Compare commits
4 Commits
feat/glpi-
...
feat/869-c
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
75235ef823 | ||
|
|
b4d26abacd | ||
| b79336a8c1 | |||
| 4e5af23214 |
@@ -0,0 +1,22 @@
|
||||
[Unit]
|
||||
Description=Mosaic lease broker daemon (framework tools/lease-broker/daemon.py)
|
||||
Documentation=https://git.mosaicstack.dev/mosaicstack/stack
|
||||
After=default.target
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
# The broker socket lives under the runtime directory so it disappears with
|
||||
# the user session instead of surviving as stale state across logins.
|
||||
# daemon.py's secure_parent() fails closed unless this directory is exactly
|
||||
# 0700, so RuntimeDirectoryMode is not cosmetic.
|
||||
RuntimeDirectory=mosaic-lease
|
||||
RuntimeDirectoryMode=0700
|
||||
# Remove loader and noninteractive-shell controls before ExecStart loads env,
|
||||
# matching the tmux fleet units in this same directory.
|
||||
UnsetEnvironment=LD_PRELOAD BASH_ENV ENV
|
||||
ExecStart=/usr/bin/env -i HOME=%h PATH=/usr/bin:/bin XDG_RUNTIME_DIR=%t /bin/bash --noprofile --norc %h/.config/mosaic/tools/lease-broker/start-lease-broker.sh
|
||||
Restart=on-failure
|
||||
RestartSec=1
|
||||
|
||||
[Install]
|
||||
WantedBy=default.target
|
||||
31
packages/mosaic/framework/tools/lease-broker/start-lease-broker.sh
Executable file
31
packages/mosaic/framework/tools/lease-broker/start-lease-broker.sh
Executable file
@@ -0,0 +1,31 @@
|
||||
#!/usr/bin/env bash
|
||||
# Supervisor entry point for the Mosaic lease broker daemon (issue #869, C3).
|
||||
#
|
||||
# Resolves the broker socket path with the SAME precedence as
|
||||
# `defaultLeaseBrokerSocket` in `packages/mosaic/src/commands/launch.ts`, so a
|
||||
# gated runtime launched through that client always finds the socket this
|
||||
# supervisor creates:
|
||||
# 1. an explicit MOSAIC_LEASE_BROKER_SOCKET
|
||||
# 2. "$XDG_RUNTIME_DIR/mosaic-lease/broker.sock"
|
||||
# 3. "/run/user/<uid>/mosaic-lease/broker.sock"
|
||||
#
|
||||
# The state file is colocated next to the socket (same directory,
|
||||
# "state.json"), mirroring how the broker already colocates its per-session
|
||||
# generation files beside the socket.
|
||||
#
|
||||
# This script never installs, enables, or starts the systemd unit that calls
|
||||
# it; it is only ever invoked BY that unit (or by a human/test harness that
|
||||
# passes its own HOME/XDG_RUNTIME_DIR).
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR=$(cd -- "$(dirname -- "$0")" && pwd)
|
||||
|
||||
if [ -n "${MOSAIC_LEASE_BROKER_SOCKET:-}" ]; then
|
||||
SOCKET="$MOSAIC_LEASE_BROKER_SOCKET"
|
||||
else
|
||||
RUNTIME_DIR="${XDG_RUNTIME_DIR:-/run/user/$(id -u)}"
|
||||
SOCKET="$RUNTIME_DIR/mosaic-lease/broker.sock"
|
||||
fi
|
||||
STATE="$(dirname -- "$SOCKET")/state.json"
|
||||
|
||||
exec python3 "$SCRIPT_DIR/daemon.py" --socket "$SOCKET" --state "$STATE"
|
||||
92
packages/mosaic/framework/tools/orchestrator/README.md
Normal file
92
packages/mosaic/framework/tools/orchestrator/README.md
Normal file
@@ -0,0 +1,92 @@
|
||||
# orchestrator/ tools
|
||||
|
||||
Helper scripts for r0 coordinator / orchestrator sessions — mission lifecycle,
|
||||
session health, continuation, and board maintenance. See
|
||||
`framework/guides/ORCHESTRATOR-PROTOCOL.md` for the surrounding process.
|
||||
|
||||
| Script | Purpose |
|
||||
| -------------------- | ----------------------------------------------------------------------------------------------- |
|
||||
| `mission-init.sh` | Initialize a new orchestration mission (manifest, scratchpad, TASKS.md). |
|
||||
| `mission-status.sh` | Show the mission progress dashboard. |
|
||||
| `session-run.sh` | Generate continuation context and launch the target runtime. |
|
||||
| `session-resume.sh` | Crash recovery for dead orchestrator sessions. |
|
||||
| `session-status.sh` | Check agent session health. |
|
||||
| `continue-prompt.sh` | Generate the continuation prompt for the next session. |
|
||||
| `board-roll.sh` | Keep a LIVE orchestration board under its byte cap by rolling the oldest entries to its LEDGER. |
|
||||
| `smoke-test.sh` | Behavior smoke checks for the coord continue/run workflows. |
|
||||
| `test-board-roll.sh` | Regression harness for `board-roll.sh`. |
|
||||
| `_lib.sh` | Shared functions sourced by the above (state files, TASKS.md parsing, locks). |
|
||||
|
||||
## board-roll.sh
|
||||
|
||||
Coordinator boards (`MOS-ORCHESTRATION-BOARD-LIVE.md`, `MS-LEAD-BOARD-LIVE.md`)
|
||||
follow a **"< 8 KB LIVE"** discipline: the LIVE board is the only file loaded on
|
||||
resume, so it must stay small, and history lives in an append-only LEDGER. When a
|
||||
board write would push LIVE over its cap, coordinators otherwise hand-trim and
|
||||
retry every time — an observed 38 ABORT-OVER-CAP cycles in one 24 h window.
|
||||
`board-roll.sh` automates that trim mechanically and reversibly: the audit trail
|
||||
is moved to the LEDGER instead of being hand-deleted.
|
||||
|
||||
### Contract (conservative — it never guesses what is safe to move)
|
||||
|
||||
The LIVE board opts in by wrapping its aging archival ticks in an explicit roll
|
||||
zone. Everything **outside** the markers (title, protocol blockquote, curated
|
||||
always-current `##` sections) is pinned and never touched:
|
||||
|
||||
```markdown
|
||||
# MOS ORCHESTRATION BOARD — LIVE state
|
||||
|
||||
> protocol blockquote … (pinned)
|
||||
|
||||
## 🟦 Curated always-current section (pinned)
|
||||
|
||||
…
|
||||
|
||||
<!-- BOARD-ROLL:START -->
|
||||
|
||||
### 2026-07-22 (mid²²) — newest tick, stays longest
|
||||
|
||||
…
|
||||
|
||||
### 2026-07-20 (dawn) — oldest tick, rolled first
|
||||
|
||||
…
|
||||
|
||||
<!-- BOARD-ROLL:END -->
|
||||
```
|
||||
|
||||
Inside the zone, entries are delimited by a heading marker (default `### `) and
|
||||
are assumed **newest-first (top) → oldest-last (bottom)**. `board-roll.sh` moves
|
||||
whole oldest (bottom-most) entry blocks out of the zone and appends them verbatim
|
||||
to the LEDGER, one at a time, until LIVE is back under the cap or the zone is
|
||||
empty. If the board has no markers, it exits `3` and changes nothing — adding the
|
||||
markers is a deliberate opt-in by the board owner.
