssh)
agent-send.sh -H user@host -s <dst_session> -m "message"
@@ -45,27 +42,10 @@ agent-send.sh -H user@host -s <dst_session> -f msg.txt
echo "msg" | agent-send.sh -s <dst_session>
```
Key flags: `-L` named tmux socket · `-s` dst session (required) · `-H` ssh target for remote · `-n` dst
Key flags: `-s` dst session (required) · `-H` ssh target for remote · `-n` dst
hostname for the preamble (else auto-resolved) · `-m`/`-f`/stdin body · `-S`
override source label · `-v` verbose · `-r N` Enter-flush attempts.
For durable fleet use, prefer exact tmux targets such as `=coder0`. The helper
normalizes exact session targets to pane-qualified targets internally so pane
commands do not fall back to tmux's prefix matching behavior.
## Named socket isolation
Durable Mosaic fleets should use a dedicated tmux socket, for example:
```bash
tmux -L mosaic-factory ls
agent-send.sh -L mosaic-factory -s '=coder0' -m "status?"
send-message.sh -L mosaic-factory -t '=coder0' -m "raw pane message"
```
This keeps fleet operations away from the user's default tmux server. It is the
safe rollout path on hosts that already have manual tmux sessions.
## Why a helper exists (the submission gotcha)
Pasting into an interactive REPL via raw `tmux send-keys` is unreliable: a
@@ -87,7 +67,6 @@ message crosses the wire as base64 (`-b`) to avoid all shell-quoting hazards.
- `agent-send.sh` — inter-agent wrapper (preamble + local/remote dispatch).
- `send-message.sh` — low-level reliable single-pane submitter (`-b` base64 input).
- `test-send-message-socket.sh` — smoke test for named-socket isolation.
## Distribution

View File

@@ -23,13 +23,12 @@
# the remote host; only bash + tmux + base64 (standard).
#
# USAGE
# agent-send.sh [-L socket] -s <dst_session> -m "message" # local target
# agent-send.sh [-L socket] -H user@host -s <dst_session> -m "message" # remote target
# agent-send.sh [-L socket] -H user@host -n <dst_hostname> -s <sess> -f msg.txt
# echo "msg" | agent-send.sh [-L socket] -H user@host -s <dst_session>
# agent-send.sh -s <dst_session> -m "message" # local target
# agent-send.sh -H user@host -s <dst_session> -m "message" # remote target
# agent-send.sh -H user@host -n <dst_hostname> -s <sess> -f msg.txt
# echo "msg" | agent-send.sh -H user@host -s <dst_session>
#
# OPTIONS
# -L NAME tmux socket name passed to `tmux -L NAME` on the target host
# -s DST_SESSION target tmux session (or session:window.pane) [required]
# -H SSH_TARGET ssh target (user@host) for a remote pane; omit for local
# -n DST_HOST hostname to show in the preamble for the target.
@@ -48,13 +47,12 @@ set -uo pipefail
SELF_DIR=$(cd -- "$(dirname -- "$0")" && pwd)
SENDER="$SELF_DIR/send-message.sh"
DST_SESSION=""; SSH_TARGET=""; DST_HOST=""; MSG=""; FILE=""; SOCKET_NAME=""
DST_SESSION=""; SSH_TARGET=""; DST_HOST=""; MSG=""; FILE=""
SRC_LABEL=""; RETRIES=2; VERBOSE=0
usage() { sed -n '2,44p' "$0"; exit "${1:-3}"; }
while getopts "L:s:H:n:m:f:S:r:vh" o; do
while getopts "s:H:n:m:f:S:r:vh" o; do
case "$o" in
L) SOCKET_NAME=$OPTARG ;;
s) DST_SESSION=$OPTARG ;; H) SSH_TARGET=$OPTARG ;; n) DST_HOST=$OPTARG ;;
m) MSG=$OPTARG ;; f) FILE=$OPTARG ;; S) SRC_LABEL=$OPTARG ;;
r) RETRIES=$OPTARG ;; v) VERBOSE=1 ;; h) usage 0 ;; *) usage 3 ;;
@@ -72,12 +70,8 @@ fi
# Source label: this agent's host:session (auto-detected, overridable).
if [ -z "$SRC_LABEL" ]; then
tmux_cmd=(tmux)
if [ -n "$SOCKET_NAME" ]; then
tmux_cmd+=(-L "$SOCKET_NAME")
fi
src_host=$(hostname -s 2>/dev/null || echo "?")
src_sess=$("${tmux_cmd[@]}" display-message -p '#S' 2>/dev/null || echo "?")
src_sess=$(tmux display-message -p '#S' 2>/dev/null || echo "?")
SRC_LABEL="${src_host}:${src_sess}"
fi
@@ -95,16 +89,12 @@ FULL="${PREAMBLE} ${MSG}"
B64=$(printf '%s' "$FULL" | base64 -w0)
vflag=""; [ "$VERBOSE" = 1 ] && vflag="-v"
socket_args=()
if [ -n "$SOCKET_NAME" ]; then
socket_args=(-L "$SOCKET_NAME")
fi
if [ -z "$SSH_TARGET" ]; then
# Local pane: call the canonical sender directly.
exec "$SENDER" "${socket_args[@]}" -t "$DST_SESSION" -b "$B64" -r "$RETRIES" $vflag
exec "$SENDER" -t "$DST_SESSION" -b "$B64" -r "$RETRIES" $vflag
else
# Remote pane: ship the sender over ssh and run it local to the target.
ssh -o ConnectTimeout=10 "$SSH_TARGET" \
"bash -s -- ${socket_args[*]@Q} -t '$DST_SESSION' -b '$B64' -r '$RETRIES' $vflag" < "$SENDER"
"bash -s -- -t '$DST_SESSION' -b '$B64' -r '$RETRIES' $vflag" < "$SENDER"
fi

View File

