Compare commits

..

1 Commits

Author SHA1 Message Date
Jarvis
054551b677 ci: eliminate cold pnpm install via pre-baked CI base image (Phase 1)
Some checks failed
ci/woodpecker/push/ci Pipeline failed
ci/woodpecker/pr/ci Pipeline failed
Every pipeline ran a cold pnpm install (network fetch + musl native
rebuilds + apk add python3 make g++), median ~731s, paid twice per push.

Phase 1 (no cluster access, repo commits only):
- Dockerfile.ci: node:22-alpine + python3/make/g++/postgresql-client +
  pnpm@10.6.2 + pnpm fetch to warm the store and compile natives once.
- .woodpecker/ci-image.yml: kaniko build/push of ci-base:latest + a
  lockfile-hash tag, triggered only when pnpm-lock.yaml or Dockerfile.ci
  change. Reuses the publish.yml kaniko/auth pattern.
- ci.yml + publish.yml: install from the baked ci-base:latest, drop the
  per-run apk add, use pnpm install --frozen-lockfile --prefer-offline.
- Framework monorepo template: single cached install other steps depend
  on instead of re-running npm ci across 6 steps.

Node 22->24 bump is a separate follow-up PR. Phase 2 (RWX Longhorn PVC)
is out of scope. Expected install ~731s -> ~30-60s.

Refs #634

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-22 16:42:48 -05:00
14 changed files with 22 additions and 467 deletions

4
.npmrc
View File

@@ -1,5 +1 @@
@mosaicstack:registry=https://git.mosaicstack.dev/api/packages/mosaicstack/npm/ @mosaicstack:registry=https://git.mosaicstack.dev/api/packages/mosaicstack/npm/
# Pin the pnpm store to the same path the ci-base image warms (Dockerfile.ci),
# so the pipeline `pnpm install --prefer-offline` consumes the baked store
# instead of repopulating a fresh one.
store-dir=/root/.local/share/pnpm/store

View File

@@ -1,5 +1,5 @@
# &node_image is the pre-baked CI base built by .woodpecker/ci-image.yml: # &node_image is the pre-baked CI base built by .woodpecker/ci-image.yml:
# node:24-alpine + python3/make/g++/postgresql-client + pnpm + a warm pnpm # node:22-alpine + python3/make/g++/postgresql-client + pnpm + a warm pnpm
# store. The install step resolves from the baked store (--prefer-offline) # store. The install step resolves from the baked store (--prefer-offline)
# instead of paying a ~731s cold fetch + native compile every run. # instead of paying a ~731s cold fetch + native compile every run.
variables: variables:

View File

@@ -2,7 +2,7 @@
# Runs only on main branch push/tag # Runs only on main branch push/tag
variables: variables:
# Pre-baked CI base (see .woodpecker/ci-image.yml): node:24-alpine + # Pre-baked CI base (see .woodpecker/ci-image.yml): node:22-alpine +
# toolchain + warm pnpm store. Kills the second cold install publish pays. # toolchain + warm pnpm store. Kills the second cold install publish pays.
- &node_image 'git.mosaicstack.dev/mosaicstack/stack/ci-base:latest' - &node_image 'git.mosaicstack.dev/mosaicstack/stack/ci-base:latest'
- &enable_pnpm 'corepack enable' - &enable_pnpm 'corepack enable'