|
||||
|
||||
### Usage
|
||||
|
||||
```bash
|
||||
board-roll.sh --live <LIVE.md> --ledger <LEDGER.md> [options]
|
||||
|
||||
--live <path> LIVE board file (required)
|
||||
--ledger <path> append-only LEDGER file (required; created if absent)
|
||||
--cap <bytes> size ceiling for LIVE (default 8192)
|
||||
--marker <prefix> entry-heading prefix inside the roll zone (default "### ")
|
||||
--dry-run report what would move; change nothing
|
||||
-h, --help show help and exit 0
|
||||
```
|
||||
|
||||
Only **one** roll zone is supported. If a board carries more than one
|
||||
`BOARD-ROLL:START`/`END` pair, `board-roll.sh` refuses (exit `3`, zero changes)
|
||||
rather than span first-START..last-END and relocate the curated content between
|
||||
the zones — consolidate the ticks into a single zone instead.
|
||||
|
||||
Exit codes: `0` LIVE under cap (already, or after rolling) — on `--dry-run`, a
|
||||
plan exists or nothing to do · `2` usage / argument / IO error · `3` cannot meet
|
||||
the cap (no markers, **more than one marker pair**, or the pinned sections alone
|
||||
exceed the cap and need a manual trim).
|
||||
|
||||
Writes are atomic (temp file + `mv`, LEDGER first) so a failure never leaves a
|
||||
board half-written; line endings are normalized to LF on rewrite. `--dry-run`
|
||||
first is recommended when wiring it into a board update protocol.
|
||||
|
||||
Run the regression suite with `bash test-board-roll.sh`.
|
||||
277
packages/mosaic/framework/tools/orchestrator/board-roll.sh
Normal file
277
packages/mosaic/framework/tools/orchestrator/board-roll.sh
Normal file
@@ -0,0 +1,277 @@
|
||||
#!/usr/bin/env bash
|
||||
#
|
||||
# board-roll.sh — keep a LIVE orchestration board under its byte cap by rolling
|
||||
# the oldest archival entries out to its append-only LEDGER.
|
||||
#
|
||||
# WHY: coordinator boards (MOS-ORCHESTRATION-BOARD-LIVE.md, MS-LEAD-BOARD-LIVE.md)
|
||||
# enforce a "< 8 KB LIVE" discipline via a self-guard that ABORTs the board write
|
||||
# when the file exceeds the cap. In practice the LIVE board keeps bumping the cap,
|
||||
# so coordinators hand-trim + retry every time (observed: 38 ABORT-OVER-CAP cycles
|
||||
# in a 24h window on one coordinator). This automates that trim, mechanically and
|
||||
# reversibly, so the audit trail is preserved in the LEDGER instead of hand-deleted.
|
||||
#
|
||||
# CONTRACT (conservative by design — it NEVER guesses what is safe to move):
|
||||
# The LIVE board must declare an explicit ROLL ZONE with HTML-comment markers:
|
||||
#
|
||||
# <!-- BOARD-ROLL:START -->
|
||||
# ### 2026-07-22 (newest tick — stays longest)
|
||||
# ...
|
||||
# ### 2026-07-19 (oldest tick — rolled first)
|
||||
# ...
|
||||
# <!-- BOARD-ROLL:END -->
|
||||
#
|
||||
# Everything OUTSIDE the markers (title, protocol blockquote, curated always-current
|
||||
# `##` sections) is PINNED and never touched. Inside the zone, entries are delimited
|
||||
# by a heading marker (default `### `) and are assumed newest-first (top) → oldest-last
|
||||
# (bottom), matching board convention. board-roll moves whole oldest (bottom-most)
|
||||
# entry blocks out of the zone and APPENDS them verbatim to the LEDGER, one block at a
|
||||
# time, until the LIVE file is back under the cap or the zone is empty.
|
||||
#
|
||||
# If no markers are present, it exits 3 without changing anything (safe default —
|
||||
# adding the markers is a deliberate opt-in by the board owner).
|
||||
#
|
||||
# USAGE:
|
||||
# board-roll.sh --live <LIVE.md> --ledger <LEDGER.md> [options]
|
||||
#
|
||||
# OPTIONS:
|
||||
# --live <path> LIVE board file (required)
|
||||
# --ledger <path> append-only LEDGER file (required; created if absent)
|
||||
# --cap <bytes> size ceiling for LIVE (default 8192)
|
||||
# --marker <prefix> entry-heading prefix inside the roll zone (default "### ")
|
||||
# --dry-run report what would move + resulting size; change nothing
|
||||
# -h, --help print usage and exit 0
|
||||
#
|
||||
# EXIT CODES:
|
||||
# 0 LIVE is under cap (already, or after rolling); on --dry-run, 0 = a plan exists
|
||||
# (or nothing to do)
|
||||
# 2 usage / argument / IO error (bad flag, missing file, unwritable target)
|
||||
# 3 cannot satisfy the cap: no roll markers present, MORE THAN ONE marker pair
|
||||
# (multiple zones are refused, not guessed), OR the zone was emptied and LIVE
|
||||
# is still over cap (curated pinned sections need a manual trim)
|
||||
#
|
||||
# NOTE: line endings are normalized to LF on rewrite (boards are LF markdown); a
|
||||
# trailing newline is always ensured. Writes are atomic (temp file + mv) so a
|
||||
# failure never leaves LIVE or LEDGER half-written.
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
START_MARK='<!-- BOARD-ROLL:START -->'
|
||||
END_MARK='<!-- BOARD-ROLL:END -->'
|
||||
|
||||
usage() {
|
||||
cat <<'EOF'
|
||||
Usage: board-roll.sh --live <LIVE.md> --ledger <LEDGER.md> [options]
|
||||
|
||||
Roll the oldest entries out of a LIVE orchestration board into its LEDGER
|
||||
until the LIVE file is under a byte cap. Conservative: only content inside
|
||||
explicit <!-- BOARD-ROLL:START -->/<!-- BOARD-ROLL:END --> markers is moved.
|
||||
|
||||
Options:
|
||||
--live <path> LIVE board file (required)
|
||||
--ledger <path> append-only LEDGER file (required; created if absent)
|
||||
--cap <bytes> size ceiling for LIVE (default 8192)
|
||||
--marker <prefix> entry-heading prefix inside the roll zone (default "### ")
|
||||
--dry-run report what would move; change nothing
|
||||
-h, --help show this help and exit 0
|
||||
|
||||
Exit: 0 under cap (or dry-run plan) · 2 usage/IO error · 3 cannot meet cap
|
||||
(no markers, or pinned sections alone exceed the cap).
|
||||
EOF
|
||||
}
|
||||
|
||||
die() { echo "board-roll: $*" >&2; exit 2; }
|
||||
|
||||
LIVE=""; LEDGER=""; CAP=8192; MARKER='### '; DRYRUN=0
|
||||
while [[ $# -gt 0 ]]; do
|
||||
case "$1" in
|
||||
--live) LIVE="${2:-}"; shift 2 || die "--live needs a value" ;;
|
||||
--ledger) LEDGER="${2:-}"; shift 2 || die "--ledger needs a value" ;;
|
||||
--cap) CAP="${2:-}"; shift 2 || die "--cap needs a value" ;;
|
||||
--marker) MARKER="${2:-}"; shift 2 || die "--marker needs a value" ;;
|
||||
--dry-run) DRYRUN=1; shift ;;
|
||||
-h|--help) usage; exit 0 ;;
|
||||
*) usage >&2; die "unknown option: $1" ;;
|
||||
esac
|
||||
done
|
||||
|
||||
[[ -n "$LIVE" ]] || { usage >&2; die "--live is required"; }
|
||||
[[ -n "$LEDGER" ]] || { usage >&2; die "--ledger is required"; }
|
||||
[[ -f "$LIVE" ]] || die "LIVE file not found: $LIVE"
|
||||
[[ "$CAP" =~ ^[0-9]+$ ]] || die "--cap must be a non-negative integer, got: $CAP"
|
||||
|
||||
# --- read LIVE into a line array (newlines stripped; re-added on write) ---------
|
||||
mapfile -t LINES < "$LIVE"
|
||||
|
||||
# byte size of an array rendered as LF-terminated text
|
||||
render_size() {
|
||||
if [[ $# -eq 0 ]]; then printf 0; return; fi
|
||||
printf '%s\n' "$@" | wc -c
|
||||
}
|
||||
|
||||
orig_size=$(render_size "${LINES[@]}")
|
||||
|
||||
# --- already under cap → nothing to do -----------------------------------------
|
||||
if (( orig_size < CAP )); then
|
||||
echo "board-roll: LIVE is ${orig_size}B (< cap ${CAP}B) — nothing to roll."