@@ -13,13 +13,12 @@
# no-op in Claude Code, so the double-Enter is safe.
#
# USAGE
# send-message.sh [-L socket_name] -t <target> -m "message"
# send-message.sh [-L socket_name] -t <target> -f <file>
# echo "message" | send-message.sh [-L socket_name] -t <target>
# ssh host bash -s -- -L socket -t <target> -b "$(base64 -w0 <<<msg)" < send-message.sh
# send-message.sh -t <target> -m "message"
# send-message.sh -t <target> -f <file>
# echo "message" | send-message.sh -t <target>
# ssh host bash -s -- -t <target> -b "$(base64 -w0 <<<msg)" < send-message.sh
#
# OPTIONS
# -L NAME tmux socket name passed to `tmux -L NAME` (optional)
# -t TARGET tmux target: session, or session:window.pane [required]
# -m MESSAGE message text (single- or multi-line)
# -f FILE read message from FILE instead of -m
@@ -35,12 +34,11 @@
# 3 usage error
set -uo pipefail
SOCKET_NAME=""; TARGET=""; MSG=""; FILE=""; B64=""; RETRIES=2; VERBOSE=0
TARGET=""; MSG=""; FILE=""; B64=""; RETRIES=2; VERBOSE=0
usage() { sed -n '2,34p' "$0"; exit "${1:-3}"; }
while getopts "L:t:m:f:b:r:vh" o; do
while getopts "t:m:f:b:r:vh" o; do
case "$o" in
L) SOCKET_NAME=$OPTARG ;;
t) TARGET=$OPTARG ;; m) MSG=$OPTARG ;; f) FILE=$OPTARG ;; b) B64=$OPTARG ;;
r) RETRIES=$OPTARG ;; v) VERBOSE=1 ;; h) usage 0 ;; *) usage 3 ;;
esac
@@ -53,21 +51,8 @@ elif [ -z "$MSG" ] && [ ! -t 0 ]; then MSG=$(cat)
fi
[ -n "$MSG" ] || { echo "ERROR: empty message (use -m, -f, or stdin)" >&2; exit 3; }
tmux_cmd=(tmux)
if [ -n "$SOCKET_NAME" ]; then
tmux_cmd+=(-L "$SOCKET_NAME")
fi
# tmux accepts `=session` for some commands, but pane-level commands such as
# capture-pane require a pane-qualified target. Keep exact-session addressing
# convenient while avoiding accidental prefix matches.
EFFECTIVE_TARGET=$TARGET
if [[ "$TARGET" == =* && "$TARGET" != *:* ]]; then
EFFECTIVE_TARGET="${TARGET}:0.0"
fi
# Target must resolve to a live pane.
if ! "${tmux_cmd[@]}" list-panes -t "$EFFECTIVE_TARGET" >/dev/null 2>&1; then
if ! tmux list-panes -t "$TARGET" >/dev/null 2>&1; then
echo "ERROR: tmux target not found: $TARGET" >&2; exit 1
fi
@@ -77,18 +62,18 @@ snippet=$(printf '%s' "$MSG" | tr '\n' ' ' | tr -s ' ' | sed 's/[^[:print:]]//g'
# 1) Paste the body as a bracketed paste so multi-line content does not submit
# line-by-line. load-buffer/paste-buffer is far safer than `send-keys -l`.
printf '%s' "$MSG" | "${tmux_cmd[@]}" load-buffer -b __mosaic_send -
printf '%s' "$MSG" | tmux load-buffer -b __mosaic_send -
# -p = bracketed paste when the client supports it; fall back if not.
"${tmux_cmd[@]}" paste-buffer -d -p -b __mosaic_send -t "$EFFECTIVE_TARGET" 2>/dev/null \
|| "${tmux_cmd[@]}" paste-buffer -d -b __mosaic_send -t "$EFFECTIVE_TARGET"
tmux paste-buffer -d -p -b __mosaic_send -t "$TARGET" 2>/dev/null \
|| tmux paste-buffer -d -b __mosaic_send -t "$TARGET"