View File

@@ -2,30 +2,23 @@
# #
# Purpose: eliminate the cold `pnpm install` that dominates every pipeline # Purpose: eliminate the cold `pnpm install` that dominates every pipeline
# (~731s median). This image ships the native toolchain (no per-run `apk add`) # (~731s median). This image ships the native toolchain (no per-run `apk add`)
# AND a warm, content-addressable pnpm store with the dependency-tree tarballs # AND a warm, content-addressable pnpm store with the dependency tree already
# already fetched at build time. `pnpm fetch` only populates the store from the # fetched and its musl native modules (better-sqlite3, node-pty, sqlite3,
# lockfile — it does NOT run the native node-gyp builds (better-sqlite3, # canvas, sharp) compiled ONCE at build time. A pipeline `pnpm install
# node-pty, sqlite3, canvas, sharp); those still compile at `pnpm install`, # --frozen-lockfile --prefer-offline` then resolves from local hard-links in
# which is exactly why the musl toolchain stays baked into this image. A # tens of seconds.
# pipeline `pnpm install --frozen-lockfile --prefer-offline` then resolves
# tarballs from local hard-links (no network) and compiles natives against the
# already-present toolchain, in tens of seconds instead of ~731s.
# #
# Rebuilt only when `pnpm-lock.yaml` or this Dockerfile change # Rebuilt only when `pnpm-lock.yaml` or this Dockerfile change
# (see .woodpecker/ci-image.yml). # (see .woodpecker/ci-image.yml).
# #
# Node version is pinned to 24 (Active LTS). This is the follow-up bump from # Node version is intentionally pinned to 22 (Active LTS at time of writing).
# node:22 — sequenced AFTER the CI cache work landed so the runtime change # The node:22 -> node:24 bump lands as a SEPARATE follow-up PR so the cache
# carries zero cache variables. node:26 stays held until it reaches LTS # change carries zero runtime-version variables.
# (Oct 2026); the Current line risks native-module (node-gyp) breakage on a FROM node:22-alpine
# runner that compiles better-sqlite3 / canvas / sharp / node-pty from source.
FROM node:24-alpine
# Native toolchain required to compile node-gyp deps on musl, plus the # Native toolchain required to compile node-gyp deps on musl, plus the
# postgresql-client used by the test step's pg_isready readiness probe. `bash` # postgresql-client used by the test step's pg_isready readiness probe.
# is baked here too — the sanitization step in ci.yml otherwise does a per-run RUN apk add --no-cache python3 make g++ postgresql-client
# `apk add bash`.
RUN apk add --no-cache python3 make g++ postgresql-client bash
# Pin pnpm to the repo's packageManager version via corepack. # Pin pnpm to the repo's packageManager version via corepack.
RUN corepack enable && corepack prepare pnpm@10.6.2 --activate RUN corepack enable && corepack prepare pnpm@10.6.2 --activate
@@ -36,10 +29,8 @@ WORKDIR /app
ENV PNPM_HOME=/root/.local/share/pnpm ENV PNPM_HOME=/root/.local/share/pnpm
RUN pnpm config set store-dir /root/.local/share/pnpm/store RUN pnpm config set store-dir /root/.local/share/pnpm/store
# Warm the store. `pnpm fetch` populates the content-addressable store with the # Warm the store + compile native modules once. `pnpm fetch` populates the
# dependency tarballs directly from the lockfile (no package.json / workspace # content-addressable store directly from the lockfile (no package.json /
# needed), so a baked store stays valid until the lockfile changes. Note: # workspace needed), so a baked store stays valid until the lockfile changes.
# `fetch` does NOT compile native modules — that happens later at `pnpm install`
# in the pipeline, against the toolchain baked above.
COPY pnpm-lock.yaml ./ COPY pnpm-lock.yaml ./
RUN pnpm fetch --frozen-lockfile RUN pnpm fetch --frozen-lockfile

View File

@@ -86,7 +86,3 @@ Active workstream is **W1 — Federation v1**. Workers should:
## #631 — re-seed preserves user fleet data (CRITICAL) — fix/631-reseed-preserves-fleet-data ## #631 — re-seed preserves user fleet data (CRITICAL) — fix/631-reseed-preserves-fleet-data
- Status: implemented + tested. PRIMARY: install.sh PRESERVE_PATHS += fleet/\*.yaml + fleet/agents + fleet/run (glob-aware cp-fallback); TS parity. SECONDARY: refreshActiveFleetUnits propagates unit fixes to ~/.config/systemd/user on mosaic update. bash F6 + TS + unit tests green. Detail: scratchpads/631-reseed-preserves-fleet.md. - Status: implemented + tested. PRIMARY: install.sh PRESERVE_PATHS += fleet/\*.yaml + fleet/agents + fleet/run (glob-aware cp-fallback); TS parity. SECONDARY: refreshActiveFleetUnits propagates unit fixes to ~/.config/systemd/user on mosaic update. bash F6 + TS + unit tests green. Detail: scratchpads/631-reseed-preserves-fleet.md.
## #633 — comms-block emitter + FLEET-LAUNCH runbook — feat/633-comms-block-runbook
- Status: implemented + tested (TDD). `mosaic fleet comms-block <role> [--host]` wraps resolveCommsBlock → readFleetCommsBlock; fails loud (stderr + exit 1) on unknown role / missing roster instead of silent empty. docs/fleet/FLEET-LAUNCH.md runbook: worker path + orchestrator .env fold (MOSAIC_AGENT_COMMAND; line-41 [-z] short-circuits line-44 yolo hardcode) + 3 launch gotchas + #632 preserve note + North-Star 4-field arc (harness ✅/model ✅ roster-native today; yolo + command/channels = PATH B #636). 177 fleet+comms tests green (6 new resolveCommsBlock cases). PATH A of the A→B→webUI arc. Detail: scratchpads/633-comms-block-runbook.md.