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# --- locate the roll-zone markers ----------------------------------------------
|
||||
# Exactly ONE marker pair is supported. If a board carries more than one START or
|
||||
# END marker we REFUSE (exit 3, zero changes) rather than guess: a naive
|
||||
# first-START..last-END span would swallow the curated content and the intermediate
|
||||
# markers sitting between two intended zones and silently relocate that pinned text
|
||||
# to the LEDGER — the exact data-loss this tool exists to prevent. Refusing matches
|
||||
# the "no markers = exit 3" conservative posture.
|
||||
start_idx=-1; end_idx=-1; start_count=0; end_count=0
|
||||
for i in "${!LINES[@]}"; do
|
||||
if [[ "${LINES[$i]}" == "$START_MARK" ]]; then
|
||||
if (( start_count == 0 )); then start_idx=$i; fi
|
||||
start_count=$(( start_count + 1 ))
|
||||
fi
|
||||
if [[ "${LINES[$i]}" == "$END_MARK" ]]; then
|
||||
end_idx=$i
|
||||
end_count=$(( end_count + 1 ))
|
||||
fi
|
||||
done
|
||||
if (( start_count > 1 || end_count > 1 )); then
|
||||
echo "board-roll: LIVE is ${orig_size}B (>= cap ${CAP}B) but has ${start_count} START / ${end_count} END" >&2
|
||||
echo " markers — only a SINGLE '$START_MARK' … '$END_MARK' roll zone is supported." >&2
|
||||
echo " Multiple zones are refused (not guessed) so content between zones is never relocated." >&2
|
||||
echo " Consolidate the archival ticks into one zone, or trim manually." >&2
|
||||
exit 3
|
||||
fi
|
||||
if (( start_idx < 0 || end_idx < 0 || end_idx <= start_idx )); then
|
||||
echo "board-roll: LIVE is ${orig_size}B (>= cap ${CAP}B) but no usable roll zone" >&2
|
||||
echo " (need '$START_MARK' then '$END_MARK'). Add the markers around the" >&2
|
||||
echo " archival tick section to opt this board into automatic rolling." >&2
|
||||
exit 3
|
||||
fi
|
||||
|
||||
# preamble = lines [0 .. start_idx] (inclusive of START marker)
|
||||
# zone = lines (start_idx .. end_idx) (exclusive of both markers)
|
||||
# footer = lines [end_idx .. end] (inclusive of END marker)
|
||||
preamble=(); zone=(); footer=()
|
||||
for i in "${!LINES[@]}"; do
|
||||
if (( i <= start_idx )); then preamble+=("${LINES[$i]}")
|
||||
elif (( i < end_idx )); then zone+=("${LINES[$i]}")
|
||||
else footer+=("${LINES[$i]}")
|
||||
fi
|
||||
done
|
||||
|
||||
# --- split the zone into a fixed head + entry blocks ----------------------------
|
||||
# zone_head = any zone lines before the first entry marker (kept, never rolled).
|
||||
# blocks[k] = newline-joined text of entry k (marker line .. line before next marker).
|
||||
zone_head=(); declare -a block_start=()
|
||||
first_block=-1
|
||||
for i in "${!zone[@]}"; do
|
||||
if [[ "${zone[$i]}" == "$MARKER"* ]]; then
|
||||
[[ $first_block -eq -1 ]] && first_block=$i
|
||||
block_start+=("$i")
|
||||
fi
|
||||
done
|
||||
if (( first_block == -1 )); then
|
||||
echo "board-roll: LIVE is ${orig_size}B (>= cap ${CAP}B) but the roll zone has no" >&2
|
||||
echo " '${MARKER}' entries to move. Trim the pinned sections manually." >&2
|
||||
exit 3
|
||||
fi
|
||||
for (( i=0; i<first_block; i++ )); do zone_head+=("${zone[$i]}"); done
|
||||
|
||||
nblocks=${#block_start[@]}
|
||||
# block k spans zone[ block_start[k] .. (block_start[k+1]-1 or end-of-zone) ]
|
||||
block_text() { # $1 = block index → prints the block's lines, LF-joined (no trailing)
|
||||
local k=$1 s e
|
||||
s=${block_start[$k]}
|
||||
if (( k+1 < nblocks )); then e=$(( block_start[$((k+1))] - 1 )); else e=$(( ${#zone[@]} - 1 )); fi
|
||||
local out=()
|
||||
for (( j=s; j<=e; j++ )); do out+=("${zone[$j]}"); done
|
||||
printf '%s\n' "${out[@]}"
|
||||
}
|
||||
|
||||
# --- greedily roll oldest (bottom-most) blocks until under cap ------------------
|
||||
# keep = number of newest blocks retained; start with all, drop from the bottom.
|
||||
keep=$nblocks # blocks [keep .. nblocks-1] are the oldest set that gets moved
|
||||
current_size=$orig_size
|
||||
build_live_size() { # size of LIVE if we keep blocks [0 .. keep-1]
|
||||
local acc=("${preamble[@]}" "${zone_head[@]}")
|
||||
local k s e j
|
||||
for (( k=0; k<keep; k++ )); do
|
||||
s=${block_start[$k]}
|
||||
if (( k+1 < nblocks )); then e=$(( block_start[$((k+1))] - 1 )); else e=$(( ${#zone[@]} - 1 )); fi
|
||||
for (( j=s; j<=e; j++ )); do acc+=("${zone[$j]}"); done
|
||||
done
|
||||
acc+=("${footer[@]}")
|
||||
render_size "${acc[@]}"
|
||||
}
|
||||
while (( current_size >= CAP && keep > 0 )); do
|
||||
keep=$(( keep - 1 ))
|
||||
current_size=$(build_live_size)
|
||||
done
|
||||
|
||||
moved_count=$(( nblocks - keep ))
|
||||
if (( moved_count == 0 )); then
|
||||
# zone had entries but none movable brought us under (shouldn't happen: keep hits 0)
|
||||
echo "board-roll: could not reduce LIVE below cap (${current_size}B >= ${CAP}B)." >&2
|
||||
exit 3
|
||||
fi
|
||||
|
||||
# --- dry-run report -------------------------------------------------------------
|
||||
plan_headers() {
|
||||
local k
|
||||
for (( k=keep; k<nblocks; k++ )); do
|
||||
# first line of each moved block
|
||||
printf ' %s\n' "${zone[${block_start[$k]}]}"
|
||||
done
|
||||
}
|
||||
if (( DRYRUN )); then
|
||||
echo "board-roll: DRY RUN"
|
||||
echo " LIVE now: ${orig_size}B (cap ${CAP}B) — over by $(( orig_size - CAP ))B"
|
||||
echo " would roll: ${moved_count} of ${nblocks} entr$([[ $moved_count -eq 1 ]] && echo y || echo ies) (oldest first):"
|
||||
plan_headers
|
||||
echo " LIVE after: ${current_size}B"
|
||||
if (( current_size >= CAP )); then
|
||||
echo " WARNING: still >= cap after emptying the zone; pinned sections need a manual trim." >&2
|
||||
exit 3
|
||||
fi
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# --- commit the roll atomically -------------------------------------------------
|
||||
live_tmp="$(mktemp "${LIVE}.roll.XXXXXX")" || die "cannot create temp next to LIVE"
|
||||
ledger_tmp=""
|
||||
# shellcheck disable=SC2329 # invoked indirectly via `trap cleanup EXIT`
|
||||
cleanup() { rm -f "$live_tmp" "$ledger_tmp" 2>/dev/null || true; }
|
||||
trap cleanup EXIT
|
||||
|
||||
# new LIVE = preamble + zone_head + kept blocks + footer
|
||||
{
|
||||
printf '%s\n' "${preamble[@]}" "${zone_head[@]}"
|
||||
for (( k=0; k<keep; k++ )); do block_text "$k"; done
|
||||
printf '%s\n' "${footer[@]}"
|
||||
} > "$live_tmp"