sleep 0.5
# 2) Submit, then verify; flush with another Enter if it is still a draft.
status="sent"
for attempt in $(seq 1 $((RETRIES + 1))); do
"${tmux_cmd[@]}" send-keys -t "$EFFECTIVE_TARGET" Enter
tmux send-keys -t "$TARGET" Enter
sleep 1.2
pane=$("${tmux_cmd[@]}" capture-pane -t "$EFFECTIVE_TARGET" -p 2>/dev/null)
pane=$(tmux capture-pane -t "$TARGET" -p 2>/dev/null)
if printf '%s' "$pane" | grep -qF "$QUEUED_RE"; then
status="queued"; break

View File

@@ -1,50 +0,0 @@
#!/usr/bin/env bash
set -euo pipefail
SCRIPT_DIR=$(cd -- "$(dirname -- "$0")" && pwd)
SEND_MESSAGE="$SCRIPT_DIR/send-message.sh"
AGENT_SEND="$SCRIPT_DIR/agent-send.sh"
SOCKET="mosaic-test-$RANDOM-$$"
TARGET="target-$RANDOM"
DEFAULT_TARGET="default-target-$RANDOM"
TMPDIR=$(mktemp -d)
trap 'tmux -L "$SOCKET" kill-server >/dev/null 2>&1 || true; tmux kill-session -t "$DEFAULT_TARGET" >/dev/null 2>&1 || true; rm -rf "$TMPDIR"' EXIT
fail() {
echo "FAIL: $*" >&2
exit 1
}
require_tmux() {
command -v tmux >/dev/null 2>&1 || fail "tmux is required"
}
capture_named() {
tmux -L "$SOCKET" capture-pane -t "=$TARGET:0.0" -p
}
capture_default() {
tmux capture-pane -t "=$DEFAULT_TARGET:0.0" -p
}
require_tmux
tmux -L "$SOCKET" new-session -d -s "$TARGET" -c "$TMPDIR" 'bash --noprofile --norc -i'
tmux new-session -d -s "$DEFAULT_TARGET" -c "$TMPDIR" 'bash --noprofile --norc -i'
"$SEND_MESSAGE" -L "$SOCKET" -t "=$TARGET" -m "named socket hello" >/tmp/send-message-named.out
sleep 0.2
capture_named | grep -qF "named socket hello" || fail "send-message.sh did not deliver to named socket"
if capture_default | grep -qF "named socket hello"; then
fail "send-message.sh leaked named-socket message to default tmux server"
fi
"$AGENT_SEND" -L "$SOCKET" -S "tester:source" -s "=$TARGET" -m "agent socket hello" >/tmp/agent-send-named.out
sleep 0.2
capture_named | grep -qF "[tester:source ->" || fail "agent-send.sh did not include preamble"
capture_named | grep -qF "agent socket hello" || fail "agent-send.sh did not deliver to named socket"
if capture_default | grep -qF "agent socket hello"; then
fail "agent-send.sh leaked named-socket message to default tmux server"
fi
echo "ok - named tmux socket send tools"

View File

@@ -1,11 +1,7 @@
import { describe, it, expect, vi, beforeEach, afterEach, type MockInstance } from 'vitest';
import { Command } from 'commander';
import { mkdtempSync, mkdirSync, writeFileSync, symlinkSync, rmSync } from 'node:fs';
import { tmpdir } from 'node:os';
import { join } from 'node:path';
import {
buildPiSkillArgs,
enumerateSkillDirs,
piForceSkillNames,
registerRuntimeLaunchers,
type RuntimeLaunchHandler,
@@ -120,101 +116,11 @@ describe('buildPiSkillArgs', () => {
]);
});
it('force-loads fleet skills under native Pi discovery when not already discoverable', () => {
// Empty native set => Pi would not find mosaic-tools on its own, so force it.
it('force-loads fleet skills even under native Pi discovery', () => {
expect(
buildPiSkillArgs([], { MOSAIC_PI_SKILL_MODE: 'discover' }, fakeSkills, fakeForced, new Set()),
buildPiSkillArgs([], { MOSAIC_PI_SKILL_MODE: 'discover' }, fakeSkills, fakeForced),
).toEqual(['--skill', '/skills/mosaic-tools']);
});
it('discover mode drops a forced skill Pi already discovers natively (no double-load)', () => {
// mosaic-tools is reachable from a Pi native root, so native discovery
// covers it — forcing it again would register the same skill twice.
expect(
buildPiSkillArgs(
[],
{ MOSAIC_PI_SKILL_MODE: 'discover' },
fakeSkills,
fakeForced,
new Set(['/skills/mosaic-tools']),
),
).toEqual([]);
});
it('discover mode keeps a forced skill that no native root provides', () => {
expect(
buildPiSkillArgs(
[],
{ MOSAIC_PI_SKILL_MODE: 'discover' },
fakeSkills,
fakeForced,
new Set(['/skills/some-other-skill']),
),
).toEqual(['--skill', '/skills/mosaic-tools']);
});
it('discover mode collapses a forced skill listed twice to a single --skill', () => {
// Mirror 'all' mode: intra-forced-set duplicates (same realpath) dedup.
expect(
buildPiSkillArgs(
[],
{ MOSAIC_PI_SKILL_MODE: 'discover' },
fakeSkills,
['--skill', '/skills/mosaic-tools', '--skill', '/skills/mosaic-tools'],
new Set(),
),
).toEqual(['--skill', '/skills/mosaic-tools']);
});
});
describe('enumerateSkillDirs (real FS)', () => {
let root: string;
beforeEach(() => {
root = mkdtempSync(join(tmpdir(), 'mosaic-skills-'));
});
afterEach(() => {
rmSync(root, { recursive: true, force: true });
});
function makeSkill(parent: string, name: string): string {
const dir = join(parent, name);
mkdirSync(dir, { recursive: true });
writeFileSync(join(dir, 'SKILL.md'), `# ${name}\n`);
return dir;
}
it('accepts a symlinked skill dir (regression: synced fleet skills are symlinks)', () => {
// Real skill lives under `canonical/`; the scanned root only has a symlink to it.
const canonical = makeSkill(join(root, 'canonical'), 'mosaic-tools');
const scanned = join(root, 'scanned');
mkdirSync(scanned, { recursive: true });
symlinkSync(canonical, join(scanned, 'mosaic-tools'), 'dir');
expect(enumerateSkillDirs([scanned])).toEqual(['--skill', join(scanned, 'mosaic-tools')]);
});
it('dedups by real path when the same skill is reachable from two roots', () => {
// Root A holds the real dir; root B symlinks to it — one --skill, not two.
const rootA = join(root, 'a');
const rootB = join(root, 'b');
const real = makeSkill(rootA, 'mosaic-tools');
mkdirSync(rootB, { recursive: true });
symlinkSync(real, join(rootB, 'mosaic-tools'), 'dir');
expect(enumerateSkillDirs([rootA, rootB])).toEqual(['--skill', real]);
});
it('skips directories without a SKILL.md and missing roots', () => {
mkdirSync(join(root, 'present', 'not-a-skill'), { recursive: true });
makeSkill(join(root, 'present'), 'real-skill');
expect(enumerateSkillDirs([join(root, 'present'), join(root, 'does-not-exist')])).toEqual([
'--skill',
join(root, 'present', 'real-skill'),
]);
});
});
describe('piForceSkillNames', () => {

View File

@@ -6,15 +6,7 @@
*/
import { execFileSync, execSync, spawnSync } from 'node:child_process';
import {
existsSync,
mkdirSync,
readFileSync,
writeFileSync,
readdirSync,
realpathSync,
rmSync,
} from 'node:fs';
import { existsSync, mkdirSync, readFileSync, writeFileSync, readdirSync, rmSync } from 'node:fs';
import { createRequire } from 'node:module';
import { homedir } from 'node:os';
import { join, dirname } from 'node:path';
@@ -436,74 +428,25 @@ function ensureRuntimeConfig(runtime: RuntimeName, destPath: string): void {
// ─── Pi skill/extension discovery ────────────────────────────────────────────
/** Resolve a skill dir to its canonical real path so symlinked duplicates
* (e.g. ~/.pi/agent/skills/X -> ~/.config/mosaic/skills/X) collapse to one key.