View File

@@ -1,114 +0,0 @@
# Fleet Launch Runbook
How every Mosaic fleet agent — workers **and** the orchestrator — is launched, and how to
configure each one. The guiding principle: **one roster-driven launcher**. There is no bespoke
per-agent launch script; the roster plus per-agent `.env` files are the single source of launch
config.
## The launch chain
| Layer | File | Responsibility |
| ---------------- | ------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------- |
| systemd unit | `mosaic-agent@<role>.service` | One templated unit per role; `ExecStart` runs the session launcher with the instance name `%i`. Defaults `MOSAIC_AGENT_RUNTIME=pi`, `MOSAIC_AGENT_NAME=%i`. |
| session launcher | `tools/fleet/start-agent-session.sh <role>` | Builds the launch command, opens the tmux pane, wires the heartbeat. |
| launch command | `mosaic yolo <runtime>` (or a per-agent override) | Replaces the pane's foreground process with the runtime, fully seeded. |
| seeding | `mosaic`'s `composeContract()` | Injects the Constitution/USER/TOOLS/runtime contract, `*.local` overlays, **and** the Fleet-Comms cheat-sheet — all via `--append-system-prompt`. |
Per-agent overrides live in `fleet/agents/<role>.env`, generated from `roster.yaml` by
`generateAgentEnv` (`packages/mosaic/src/commands/fleet.ts`) and consumed by the launcher.
## Worker launch path (default)
1. `roster.yaml` carries each agent's `runtime` and optional `model_hint`.
2. `generateAgentEnv` emits `fleet/agents/<role>.env` with `MOSAIC_AGENT_NAME`,
`MOSAIC_AGENT_RUNTIME`, and `MOSAIC_AGENT_MODEL`.
3. `start-agent-session.sh` has no `MOSAIC_AGENT_COMMAND` set, so it falls through to the default
(line ~44):
```sh
MOSAIC_AGENT_COMMAND="mosaic yolo $MOSAIC_AGENT_RUNTIME${MOSAIC_AGENT_MODEL:+ --model $MOSAIC_AGENT_MODEL}"
```
4. The launcher bakes `MOSAIC_AGENT_NAME` into the pane command (line ~118), so `composeContract`
can inject the Fleet-Comms cheat-sheet for that role.
That is the whole worker path: roster → `.env` → `mosaic yolo <runtime>` → seeded pane.
## Orchestrator fold (PATH A — ships today)
The orchestrator is **just another roster agent** launched through the canonical path — not a
snowflake script.
| Piece | Value |
| ------------------ | ----------------------------------- |
| host-side launcher | `orchestrator-launch.sh` |
| systemd unit | `mosaic-fleet-orchestrator.service` |
| tmux session | `orchestrator` (role-named) |
Set its launch command via `fleet/agents/orchestrator.env`:
```sh
MOSAIC_AGENT_COMMAND='mosaic yolo claude --channels plugin:discord@<channel>'
```
When `MOSAIC_AGENT_COMMAND` is set, `start-agent-session.sh`'s `if [ -z "$MOSAIC_AGENT_COMMAND" ]`
guard (line ~41) is false, so the line-44 default — **including its hardcoded `yolo`** — is skipped
entirely. The override fully controls the runtime and flags. Routing through `mosaic yolo claude`
(rather than a raw `claude` invocation) is what gives the orchestrator the same full
`composeContract` seeding + Fleet-Comms cheat-sheet as every worker, with `--channels` and any
other flags passed straight through to the `claude` binary.
## Launch gotchas
1. **Flag conflict.** `mosaic yolo claude` already injects `--dangerously-skip-permissions`. Do
**not** also pass `--permission-mode bypassPermissions` — the `claude` binary would receive both.
Use `mosaic yolo claude …` alone (yolo covers the unattended posture), **or** non-yolo
`mosaic claude --permission-mode bypassPermissions …`. Never mix the two.
2. **`MOSAIC_AGENT_NAME` must reach the pane.** The launcher bakes it from the instance name, and
`composeContract` gates the Fleet-Comms block on it (`launch.ts`, in `composeContract`) — **and**
the role must be a member of `roster.yaml`, or the block resolves empty.
3. **`launchRuntime` guards.** `mosaic yolo claude` runs `checkSoul` / `checkRuntime` /
`checkSequentialThinking`. The host needs `SOUL.md` and the sequential-thinking MCP, or the
launch aborts (a raw `claude` invocation skipped these checks). Dry-run the composed command in a
throwaway tmux session before swapping a live launcher.
## Why per-agent `.env` survives upgrades (#632)
`install.sh` `PRESERVE_PATHS` includes `fleet/*.yaml`, `fleet/agents`, and `fleet/run`, so
`mosaic update`'s framework re-seed **preserves** your roster and per-agent `.env` overrides
(glob-aware `cp` fallback; matching TS parity in `file-adapter.ts`). Before #632, an auto re-seed
could wipe them — which is exactly why PATH A's `.env` override is safe to rely on now.
## Inspecting the comms wiring
- `mosaic fleet comms-block <role>` prints the Fleet-Comms cheat-sheet a given role receives at
launch — its `[host:session]` identity, the exact `agent-send.sh` command for each peer, and the
FLIP / `--verify` conventions. `--host <h>` previews a cross-host view. An unknown role or missing
roster **fails loud** (stderr + non-zero exit), so a typo is never a silent no-op.
- Versus `mosaic compose-contract <runtime>`: that emits the **whole** system prompt and reads the
role from `MOSAIC_AGENT_NAME` (a full-prompt smoke test). `comms-block` is the targeted,
explicit-arg, comms-only view — e.g. `mosaic fleet comms-block coder0-0` to preview a peer.
## North Star / future direction
**Vision:** a webUI lets the user edit each agent's launch config — switch **harness**
(claude / pi / codex / opencode), toggle **yolo**, pick a **model**, set a **command/channels**
override — with no terminal.
**Continuity — this is not a new launch path.** It is a data-model + UI-binding layer over the
existing roster-driven launcher. Field-by-field status today:
| Launch-config field | Roster-native today? | Mechanism / gap |
| ------------------------ | -------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **harness** (`runtime`) | ✅ end-to-end | `roster.runtime` → `generateAgentEnv` emits `MOSAIC_AGENT_RUNTIME` → launcher line 44. UI just writes the field. |
| **model** (`model_hint`) | ✅ end-to-end | `roster.model_hint` → `MOSAIC_AGENT_MODEL` → launcher line 44 `--model`. UI just writes the field. |
| **yolo** | ❌ new | Launcher line 44 **hardcodes** `mosaic yolo`. A non-yolo toggle needs a roster `yolo` field → emit `MOSAIC_AGENT_YOLO` → make line 44 conditional. |
| **command / channels** | ❌ new | `MOSAIC_AGENT_COMMAND` is **consumed** (launcher line ~12) but `generateAgentEnv` does not emit it. Needs a roster `command`/`channels` field → emitted. |
**The arc:**
- **A** — `.env` `MOSAIC_AGENT_COMMAND` hatch: manual, ships now, kept safe across upgrades by #632.
- **B** — roster-native launch-config: harness + model are already there; add the **yolo** toggle
(line-44 conditional) and **command/channels** emission to complete the data model.
- **webUI** — binds dropdowns/toggles directly to those four roster fields.
PATH A's `.env` override is the **manual form** of exactly what PATH B makes roster-native and the
webUI edits — one continuous arc, not three separate features. PATH B is tracked as #636.