|
||||
|
||||
# LEDGER gets the moved blocks appended verbatim, in original top→bottom order,
|
||||
# under a provenance separator. LEDGER is append-only, so we only ever add at EOF.
|
||||
ledger_tmp="$(mktemp "${LEDGER}.roll.XXXXXX")" || die "cannot create temp next to LEDGER"
|
||||
if [[ -f "$LEDGER" ]]; then cat "$LEDGER" > "$ledger_tmp"; fi
|
||||
# ensure a trailing newline on existing content before appending
|
||||
if [[ -s "$ledger_tmp" && -n "$(tail -c1 "$ledger_tmp")" ]]; then printf '\n' >> "$ledger_tmp"; fi
|
||||
{
|
||||
printf '\n<!-- board-roll: %d entr%s rolled from %s -->\n' \
|
||||
"$moved_count" "$([[ $moved_count -eq 1 ]] && echo y || echo ies)" "$(basename "$LIVE")"
|
||||
for (( k=keep; k<nblocks; k++ )); do block_text "$k"; done
|
||||
} >> "$ledger_tmp"
|
||||
|
||||
# atomic swap (both, LEDGER first so a crash never drops content that left LIVE)
|
||||
mv "$ledger_tmp" "$LEDGER"; ledger_tmp=""
|
||||
mv "$live_tmp" "$LIVE"; live_tmp=""
|
||||
trap - EXIT
|
||||
|
||||
# read the real on-disk size back (truthful, not the predicted value)
|
||||
final_size=$(wc -c < "$LIVE")
|
||||
echo "board-roll: rolled ${moved_count} entr$([[ $moved_count -eq 1 ]] && echo y || echo ies) to $(basename "$LEDGER"); LIVE ${orig_size}B → ${final_size}B (cap ${CAP}B)."
|
||||
if (( final_size >= CAP )); then
|
||||
echo "board-roll: still >= cap after rolling all zone entries; pinned sections need a manual trim." >&2
|
||||
exit 3
|
||||
fi
|
||||
exit 0
|
||||
156
packages/mosaic/framework/tools/orchestrator/test-board-roll.sh
Normal file
156
packages/mosaic/framework/tools/orchestrator/test-board-roll.sh
Normal file
@@ -0,0 +1,156 @@
|
||||
#!/usr/bin/env bash
|
||||
# Regression harness for board-roll.sh — rolling oldest LIVE-board entries to LEDGER.
|
||||
#
|
||||
# Asserts:
|
||||
# 1. Under cap → no-op, exit 0, files unchanged.
|
||||
# 2. Over cap, no roll markers → exit 3, LIVE unchanged (never guesses).
|
||||
# 3. Over cap, markers present → rolls the fewest oldest entries to get under cap,
|
||||
# LIVE ends under cap, pinned preamble/footer + newest entries preserved.
|
||||
# 4. Rolled blocks land in the LEDGER verbatim, oldest set in original order.
|
||||
# 5. --dry-run changes nothing and reports a plan.
|
||||
# 6. Zone emptied but pinned sections alone exceed cap → exit 3.
|
||||
# 7. --help exits 0 and prints usage; an unknown flag exits nonzero (#701 discipline).
|
||||
# 8. More than one marker pair → exit 3, unchanged; curated content between the two
|
||||
# zones is never relocated to the LEDGER (rev0 #868 regression).
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
SUT="$SCRIPT_DIR/board-roll.sh"
|
||||
|
||||
fail=0
|
||||
note() { echo "FAIL: $*" >&2; fail=1; }
|
||||
|
||||
WORK="$(mktemp -d)"
|
||||
trap 'rm -rf "$WORK"' EXIT
|
||||
|
||||
# builds a LIVE board: pinned preamble + roll zone with N dated entries (newest first),
|
||||
# each entry padded to be individually large so the cap math is predictable.
|
||||
make_board() { # $1 file $2 n_entries $3 with_markers(1/0) $4 pad_bytes
|
||||
local f=$1 n=$2 markers=$3 pad=$4 i padtxt
|
||||
padtxt=$(head -c "$pad" < /dev/zero | tr '\0' 'x')
|
||||
{
|
||||
echo "# BOARD — LIVE"
|
||||
echo "> pinned protocol blockquote, never rolled."
|
||||
echo
|
||||
echo "## Curated always-current section (pinned)"
|
||||
echo "- this stays no matter what"
|
||||
echo
|
||||
[[ "$markers" == 1 ]] && echo '<!-- BOARD-ROLL:START -->'
|
||||
# newest first (i=n .. 1); oldest (i=1) ends at the bottom
|
||||
for (( i=n; i>=1; i-- )); do
|
||||
echo "### 2026-07-$(printf '%02d' $i) tick number $i"
|
||||
echo "- detail $i $padtxt"
|
||||
echo
|
||||
done
|
||||
[[ "$markers" == 1 ]] && echo '<!-- BOARD-ROLL:END -->'
|
||||
} > "$f"
|
||||
return 0
|
||||
}
|
||||
|
||||
# ── 1. under cap → no-op ───────────────────────────────────────────────────────
|
||||
L="$WORK/live1.md"; G="$WORK/ledger1.md"; : > "$G"
|
||||
make_board "$L" 2 1 10
|
||||
before=$(cat "$L")
|
||||
if ! out=$(bash "$SUT" --live "$L" --ledger "$G" --cap 100000 2>&1); then
|
||||
note "under-cap should exit 0 (got nonzero): $out"
|
||||
fi
|
||||
[[ "$(cat "$L")" == "$before" ]] || note "under-cap modified LIVE"
|
||||
[[ -s "$G" ]] && note "under-cap wrote to LEDGER"
|
||||
|
||||
# ── 2. over cap, no markers → exit 3, unchanged ────────────────────────────────
|
||||
L="$WORK/live2.md"; G="$WORK/ledger2.md"; : > "$G"
|
||||
make_board "$L" 6 0 400
|
||||
before=$(cat "$L")
|
||||
set +e; bash "$SUT" --live "$L" --ledger "$G" --cap 800 >/dev/null 2>&1; rc=$?; set -e
|
||||
[[ "$rc" -eq 3 ]] || note "no-markers over-cap should exit 3 (got $rc)"
|
||||
[[ "$(cat "$L")" == "$before" ]] || note "no-markers run modified LIVE (must never guess)"
|
||||
|
||||
# ── 3+4. over cap with markers → rolls oldest, LIVE under cap, LEDGER gets them ─
|
||||
L="$WORK/live3.md"; G="$WORK/ledger3.md"; echo "# LEDGER" > "$G"
|
||||
make_board "$L" 6 1 400 # 6 entries, each ~>400B
|
||||
big=$(wc -c < "$L")
|
||||
[[ "$big" -ge 2000 ]] || note "fixture too small to test rolling ($big B)"
|
||||
if ! out=$(bash "$SUT" --live "$L" --ledger "$G" --cap 2000 2>&1); then
|
||||
note "marker roll should exit 0 when it can get under cap: $out"
|
||||
fi
|
||||
after=$(wc -c < "$L")
|
||||
[[ "$after" -lt 2000 ]] || note "LIVE still >= cap after roll ($after B)"
|
||||
# pinned content survives
|
||||
grep -q "Curated always-current section" "$L" || note "roll dropped pinned section"
|
||||
grep -q 'BOARD-ROLL:START' "$L" || note "roll dropped START marker"
|
||||
grep -q 'BOARD-ROLL:END' "$L" || note "roll dropped END marker"
|
||||
# newest entry (07-06) stays; oldest (07-01) is the first to leave
|
||||
grep -q "### 2026-07-06 tick number 6" "$L" || note "roll dropped the newest entry"
|
||||
grep -q "### 2026-07-01 tick number 1" "$L" && note "oldest entry not rolled out of LIVE"
|
||||
# oldest went to LEDGER
|
||||
grep -q "### 2026-07-01 tick number 1" "$G" || note "oldest entry not appended to LEDGER"