* Falls back to the literal path if it can't be resolved (e.g. broken link). */
function skillRealPath(dir: string): string {
try {
return realpathSync(dir);
} catch {
return dir;
}
}
/** Skill roots Pi auto-discovers natively (no `--skill` needed): its global
* skills dir and the project-local one relative to the launch cwd. */
function piNativeSkillRoots(cwd: string = process.cwd()): string[] {
return [join(homedir(), '.pi', 'agent', 'skills'), join(cwd, '.pi', 'skills')];
}
/** Enumerate skill dirs under a set of roots, deduped by real path. A directory
* counts as a skill when it (or its symlink target) contains a SKILL.md.
* Exported for tests (real-FS coverage of symlink acceptance + realpath dedup). */
export function enumerateSkillDirs(roots: string[]): string[] {
const seen = new Set<string>();
function discoverPiSkills(): string[] {
const args: string[] = [];
for (const skillsRoot of roots) {
for (const skillsRoot of [join(MOSAIC_HOME, 'skills'), join(MOSAIC_HOME, 'skills-local')]) {
if (!existsSync(skillsRoot)) continue;
try {
for (const entry of readdirSync(skillsRoot, { withFileTypes: true })) {
// Synced fleet skills land as symlinks, so accept both dirs and links.
if (!entry.isDirectory() && !entry.isSymbolicLink()) continue;
if (!entry.isDirectory()) continue;
const skillDir = join(skillsRoot, entry.name);
if (!existsSync(join(skillDir, 'SKILL.md'))) continue;
const key = skillRealPath(skillDir);
if (seen.has(key)) continue;
seen.add(key);
if (existsSync(join(skillDir, 'SKILL.md'))) {
args.push('--skill', skillDir);
}
}
} catch {
// skip unreadable roots
// skip
}
}
return args;
}
/** Every skill dir Pi would link under `MOSAIC_PI_SKILL_MODE=all`: the Mosaic
* global/local catalog plus Pi's own native roots. `--no-skills` suppresses
* native auto-discovery, so 'all' must re-add the native roots explicitly or
* they would be silently dropped. Deduped by real path. */
function discoverPiSkills(cwd: string = process.cwd()): string[] {
return enumerateSkillDirs([
join(MOSAIC_HOME, 'skills'),
join(MOSAIC_HOME, 'skills-local'),
...piNativeSkillRoots(cwd),
]);
}
/** Real paths of skills Pi will auto-discover from its native roots. Used to
* drop redundant force-loads in 'discover' mode (which keeps native discovery
* on) so the same skill is not registered twice. */
function piNativeSkillRealPaths(cwd: string = process.cwd()): Set<string> {
const args = enumerateSkillDirs(piNativeSkillRoots(cwd));
const set = new Set<string>();
for (let i = 1; i < args.length; i += 2) {
const dir = args[i];
if (dir !== undefined) set.add(skillRealPath(dir));
}
return set;
}
type PiSkillMode = 'none' | 'all' | 'discover';
function normalizePiSkillMode(env: NodeJS.ProcessEnv): PiSkillMode {
@@ -549,19 +492,15 @@ function forcedPiSkillArgs(env: NodeJS.ProcessEnv = process.env): string[] {
return args;
}
/** Concatenate `--skill <dir>` arg groups, dropping any skill already seen.
* Dedup is by real path, so a forced skill and the same skill reached via a
* different (e.g. symlinked) directory collapse to a single `--skill`. */
/** Concatenate `--skill <dir>` arg groups, dropping any directory already seen. */
function mergeSkillArgs(...groups: string[][]): string[] {
const seen = new Set<string>();
const out: string[] = [];
for (const group of groups) {
for (let i = 0; i < group.length; i += 2) {
const dir = group[i + 1];
if (group[i] !== '--skill' || dir === undefined) continue;
const key = skillRealPath(dir);
if (seen.has(key)) continue;
seen.add(key);
if (group[i] !== '--skill' || dir === undefined || seen.has(dir)) continue;
seen.add(dir);
out.push('--skill', dir);
}
}
@@ -573,31 +512,17 @@ export function buildPiSkillArgs(
env: NodeJS.ProcessEnv = process.env,
discoveredSkillArgs: string[] = discoverPiSkills(),
forcedSkillArgs: string[] = forcedPiSkillArgs(env),
nativeSkillRealPaths: Set<string> = piNativeSkillRealPaths(),
): string[] {
const mode = normalizePiSkillMode(env);
if (mode === 'discover') {
// Native Pi discovery stays on, so only force-load fleet skills it will NOT
// already find under its native roots — otherwise the same skill is
// registered twice (once natively, once via --skill). mergeSkillArgs first
// collapses any intra-forced-set realpath duplicates, mirroring 'all' mode.
const deduped = mergeSkillArgs(forcedSkillArgs);
const out: string[] = [];
for (let i = 0; i < deduped.length; i += 2) {
const dir = deduped[i + 1];
if (deduped[i] !== '--skill' || dir === undefined) continue;
if (nativeSkillRealPaths.has(skillRealPath(dir))) continue;
out.push('--skill', dir);
}
return out;
// Native Pi discovery handles the rest; still force-load the fleet skills.
return [...forcedSkillArgs];
}
if (mode === 'all') {
// 'all' links the full catalog; merge in the forced set so fleet-critical
// skills are guaranteed present even if they live only under skills-local/.
// discoverPiSkills already covers Pi's native roots, which `--no-skills`
// would otherwise suppress.
return ['--no-skills', ...mergeSkillArgs(discoveredSkillArgs, forcedSkillArgs)];
}

View File

@@ -1,755 +0,0 @@
# Durable tmux Fleet Installation Plan
> **For Mosaic/Hermes:** This is an implementation plan for making the tmux-backed Mosaic software-factory fleet durable on this server and reusable in generic Mosaic Stack installs. Keep local USC/Mosaic defaults in profiles; keep framework behavior customizable.
**Goal:** Add a supported Mosaic tmux-fleet installation path: holder-owned tmux server, per-agent reusable sessions, reliable send/reset/status tools, local roster customization, and a documented cutover for this server.
**Architecture:** Mosaic should ship generic tmux fleet primitives in the framework, then layer local rosters through configuration. The holder service owns the tmux socket; each agent service joins the holder-owned server and runs `mosaic yolo <runtime>`. The orchestrator addresses agents through `mosaic agent ...` abstractions so tmux can later be replaced by Matrix-backed agent comms without changing mission flow.
**Reference:** AI Guide `playbooks/tmux-fleet.md` at commit `2a0b0b5` documents the organization-neutral holder-service pattern, exact-match `=<name>` stop targets, and coupled-server cutover/verification sequence. The Stack implementation should treat that as the lifecycle model and keep concrete Mosaic unit/tooling details here.
**Tech Stack:** Bash, tmux, user systemd units, Mosaic CLI/framework installer, JSON/YAML roster config, existing `packages/mosaic/framework/tools/tmux/{agent-send.sh,send-message.sh}`.
---
## Current evidence from this server
Checked 2026-06-19:
- Host: `W-jarvis`
- User: `jarvis`
- tmux: `/usr/bin/tmux`, version `3.4`
- user systemd: active
- existing tmux sessions: `ai-bma-0`, `dyor-1`, `melaniewoltje-3`, `sage-2`
- existing Mosaic runtime: `/home/jarvis/.npm-global/bin/mosaic`, version `0.0.31`
- installed `~/.config/mosaic/tools/tmux` was not present even though the stack repo contains `packages/mosaic/framework/tools/tmux/`
Implication: do not kill the current tmux server casually. This server has active ad-hoc/service sessions. The durable fleet cutover must be planned, with either a separate socket first or a scheduled fleet recycle.
## Design decisions
### 1. Generic framework, local profile
The Mosaic framework should ship:
- systemd unit templates;
- tmux fleet CLI wrappers;
- roster schema and examples;
- install/enable/status/reset commands;
- docs and verification scripts.
Local environments should provide:
- agent names;
- runtime per slot (`claude`, `pi`, `codex`, etc.);
- default role class;
- launch directory;
- optional kickstart prompt;
- model/provider hints;
- transport selection (`tmux` now, `matrix` later).
Do not bake the USC roster into generic install code. Ship it as an example profile.
### 2. Durable sessions, disposable task context
Session names are durable operational addresses. Task persona is disposable. Reusable worker slots should be reset with `/clear` or `/new` and then receive a fresh task kickstart.
Persistent/semi-persistent personas:
- lead orchestrator;
- final/adversarial reviewer;
- architecture/enhancement lane.
Disposable slots:
- implementers;
- ordinary reviewers;
- security reviewers unless actively holding a security mission.
### 3. Transport abstraction now
Add commands around tmux instead of calling tmux directly from orchestration:
```bash
mosaic agent send <agent> --message "..."
mosaic agent status [--json]
mosaic agent reset <agent> [--clear|--new]
mosaic agent roster [--json]
mosaic fleet install|start|stop|restart|status|verify
```
Today these call tmux/systemd. Later the same command surface can target Matrix or per-agent gateways.
### 4. Avoid shared-server ownership bug
Use the AI Guide holder pattern:
```text
mosaic-tmux-holder.service owns the tmux server/socket
mosaic-agent@<name>.service joins the existing holder-owned socket
ExecStop kills only session =<name>
```
Use exact tmux targets: `=<session>`.
### 5. Prefer separate named socket for Mosaic factory
To avoid disturbing existing tmux work, the default fleet should use a named socket such as:
```text
$XDG_RUNTIME_DIR/mosaic-factory.tmux
```
or tmux socket name:
```bash
tmux -L mosaic-factory ...
```
This avoids collision with ordinary `tmux ls` sessions. The send tools need socket support.
---
## Target USC-style roster example
Ship as example only, not default:
```yaml
version: 1
transport: tmux
tmux:
socket_name: mosaic-factory
holder_session: _holder
working_directory: ~/src
agents:
- name: mos-claude
runtime: claude
class: orchestrator
model_hint: Claude Opus
persistent_persona: true
- name: coder0
runtime: claude
class: implementer
model_hint: Claude Opus
reset_between_tasks: true
- name: coder1
runtime: claude
class: implementer
model_hint: Claude Opus
reset_between_tasks: true
- name: coder2
runtime: pi
class: implementer
model_hint: Pi GPT-5.5
reset_between_tasks: true
- name: coder3
runtime: pi
class: implementer
model_hint: Pi GPT-5.5
reset_between_tasks: true
- name: coder4
runtime: claude
class: implementer
model_hint: Claude Opus
reset_between_tasks: true
- name: coder5
runtime: claude
class: implementer
model_hint: Claude Opus
reset_between_tasks: true
- name: enhance
runtime: claude
class: enhancer
model_hint: Claude Opus
persistent_persona: semi
- name: rev0
runtime: pi
class: reviewer
model_hint: Pi GPT-5.5
reset_between_tasks: true
- name: rev1
runtime: pi
class: reviewer
model_hint: Pi GPT-5.5
reset_between_tasks: true
- name: secrev0
runtime: pi
class: security_reviewer
model_hint: Pi GPT-5.5
reset_between_tasks: true
- name: secrev1
runtime: pi
class: security_reviewer
model_hint: Pi GPT-5.5
reset_between_tasks: true
- name: ultron
runtime: pi
class: final_reviewer
model_hint: Pi GPT-5.5
persistent_persona: semi
```
---
## Phase 0 — Confirm install surfaces
### Task 0.1: Inspect installer copy behavior
**Objective:** Confirm how framework files under `packages/mosaic/framework/` become installed under `~/.config/mosaic/`.