|
||||
grep -q "board-roll:.*rolled from live3.md" "$G" || note "LEDGER missing provenance separator"
|
||||
# a rolled entry must not be duplicated (present in exactly one of LIVE/LEDGER)
|
||||
if grep -q "### 2026-07-01 tick number 1" "$L"; then note "rolled entry duplicated in LIVE"; fi
|
||||
# LEDGER original content preserved
|
||||
grep -q "^# LEDGER" "$G" || note "roll clobbered existing LEDGER content"
|
||||
|
||||
# ── 5. --dry-run changes nothing ───────────────────────────────────────────────
|
||||
L="$WORK/live5.md"; G="$WORK/ledger5.md"; echo "# LEDGER" > "$G"
|
||||
make_board "$L" 6 1 400
|
||||
before_l=$(cat "$L"); before_g=$(cat "$G")
|
||||
out=$(bash "$SUT" --live "$L" --ledger "$G" --cap 2000 --dry-run 2>&1) || note "dry-run exited nonzero: $out"
|
||||
echo "$out" | grep -qi "dry run" || note "dry-run did not announce itself"
|
||||
echo "$out" | grep -q "would roll" || note "dry-run did not report a plan"
|
||||
[[ "$(cat "$L")" == "$before_l" ]] || note "dry-run modified LIVE"
|
||||
[[ "$(cat "$G")" == "$before_g" ]] || note "dry-run modified LEDGER"
|
||||
|
||||
# ── 6. zone emptied, pinned alone over cap → exit 3 ────────────────────────────
|
||||
# cap 120 is below the pinned preamble+footer size (~180B), so even after rolling
|
||||
# every zone entry the LIVE file stays over cap → must report the unsatisfiable case.
|
||||
L="$WORK/live6.md"; G="$WORK/ledger6.md"; echo "# LEDGER" > "$G"
|
||||
make_board "$L" 3 1 50
|
||||
set +e; bash "$SUT" --live "$L" --ledger "$G" --cap 120 >/dev/null 2>&1; rc=$?; set -e
|
||||
[[ "$rc" -eq 3 ]] || note "unsatisfiable cap should exit 3 (got $rc)"
|
||||
|
||||
# ── 7. help exits 0, unknown flag exits nonzero (#701) ─────────────────────────
|
||||
if ! out=$(bash "$SUT" --help 2>&1); then note "--help exited nonzero"; fi
|
||||
[[ "$out" == Usage:* ]] || note "--help did not print usage"
|
||||
bash "$SUT" -h >/dev/null 2>&1 || note "-h exited nonzero"
|
||||
if bash "$SUT" --not-a-real-flag >/dev/null 2>&1; then note "unknown flag was accepted"; fi
|
||||
if bash "$SUT" --live "$WORK/live3.md" >/dev/null 2>&1; then note "missing --ledger was accepted"; fi
|
||||
|
||||
# ── 8. multiple marker pairs → exit 3, unchanged (no cross-zone relocation) ─────
|
||||
# Two separately-marked zones with a curated pinned section BETWEEN them. A naive
|
||||
# first-START..last-END span would sweep that curated section (and the intermediate
|
||||
# markers) into the LEDGER. board-roll must refuse (exit 3) and touch nothing.
|
||||
L="$WORK/live8.md"; G="$WORK/ledger8.md"; echo "# LEDGER" > "$G"
|
||||
pad8=$(head -c 300 < /dev/zero | tr '\0' 'x')
|
||||
{
|
||||
echo "# BOARD — LIVE"
|
||||
echo "> pinned protocol blockquote"
|
||||
echo
|
||||
echo '<!-- BOARD-ROLL:START -->'
|
||||
echo "### 2026-07-10 zone-A newest"
|
||||
echo "- detail A2 $pad8"
|
||||
echo "### 2026-07-09 zone-A oldest"
|
||||
echo "- detail A1 $pad8"
|
||||
echo '<!-- BOARD-ROLL:END -->'
|
||||
echo
|
||||
echo "## Curated-between-zones (pinned — must never move)"
|
||||
echo "- CANARY-BETWEEN keep me"
|
||||
echo
|
||||
echo '<!-- BOARD-ROLL:START -->'
|
||||
echo "### 2026-07-08 zone-B newest"
|
||||
echo "- detail B2 $pad8"
|
||||
echo "### 2026-07-07 zone-B oldest"
|
||||
echo "- detail B1 $pad8"
|
||||
echo '<!-- BOARD-ROLL:END -->'
|
||||
} > "$L"
|
||||
before8=$(cat "$L")
|
||||
set +e; bash "$SUT" --live "$L" --ledger "$G" --cap 80 >/dev/null 2>&1; rc=$?; set -e
|
||||
[[ "$rc" -eq 3 ]] || note "multi-pair board should exit 3 (got $rc)"
|
||||
[[ "$(cat "$L")" == "$before8" ]] || note "multi-pair run modified LIVE (must never guess across zones)"
|
||||
grep -q "CANARY-BETWEEN keep me" "$L" || note "multi-pair run relocated curated between-zones content"
|
||||
grep -q "CANARY-BETWEEN" "$G" && note "curated between-zones content leaked into LEDGER"
|
||||
|
||||
if [[ "$fail" -eq 0 ]]; then
|
||||
echo "board-roll regression passed (8 groups)"
|
||||
fi
|
||||
exit "$fail"
|
||||
237
packages/mosaic/src/lease-broker/broker-supervisor.spec.ts
Normal file
237
packages/mosaic/src/lease-broker/broker-supervisor.spec.ts
Normal file
@@ -0,0 +1,237 @@
|
||||
import { createServer, type Server } from 'node:net';
|
||||
import { mkdir, mkdtemp, readFile, rm, stat, writeFile } from 'node:fs/promises';
|
||||
import { tmpdir } from 'node:os';
|
||||
import { join } from 'node:path';
|
||||
|
||||
import { afterEach, describe, expect, it } from 'vitest';
|
||||
|
||||
import {
|
||||
applyBrokerSupervisor,
|
||||
checkBrokerSupervisorHealth,
|
||||
isBrokerSupervisorHealthy,
|
||||
resolveBrokerSupervisorPaths,
|
||||
resolveLeaseBrokerSocketPath,
|
||||
type BrokerSupervisorPaths,
|
||||
} from './broker-supervisor.js';
|
||||
|
||||
const REAL_FRAMEWORK_ROOT = new URL('../../framework/', import.meta.url).pathname;
|
||||
|
||||
const cleanupDirs: string[] = [];
|
||||
const cleanupServers: Server[] = [];
|
||||
|
||||
async function tempDir(prefix: string): Promise<string> {
|
||||
const dir = await mkdtemp(join(tmpdir(), prefix));
|
||||
cleanupDirs.push(dir);
|
||||
return dir;
|
||||
}
|
||||
|
||||
afterEach(async () => {
|
||||
for (const server of cleanupServers.splice(0)) {
|
||||
await new Promise<void>((resolve) => server.close(() => resolve()));
|
||||
}
|
||||
for (const dir of cleanupDirs.splice(0)) {
|
||||
await rm(dir, { recursive: true, force: true });
|
||||
}
|
||||
});
|
||||
|
||||
describe('resolveLeaseBrokerSocketPath', () => {
|
||||
it('honors an explicit MOSAIC_LEASE_BROKER_SOCKET override', () => {
|
||||
expect(resolveLeaseBrokerSocketPath({ MOSAIC_LEASE_BROKER_SOCKET: '/tmp/explicit.sock' })).toBe(
|
||||
'/tmp/explicit.sock',
|
||||
);
|
||||
});
|
||||
|
||||
it('falls back to $XDG_RUNTIME_DIR/mosaic-lease/broker.sock', () => {
|
||||
expect(resolveLeaseBrokerSocketPath({ XDG_RUNTIME_DIR: '/run/user/1000' })).toBe(
|
||||
join('/run/user/1000', 'mosaic-lease', 'broker.sock'),
|
||||
);
|
||||
});
|
||||
|
||||