**Files:**
- Read: `tools/install.sh`
- Read: `packages/mosaic/framework/install.sh`
- Read: `packages/mosaic/src/runtime/install-manifest.ts`
**Steps:**
1. Verify `packages/mosaic/framework/install.sh` rsyncs `tools/tmux`.
2. Verify whether npm-packaged installs include `framework/tools/tmux`.
3. Confirm whether installed hosts should run `mosaic update`, `bash tools/install.sh`, or `packages/mosaic/framework/install.sh` to receive new tmux tools.
4. Record exact propagation command in docs.
**Verification:**
```bash
bash packages/mosaic/framework/install.sh --help || true
npm pack --dry-run --json | jq '.[0].files[].path' | grep 'framework/tools/tmux'
```
Expected: tmux tools are included in installable package or packaging fix is identified.
### Task 0.2: Inspect current yolo launch semantics
**Objective:** Confirm `mosaic yolo claude` and `mosaic yolo pi` accept optional initial prompt text and behave well under systemd/tmux.
**Files:**
- Read: `packages/mosaic/src/**`
- Read: `packages/mosaic/framework/runtime/claude/RUNTIME.md`
- Read: `packages/mosaic/framework/runtime/pi/RUNTIME.md`
**Verification commands:**
```bash
mosaic yolo claude --help
mosaic yolo pi --help
```
Expected: a systemd `ExecStart` can launch the runtime either with no prompt or with a kickstart prompt file/string.
---
## Phase 1 — Framework tmux primitives
### Task 1.1: Add socket support to send tools
**Objective:** Allow `agent-send.sh` and `send-message.sh` to target a named Mosaic tmux socket without affecting default tmux sessions.
**Files:**
- Modify: `packages/mosaic/framework/tools/tmux/send-message.sh`
- Modify: `packages/mosaic/framework/tools/tmux/agent-send.sh`
- Modify: `packages/mosaic/framework/tools/tmux/README.md`
- Test: `packages/mosaic/framework/tools/tmux/test-send-message.sh` (new)
**Design:**
Add optional flags:
```bash
-L SOCKET_NAME # tmux -L socket name
-SOCKET PATH # optional later if needed; avoid conflict with existing -S source label in agent-send
```
Because `agent-send.sh` already uses `-S` for source label, prefer `-L` for socket name and `-T` or `--socket-path` only if long-option parsing is added.
**Implementation notes:**
- Build a tmux command array:
```bash
tmux_cmd=(tmux)
if [ -n "$SOCKET_NAME" ]; then tmux_cmd+=( -L "$SOCKET_NAME" ); fi
```
- Replace raw `tmux ...` calls with `"${tmux_cmd[@]}" ...`.
- Pass `-L` through remote ssh invocation.
- Include socket name in verbose output.
**Verification:**
```bash
tmux -L mosaic-test new-session -d -s target 'cat'
packages/mosaic/framework/tools/tmux/send-message.sh -L mosaic-test -t target -m 'hello'
tmux -L mosaic-test capture-pane -t target -p | grep hello
tmux -L mosaic-test kill-server
```
Expected: message lands in the named socket session; default `tmux ls` is untouched.
### Task 1.2: Add exact target validation helper
**Objective:** Prevent accidental prefix targeting in all tmux fleet operations.
**Files:**
- Create: `packages/mosaic/framework/tools/tmux/_lib.sh`
- Modify: `send-message.sh`
- Modify: `agent-send.sh`
**Behavior:**
- For session-only agent names, normalize target to `=<name>` before kill/status/reset operations.
- For explicit pane targets like `session:window.pane`, allow as advanced path but document the risk.
**Verification:**
Create sessions `agent` and `agent0`; verify killing/resetting `agent` does not affect `agent0`.
---
## Phase 2 — systemd unit templates
### Task 2.1: Add holder service template
**Objective:** Ship a user systemd unit template that owns the Mosaic factory tmux server.
**Files:**
- Create: `packages/mosaic/framework/systemd/user/mosaic-tmux-holder.service`
- Create: `packages/mosaic/framework/tools/fleet/install-user-units.sh`
**Unit shape:**
```ini
[Unit]
Description=Mosaic tmux fleet holder
Documentation=https://git.mosaicstack.dev/mosaicstack/aiguide
[Service]
Type=oneshot
RemainAfterExit=yes
Environment=MOSAIC_TMUX_SOCKET=mosaic-factory
ExecStart=/usr/bin/tmux -L ${MOSAIC_TMUX_SOCKET} new-session -d -s _holder 'while true; do sleep 3600; done'
ExecStop=-/usr/bin/tmux -L ${MOSAIC_TMUX_SOCKET} kill-server
[Install]
WantedBy=default.target
```
**Important:** systemd environment expansion in `ExecStart` is limited. Verify syntax; if `%E`/environment expansion is awkward, generate concrete units from config instead of relying on dynamic expansion.