it('falls back to /run/user/<uid>/mosaic-lease/broker.sock as a last resort', () => {
|
||||
expect(resolveLeaseBrokerSocketPath({}, 4242)).toBe(
|
||||
join('/run/user', '4242', 'mosaic-lease', 'broker.sock'),
|
||||
);
|
||||
});
|
||||
|
||||
it('prefers the explicit override over XDG_RUNTIME_DIR', () => {
|
||||
expect(
|
||||
resolveLeaseBrokerSocketPath({
|
||||
MOSAIC_LEASE_BROKER_SOCKET: '/explicit.sock',
|
||||
XDG_RUNTIME_DIR: '/run/user/1000',
|
||||
}),
|
||||
).toBe('/explicit.sock');
|
||||
});
|
||||
});
|
||||
|
||||
describe('resolveBrokerSupervisorPaths', () => {
|
||||
it('colocates the state file next to the resolved socket', () => {
|
||||
const paths = resolveBrokerSupervisorPaths({
|
||||
mosaicHome: '/home/x/.config/mosaic',
|
||||
frameworkRoot: '/repo/framework',
|
||||
env: { XDG_RUNTIME_DIR: '/run/user/1000' },
|
||||
});
|
||||
expect(paths.socketPath).toBe(join('/run/user/1000', 'mosaic-lease', 'broker.sock'));
|
||||
expect(paths.statePath).toBe(join('/run/user/1000', 'mosaic-lease', 'state.json'));
|
||||
});
|
||||
|
||||
it('targets the systemd --user dir under the given home, not mosaicHome', () => {
|
||||
const paths = resolveBrokerSupervisorPaths({
|
||||
mosaicHome: '/somewhere-else/.config/mosaic',
|
||||
frameworkRoot: '/repo/framework',
|
||||
homeDir: '/home/canary',
|
||||
env: {},
|
||||
uid: 0,
|
||||
});
|
||||
expect(paths.systemdUserDir).toBe(join('/home/canary', '.config', 'systemd', 'user'));
|
||||
expect(paths.unitTargetPath).toBe(
|
||||
join('/home/canary', '.config', 'systemd', 'user', 'mosaic-lease-broker.service'),
|
||||
);
|
||||
});
|
||||
|
||||
it('is a pure function: identical options resolve to identical paths', () => {
|
||||
const options = {
|
||||
mosaicHome: '/h/.config/mosaic',
|
||||
frameworkRoot: '/repo/framework',
|
||||
env: { XDG_RUNTIME_DIR: '/run/user/1000' },
|
||||
};
|
||||
expect(resolveBrokerSupervisorPaths(options)).toEqual(resolveBrokerSupervisorPaths(options));
|
||||
});
|
||||
});
|
||||
|
||||
describe('applyBrokerSupervisor', () => {
|
||||
async function fakePaths(): Promise<BrokerSupervisorPaths> {
|
||||
const home = await tempDir('mosaic-broker-supervisor-home-');
|
||||
const mosaicHome = join(home, '.config', 'mosaic');
|
||||
const runtimeDir = await tempDir('mosaic-broker-supervisor-runtime-');
|
||||
return resolveBrokerSupervisorPaths({
|
||||
mosaicHome,
|
||||
frameworkRoot: REAL_FRAMEWORK_ROOT,
|
||||
homeDir: home,
|
||||
env: { XDG_RUNTIME_DIR: runtimeDir },
|
||||
});
|
||||
}
|
||||
|
||||
it('renders a unit that references the installed wrapper script and hardens the runtime dir', async () => {
|
||||
const paths = await fakePaths();
|
||||
const unitSource = await readFile(paths.unitSourcePath, 'utf8');
|
||||
expect(unitSource).toContain('ExecStart=');
|
||||
expect(unitSource).toContain('%h/.config/mosaic/tools/lease-broker/start-lease-broker.sh');
|
||||
expect(unitSource).toContain('RuntimeDirectory=mosaic-lease');
|
||||
expect(unitSource).toContain('RuntimeDirectoryMode=0700');
|
||||
expect(unitSource).toContain('Restart=on-failure');
|
||||
expect(unitSource).toContain('WantedBy=default.target');
|
||||
// No ambient environment file preload, matching the other fleet units'
|
||||
// strict-parsing convention.
|
||||
expect(unitSource).not.toMatch(/^Environment(File)?=/m);
|
||||
});
|
||||
|
||||
it('materializes the unit, wrapper script, and daemon sources on first apply', async () => {
|
||||
const paths = await fakePaths();
|
||||
|
||||
const result = await applyBrokerSupervisor(paths);
|
||||
|
||||
expect(result.installedFiles).toContain(paths.unitTargetPath);
|
||||
expect(result.installedFiles).toContain(paths.wrapperTargetPath);
|
||||
for (const target of paths.daemonTargetPaths) {
|
||||
expect(result.installedFiles).toContain(target);
|
||||
}
|
||||
|
||||
const unitTargetContent = await readFile(paths.unitTargetPath, 'utf8');
|
||||
const unitSourceContent = await readFile(paths.unitSourcePath, 'utf8');
|
||||
expect(unitTargetContent).toBe(unitSourceContent);
|
||||
|
||||
const wrapperMode = (await stat(paths.wrapperTargetPath)).mode & 0o777;
|
||||
expect(wrapperMode).toBe(0o755);
|
||||
|
||||
for (const target of paths.daemonTargetPaths) {
|
||||
await expect(stat(target)).resolves.toBeDefined();
|
||||
}
|
||||
});
|
||||
|
||||
it('is idempotent: applying twice reproduces identical files with no error', async () => {
|
||||
const paths = await fakePaths();
|
||||
|
||||
await applyBrokerSupervisor(paths);
|
||||
const firstUnit = await readFile(paths.unitTargetPath, 'utf8');
|
||||
const firstWrapper = await readFile(paths.wrapperTargetPath, 'utf8');
|
||||
const firstWrapperMode = (await stat(paths.wrapperTargetPath)).mode & 0o777;
|
||||
|
||||
await expect(applyBrokerSupervisor(paths)).resolves.toBeDefined();
|
||||
|
||||
const secondUnit = await readFile(paths.unitTargetPath, 'utf8');
|
||||
const secondWrapper = await readFile(paths.wrapperTargetPath, 'utf8');
|
||||
const secondWrapperMode = (await stat(paths.wrapperTargetPath)).mode & 0o777;
|
||||
|
||||
expect(secondUnit).toBe(firstUnit);
|
||||
expect(secondWrapper).toBe(firstWrapper);
|
||||
expect(secondWrapperMode).toBe(firstWrapperMode);
|
||||
});
|
||||
|
||||
it('never touches the real host: only writes under the supplied temp dirs', async () => {
|
||||
const paths = await fakePaths();
|
||||
await applyBrokerSupervisor(paths);
|
||||
expect(paths.systemdUserDir.startsWith(tmpdir())).toBe(true);
|
||||
expect(paths.mosaicHome.startsWith(tmpdir())).toBe(true);
|
||||
});
|
||||
});
|
||||
|
||||
describe('checkBrokerSupervisorHealth / isBrokerSupervisorHealthy', () => {
|
||||
async function fakeHealthPaths(): Promise<
|
||||
Pick<BrokerSupervisorPaths, 'unitTargetPath' | 'socketPath'>
|
||||
> {
|
||||
const runtimeDir = await tempDir('mosaic-broker-supervisor-health-');
|
||||
await mkdir(join(runtimeDir, 'systemd-user'), { recursive: true });
|
||||
return {
|
||||
unitTargetPath: join(runtimeDir, 'systemd-user', 'mosaic-lease-broker.service'),
|
||||
socketPath: join(runtimeDir, 'broker.sock'),
|
||||
};
|
||||
}
|
||||
|
||||
it('reports unhealthy when neither the unit nor the socket exist', async () => {
|
||||
const paths = await fakeHealthPaths();
|
||||
|
||||
const health = await checkBrokerSupervisorHealth(paths);
|
||||
|
||||
expect(health).toEqual({ unitInstalled: false, socketPresent: false, healthy: false });
|
||||
expect(await isBrokerSupervisorHealthy(paths)).toBe(false);
|
||||
});
|
||||
|
||||
it('reports unhealthy when the unit is installed but no socket is listening', async () => {
|
||||
const paths = await fakeHealthPaths();
|
||||
await writeFile(paths.unitTargetPath, '[Unit]\n');
|
||||
|
||||
const health = await checkBrokerSupervisorHealth(paths);
|
||||
|
||||
expect(health.unitInstalled).toBe(true);
|
||||
expect(health.socketPresent).toBe(false);
|
||||
expect(health.healthy).toBe(false);
|
||||
});
|
||||
|
||||
it('reports healthy=true once a real Unix socket exists at the resolved path, and false again once removed', async () => {
|
||||
const paths = await fakeHealthPaths();
|
||||
|
||||
const server = createServer();
|
||||
cleanupServers.push(server);
|
||||
await new Promise<void>((resolve, reject) => {
|
||||
server.once('error', reject);
|
||||
server.listen(paths.socketPath, resolve);
|
||||
});
|
||||
|
||||
expect(await isBrokerSupervisorHealthy(paths)).toBe(true);
|
||||
const health = await checkBrokerSupervisorHealth(paths);
|
||||
expect(health.socketPresent).toBe(true);
|
||||
expect(health.healthy).toBe(true);
|
||||
|
||||
await new Promise<void>((resolve) => server.close(() => resolve()));
|
||||
await rm(paths.socketPath, { force: true });
|
||||
|
||||
expect(await isBrokerSupervisorHealthy(paths)).toBe(false);
|
||||
});
|
||||
|
||||
it('does not confuse a stale regular file at the socket path with a live socket', async () => {
|
||||
const paths = await fakeHealthPaths();
|
||||
await writeFile(paths.socketPath, 'not actually a socket');
|
||||
|
||||
expect(await isBrokerSupervisorHealthy(paths)).toBe(false);
|
||||
});
|
||||
});
|
||||
223
packages/mosaic/src/lease-broker/broker-supervisor.ts
Normal file
223
packages/mosaic/src/lease-broker/broker-supervisor.ts
Normal file
@@ -0,0 +1,223 @@
|
||||
/**
|
||||
* Activation-side supervisor for the Mosaic lease broker (issue #869, Point-1
|
||||
* C3). #828 shipped fail-closed enforcement hooks (`mutator-gate.py`,
|
||||
* `receipt-observer-client.py`) with nothing that guaranteed `daemon.py` was
|
||||
* running or that its socket existed before a gated runtime started. This
|
||||
* module:
|
||||
*
|
||||
* - resolves the broker socket/state paths and the on-disk locations of the
|
||||
* supervisor artifacts, deterministically and consistently with
|
||||
* `defaultLeaseBrokerSocket` in `../commands/launch.ts`;
|
||||
* - idempotently applies (materializes) a systemd `--user` unit plus the
|
||||
* wrapper script and daemon sources it execs, mirroring the tmux fleet
|
||||
* unit convention in `framework/systemd/user/`;
|
||||
* - exposes a health predicate other cards (e.g. the C1 activation probe)
|
||||
* can call to learn whether a broker supervisor is present and healthy.
|
||||
*
|
||||
* `applyBrokerSupervisor` only writes files under the paths it is given. It
|
||||
* never runs `systemctl`, never starts `daemon.py`, and never touches a real
|
||||
* host's `~/.config` unless the caller explicitly resolves paths there.
|
||||
* Enabling/starting the unit is a separate, later, out-of-scope step.
|
||||
*/
|
||||
import { chmod, copyFile, mkdir, stat } from 'node:fs/promises';
|
||||
import { homedir } from 'node:os';
|
||||
import { dirname, join } from 'node:path';
|
||||
|
||||
const UNIT_NAME = 'mosaic-lease-broker.service';
|
||||
const WRAPPER_SCRIPT_NAME = 'start-lease-broker.sh';
|
||||
|
||||
/** Co-located modules `daemon.py` imports at runtime; kept alongside it. */
|
||||
const DAEMON_SOURCE_FILE_NAMES = [
|
||||
'daemon.py',
|
||||
'lease_generation.py',
|
||||
'normative_fragments.py',
|
||||
'receipt_challenge.py',
|
||||
'receipt_observer.py',
|
||||
] as const;
|
||||
|
||||
export interface ResolveBrokerSupervisorPathsOptions {
|
||||
/** `~/.config/mosaic` (or an override) — where installed tool copies live. */
|
||||
mosaicHome: string;
|
||||
/** Root of the checked-out `framework/` directory (canonical file source). */
|
||||
frameworkRoot: string;
|
||||
/** Defaults to `process.env`; pass a fake for tests. */
|
||||
env?: NodeJS.ProcessEnv;
|
||||
/** Defaults to `os.homedir()`; pass a temp dir in tests. */
|
||||
homeDir?: string;
|
||||
/** Defaults to `process.getuid()` (or 0); pass a fake for tests. */
|
||||
uid?: number;
|
||||
}
|
||||
|
||||
export interface BrokerSupervisorPaths {
|
||||
readonly mosaicHome: string;
|
||||
readonly frameworkRoot: string;
|
||||
readonly systemdUserDir: string;
|
||||
readonly leaseBrokerToolsDir: string;
|
||||
readonly unitSourcePath: string;
|
||||
readonly unitTargetPath: string;
|
||||
readonly wrapperSourcePath: string;
|
||||
readonly wrapperTargetPath: string;
|
||||
readonly daemonSourcePaths: readonly string[];
|
||||
readonly daemonTargetPaths: readonly string[];
|
||||
/**
|
||||
* Resolved with the same precedence as `defaultLeaseBrokerSocket` in
|
||||
* `../commands/launch.ts`: an explicit `MOSAIC_LEASE_BROKER_SOCKET`, else
|
||||
* `$XDG_RUNTIME_DIR/mosaic-lease/broker.sock`, else
|
||||
* `/run/user/<uid>/mosaic-lease/broker.sock`.
|
||||
*/
|
||||
readonly socketPath: string;
|
||||
/** Colocated next to the socket, matching the broker's own generation-file convention. */
|
||||
readonly statePath: string;
|
||||
}
|
||||
|
||||
/**
|
||||
* Resolve the lease broker socket path alone, with the same precedence as
|
||||
* `defaultLeaseBrokerSocket` in `../commands/launch.ts`. Exported so callers
|
||||
* (and tests) can assert the two stay in agreement without importing the CLI
|
||||
* command module.