**Verification:**
```bash
systemd-analyze --user verify ~/.config/systemd/user/mosaic-tmux-holder.service
systemctl --user daemon-reload
systemctl --user start mosaic-tmux-holder.service
tmux -L mosaic-factory ls | grep _holder
```
### Task 2.2: Add agent service template
**Objective:** Ship a user systemd template that starts one configured agent slot.
**Files:**
- Create: `packages/mosaic/framework/systemd/user/mosaic-agent@.service`
- Modify: `packages/mosaic/framework/tools/fleet/install-user-units.sh`
**Unit shape:**
```ini
[Unit]
Description=Mosaic agent session %i
Requires=mosaic-tmux-holder.service
After=mosaic-tmux-holder.service
PartOf=mosaic-tmux-holder.service
[Service]
Type=oneshot
RemainAfterExit=yes
WorkingDirectory=%h/src
Environment=MOSAIC_TMUX_SOCKET=mosaic-factory
ExecStart=/bin/bash -lc 'tmux -L "$MOSAIC_TMUX_SOCKET" new-session -d -s "%i" "mosaic yolo $(mosaic fleet runtime %i)"'
ExecStop=-/usr/bin/tmux -L mosaic-factory kill-session -t '=%i'
[Install]
WantedBy=default.target
```
**Design warning:** command substitution in unit files can become brittle. Prefer a generated per-agent EnvironmentFile:
```text
~/.config/mosaic/fleet/agents/coder0.env
```
with:
```bash
MOSAIC_AGENT_NAME=coder0
MOSAIC_AGENT_RUNTIME=claude
MOSAIC_AGENT_WORKDIR=/home/jarvis/src
MOSAIC_TMUX_SOCKET=mosaic-factory
```
Then `ExecStart` calls a wrapper:
```bash
~/.config/mosaic/tools/fleet/start-agent-session.sh
```
**Verification:**
```bash
systemd-analyze --user verify ~/.config/systemd/user/mosaic-agent@.service
systemctl --user start mosaic-agent@coder0.service
tmux -L mosaic-factory has-session -t '=coder0'
systemctl --user restart mosaic-agent@coder0.service
```
Expected: holder server PID remains unchanged; only `coder0` session recycles.
### Task 2.3: Add start-agent wrapper
**Objective:** Keep systemd units simple by moving config lookup and launch command construction into a script.
**Files:**
- Create: `packages/mosaic/framework/tools/fleet/start-agent-session.sh`
**Behavior:**
Inputs:
```bash
start-agent-session.sh <agent-name>
```
Reads:
```text
$MOSAIC_HOME/fleet/agents/<agent-name>.env
```
Starts:
```bash
tmux -L "$MOSAIC_TMUX_SOCKET" new-session -d -s "$MOSAIC_AGENT_NAME" -c "$MOSAIC_AGENT_WORKDIR" "mosaic yolo $MOSAIC_AGENT_RUNTIME"
```
Guardrails:
- fail if runtime is empty;
- fail if workdir does not exist;
- no duplicate sessions unless `--replace` is passed;
- exact session names only.
---
## Phase 3 — roster config and CLI wrappers
### Task 3.1: Add fleet config schema and examples
**Objective:** Define customizable install-time roster without hardcoding USC.
**Files:**
- Create: `packages/mosaic/framework/fleet/roster.schema.json`
- Create: `packages/mosaic/framework/fleet/examples/minimal.yaml`
- Create: `packages/mosaic/framework/fleet/examples/usc-software-factory.yaml`
- Create: `packages/mosaic/framework/fleet/README.md`
**Schema concepts:**
- `transport`: `tmux` now; `matrix` later.
- `tmux.socket_name`
- `tmux.holder_session`
- `defaults.working_directory`
- `agents[].name`
- `agents[].runtime`
- `agents[].class`
- `agents[].model_hint`
- `agents[].persistent_persona`
- `agents[].reset_between_tasks`
- `agents[].kickstart_template`
**Verification:**
Use `jq` for JSON examples or add a small Python/YAML validator if YAML is chosen. If no YAML parser is guaranteed, store examples as JSON or support both with Python stdlib JSON first.
### Task 3.2: Add `mosaic fleet` commands
**Objective:** Provide operator-safe commands for install/status/start/stop/restart/verify.
**Files:**
- Modify: `packages/mosaic/src/cli.ts` or the current commander entrypoint.
- Create scripts under: `packages/mosaic/framework/tools/fleet/`
**Commands:**
```bash
mosaic fleet init --profile minimal|usc --write
mosaic fleet install-systemd
mosaic fleet start [agent]
mosaic fleet stop [agent]
mosaic fleet restart [agent]
mosaic fleet status --json
mosaic fleet verify
```
**Implementation path:**
Start by wrapping framework shell scripts from the TypeScript CLI. Do not overbuild a TypeScript service manager in the first pass.
### Task 3.3: Add `mosaic agent` commands
**Objective:** Provide transport-stable per-agent operations.
**Files:**
- Modify: Mosaic CLI entrypoint.
- Create: `packages/mosaic/framework/tools/agent/` or reuse `tools/tmux` + `tools/fleet`.
**Commands:**
```bash
mosaic agent roster [--json]
mosaic agent status [agent] [--json]
mosaic agent send <agent> --message "..."
mosaic agent reset <agent> --clear|--new
mosaic agent tail <agent> [-n 80]
```
**Reset behavior:**
For tmux transport, `reset --clear` sends `/clear` then Enter through `send-message.sh`.
For Claude/Pi differences, keep reset command configurable per runtime:
```yaml
runtimes:
claude:
reset_command: /clear
pi:
reset_command: /new
```
If a runtime does not support a known reset command, restart the service and send a fresh kickstart.
---
## Phase 4 — this-server rollout strategy
### Task 4.1: Install on separate socket first
**Objective:** Prove the holder pattern without disturbing existing sessions.
**Commands after implementation lands locally:**
```bash
mosaic fleet init --profile minimal --write
mosaic fleet install-systemd
systemctl --user daemon-reload
systemctl --user start mosaic-tmux-holder.service
mosaic fleet verify
```
Expected:
- `tmux -L mosaic-factory ls` shows `_holder`.
- normal `tmux ls` still shows existing sessions unchanged.
### Task 4.2: Start one canary agent
**Objective:** Validate single-agent start/restart isolation.
Use a harmless canary first, not the full fleet.
Example roster addition:
```yaml
- name: canary-pi
runtime: pi
class: canary
working_directory: /home/jarvis/src
```
Commands:
```bash
systemctl --user start mosaic-agent@canary-pi.service
SRV=$(tmux -L mosaic-factory display-message -p '#{pid}')
systemctl --user restart mosaic-agent@canary-pi.service
test "$SRV" = "$(tmux -L mosaic-factory display-message -p '#{pid}')"
tmux -L mosaic-factory ls
```
Expected: holder PID unchanged; `_holder` remains; `canary-pi` recreated.
### Task 4.3: Configure local Mosaic factory roster
**Objective:** Create the actual local roster for this server after canary passes.
Do not assume USC exact roster is desired here. Create a local profile such as:
```text
~/.config/mosaic/fleet/roster.yaml
```
Initial local recommendation:
- `mos-claude` orchestrator
- `coder0` / `coder1` implementers
- `rev0` reviewer
- `secrev0` security reviewer
- `ultron` final/adversarial reviewer
Scale to full USC-style pool only after resource/budget behavior is understood.
### Task 4.4: Cut over existing ad-hoc tmux sessions only if desired
**Objective:** Avoid data loss.
Existing sessions on this server are not on the proposed `mosaic-factory` socket. They can remain untouched. If we later want them under Mosaic fleet control:
1. list sessions;
2. capture logs/handoffs;
3. stop old processes intentionally;
4. recreate as configured `mosaic-agent@...` services;
5. verify comms and state.
Do not run `tmux kill-server` on the default socket unless Jason explicitly approves that outage.
---
## Phase 5 — docs and AI Guide backfill
### Task 5.1: Stack docs
**Objective:** Document install and customization for Mosaic Stack users.
**Files:**
- Create: `docs/fleet/tmux-fleet.md` or `packages/mosaic/framework/tools/fleet/README.md`
- Modify: top-level `README.md` if appropriate.
Must cover:
- what problem holder service solves;
- install commands;
- customization file;
- example rosters;
- reset/reuse lifecycle;
- exact-target safety;
- separate socket default;
- Matrix migration path.
### Task 5.2: AI Guide docs
**Objective:** Keep generic guidance in AI Guide and implementation details in Stack.
**Files in `mosaicstack/aiguide`:**
- Update: `playbooks/tmux-fleet.md` with named socket, roster/profile, and resettable-slot pattern.
- Add or update: `reference/agent-role-matrix.md` if PR #5 lands.
Do not put Mosaic install commands as the only path in AI Guide. Present them as one implementation profile.
---
## Phase 6 — Matrix migration seam
### Task 6.1: Add transport enum but implement tmux only
**Objective:** Avoid hardcoding tmux into orchestration semantics.
Roster:
```yaml
transport: tmux
```
Future:
```yaml
transport: matrix
matrix:
homeserver: https://matrix.example
room_prefix: mosaic-factory
```
### Task 6.2: Define transport interface docs
**Objective:** Make Matrix plugin work a transport swap, not a rewrite.
Minimum operations:
```text
send(agent, message)
reset(agent, mode)
status(agent)
tail(agent)
listAgents()
```
Any tmux-specific concept must stay below this line.
---
## Acceptance criteria
The implementation is complete when:
- `mosaic fleet init` can write a minimal roster.
- `mosaic fleet install-systemd` installs holder and agent units without hand editing.
- `mosaic fleet start` starts the holder and configured agents on a named tmux socket.
- Restarting one `mosaic-agent@name.service` does not change holder server PID or kill sibling sessions.
- `mosaic agent send` can deliver a message to a named agent with a self-identifying preamble.
- `mosaic agent reset` can clear/new a reusable slot and send a fresh kickstart.
- `mosaic fleet verify` proves holder ownership, exact-target safety, and per-agent restart isolation.
- Existing default tmux sessions on this server are not disturbed by default install.
- Docs explain generic customization and include USC-style roster only as an example.
- AI Guide remains generic; Mosaic Stack docs carry the concrete install path.
## Risks and mitigations
| Risk | Mitigation |
| --------------------------------------------------- | --------------------------------------------------------------------------------- |
| Killing existing tmux sessions | Use named `mosaic-factory` socket; no default `tmux kill-server`. |
| systemd unit quoting/env expansion bugs | Move logic into shell wrappers; verify with `systemd-analyze --user verify`. |
| Runtime reset command mismatch | Make reset command runtime-configurable; fallback to service restart + kickstart. |
| Tool install drift | Ensure npm package includes framework tmux/fleet tools; add packaging test. |
| Mosaic-specific assumptions leak into generic guide | Keep USC roster as example profile; AI Guide documents pattern/options. |
| Matrix migration blocked by tmux coupling | Add `mosaic agent` abstraction now; keep tmux details below transport layer. |
## Suggested first PR split
1. **PR A — tmux tool hardening**
- socket support;
- exact target helpers;
- tests/docs.
2. **PR B — fleet systemd primitives**
- holder unit;
- agent unit;
- start-agent wrapper;
- install-user-units script;
- verify script.
3. **PR C — roster and CLI**
- roster schema/examples;
- `mosaic fleet ...` commands;
- `mosaic agent ...` commands.
4. **PR D — local rollout and docs**
- local roster for this server;
- run canary;
- document verification evidence;
- update AI Guide with generic lessons.
## Immediate next action
Implement PR A first. It is low-risk, improves existing tools, and is required for a safe named-socket rollout on this server.