|
||||
*/
|
||||
export function resolveLeaseBrokerSocketPath(
|
||||
env: NodeJS.ProcessEnv = process.env,
|
||||
uid: number = typeof process.getuid === 'function' ? process.getuid() : 0,
|
||||
): string {
|
||||
const explicit = env['MOSAIC_LEASE_BROKER_SOCKET'];
|
||||
if (explicit) return explicit;
|
||||
const runtimeDir = env['XDG_RUNTIME_DIR'];
|
||||
if (runtimeDir) return join(runtimeDir, 'mosaic-lease', 'broker.sock');
|
||||
return join('/run/user', String(uid), 'mosaic-lease', 'broker.sock');
|
||||
}
|
||||
|
||||
/** Resolve every path the supervisor apply/health functions need, deterministically. */
|
||||
export function resolveBrokerSupervisorPaths(
|
||||
options: ResolveBrokerSupervisorPathsOptions,
|
||||
): BrokerSupervisorPaths {
|
||||
const { mosaicHome, frameworkRoot } = options;
|
||||
const env = options.env ?? process.env;
|
||||
const homeDir = options.homeDir ?? homedir();
|
||||
const systemdUserDir = join(homeDir, '.config', 'systemd', 'user');
|
||||
const leaseBrokerToolsDir = join(mosaicHome, 'tools', 'lease-broker');
|
||||
const frameworkLeaseBrokerDir = join(frameworkRoot, 'tools', 'lease-broker');
|
||||
const socketPath = resolveLeaseBrokerSocketPath(env, options.uid);
|
||||
const statePath = join(dirname(socketPath), 'state.json');
|
||||
|
||||
return {
|
||||
mosaicHome,
|
||||
frameworkRoot,
|
||||
systemdUserDir,
|
||||
leaseBrokerToolsDir,
|
||||
unitSourcePath: join(frameworkRoot, 'systemd', 'user', UNIT_NAME),
|
||||
unitTargetPath: join(systemdUserDir, UNIT_NAME),
|
||||
wrapperSourcePath: join(frameworkLeaseBrokerDir, WRAPPER_SCRIPT_NAME),
|
||||
wrapperTargetPath: join(leaseBrokerToolsDir, WRAPPER_SCRIPT_NAME),
|
||||
daemonSourcePaths: DAEMON_SOURCE_FILE_NAMES.map((name) => join(frameworkLeaseBrokerDir, name)),
|
||||
daemonTargetPaths: DAEMON_SOURCE_FILE_NAMES.map((name) => join(leaseBrokerToolsDir, name)),
|
||||
socketPath,
|
||||
statePath,
|
||||
};
|
||||
}
|
||||
|
||||
export interface ApplyBrokerSupervisorResult {
|
||||
readonly installedFiles: readonly string[];
|
||||
}
|
||||
|
||||
/**
|
||||
* Idempotently materialize the supervisor unit, its wrapper script, and the
|
||||
* daemon sources it execs. Safe to call on every reseed: every write is a
|
||||
* deterministic overwrite of the same target path from the same source, so a
|
||||
* second call reproduces identical bytes/modes and never errors.
|
||||
*
|
||||
* Never runs `systemctl`; the caller decides separately whether/when to
|
||||
* `daemon-reload`/`enable`/`start` the installed unit.
|
||||
*/
|
||||
export async function applyBrokerSupervisor(
|
||||
paths: BrokerSupervisorPaths,
|
||||
): Promise<ApplyBrokerSupervisorResult> {
|
||||
await mkdir(paths.leaseBrokerToolsDir, { recursive: true });
|
||||
await mkdir(paths.systemdUserDir, { recursive: true });
|
||||
|
||||
const installedFiles: string[] = [];
|
||||
|
||||
for (let index = 0; index < paths.daemonSourcePaths.length; index += 1) {
|
||||
const source = paths.daemonSourcePaths[index];
|
||||
const target = paths.daemonTargetPaths[index];
|
||||
if (source === undefined || target === undefined) continue;
|
||||
await copyFile(source, target);
|
||||
await chmod(target, 0o644);
|
||||
installedFiles.push(target);
|
||||
}
|
||||
|
||||
await copyFile(paths.wrapperSourcePath, paths.wrapperTargetPath);
|
||||
await chmod(paths.wrapperTargetPath, 0o755);
|
||||
installedFiles.push(paths.wrapperTargetPath);
|
||||
|
||||
await copyFile(paths.unitSourcePath, paths.unitTargetPath);
|
||||
await chmod(paths.unitTargetPath, 0o644);
|
||||
installedFiles.push(paths.unitTargetPath);
|
||||
|
||||
return { installedFiles };
|
||||
}
|
||||
|
||||
export interface BrokerSupervisorHealth {
|
||||
/** Whether the systemd unit file has been materialized at its target path. */
|
||||
readonly unitInstalled: boolean;
|
||||
/** Whether a Unix domain socket currently exists at the resolved socket path. */
|
||||
readonly socketPresent: boolean;
|
||||
/**
|
||||
* The signal other cards (e.g. C1's activation probe) should treat as
|
||||
* "a broker supervisor is present and healthy". Presence of a live socket
|
||||
* is the authoritative signal: a gated runtime can only ever succeed by
|
||||
* connecting to it, so this is what fail-closed callers must check.
|
||||
*/
|
||||
readonly healthy: boolean;
|
||||
}
|
||||
|
||||
/**
|
||||
* Report the supervisor's on-disk/health signals. Never throws for an
|
||||
* absent unit or socket — both simply report `false`; unexpected filesystem
|
||||
* errors (permission issues, etc.) still propagate.
|
||||
*/
|
||||
export async function checkBrokerSupervisorHealth(
|
||||
paths: Pick<BrokerSupervisorPaths, 'unitTargetPath' | 'socketPath'>,
|
||||
): Promise<BrokerSupervisorHealth> {
|
||||
const [unitInstalled, socketPresent] = await Promise.all([
|
||||
pathExists(paths.unitTargetPath),
|
||||
isUnixSocket(paths.socketPath),
|
||||
]);
|
||||
return { unitInstalled, socketPresent, healthy: socketPresent };
|
||||
}
|
||||
|
||||
/** Convenience boolean form of {@link checkBrokerSupervisorHealth} for simple call sites. */
|
||||
export async function isBrokerSupervisorHealthy(
|
||||
paths: Pick<BrokerSupervisorPaths, 'unitTargetPath' | 'socketPath'>,
|
||||
): Promise<boolean> {
|
||||
return (await checkBrokerSupervisorHealth(paths)).healthy;
|
||||
}
|
||||
|
||||
async function pathExists(path: string): Promise<boolean> {
|
||||
try {
|
||||
await stat(path);
|
||||
return true;
|
||||
} catch (error) {
|
||||
if (isEnoent(error)) return false;
|
||||
throw error;
|
||||
}
|
||||
}
|
||||
|
||||
async function isUnixSocket(path: string): Promise<boolean> {
|
||||
try {
|
||||
const info = await stat(path);
|
||||
return info.isSocket();
|
||||
} catch (error) {
|
||||
if (isEnoent(error)) return false;
|
||||
throw error;
|
||||
}
|
||||
}
|
||||
|
||||
function isEnoent(error: unknown): boolean {
|
||||
return (
|
||||
typeof error === 'object' &&
|
||||
error !== null &&
|
||||
'code' in error &&
|
||||
(error as NodeJS.ErrnoException).code === 'ENOENT'
|
||||
);
|
||||
}
|
||||
Reference in New Issue
Block a user