View File

@@ -1,54 +0,0 @@
# #633 — comms-block emitter + FLEET-LAUNCH runbook
Branch: `feat/633-comms-block-runbook` (off `bf2a6745`, post-#632 merge)
Issue: #633 · Follow-up filed: #636 (PATH B)
## Goal
PATH A of the orchestrator-launch fix: give every launch path the Fleet-Comms onboarding, and
document the canonical roster-driven launcher so the orchestrator stops being a bespoke snowflake.
## Deliverables
1. **`mosaic fleet comms-block <role> [--host <h>]`** — explicit-arg, comms-block-only emitter.
- Backed by new `resolveCommsBlock(mosaicHome, role, fleetHost?)` in `fleet/comms-onboarding.ts`
returning `{ ok, output, error }`.
- Unlike `readFleetCommsBlock` (returns `''` on any miss so `composeContract` can no-op silently
during launch), the emitter **fails loud**: unknown role / missing roster → `ok:false` → CLI
prints to stderr + sets `process.exitCode = 1`. A typo is never a silent no-op.
- Distinct from `mosaic compose-contract <runtime>` (whole prompt, env-coupled via
`MOSAIC_AGENT_NAME`); comms-block is the targeted, explicit-arg, comms-only view.
2. **`docs/fleet/FLEET-LAUNCH.md`** — worker path + orchestrator `.env` fold + 3 launch gotchas +
#632 preserve note + North-Star 4-field arc.
## Key findings (drove the design)
- `mosaic yolo claude` **already** forwards `--channels`/`--permission-mode` to the binary
(`launch.ts` claude case `cliArgs.push(...args)`) AND injects the comms block via
`composeContract``readFleetCommsBlock(home, env.MOSAIC_AGENT_NAME)`. So no `launch.ts` change
was needed — PATH A is `.env` + doc only.
- `start-agent-session.sh` line ~41 `[ -z "$MOSAIC_AGENT_COMMAND" ]` short-circuits the line-44
default, so an `.env` `MOSAIC_AGENT_COMMAND` override bypasses the hardcoded `yolo` entirely — the
yolo-conditional is therefore a PATH B (default-path) concern, not PATH A.
- `generateAgentEnv` (`fleet.ts` ~202-207) emits NAME/RUNTIME/MODEL but **not** `MOSAIC_AGENT_COMMAND`
— the seam PATH B (#636) closes.
## A → B → webUI arc (North Star)
- A = `.env` `MOSAIC_AGENT_COMMAND` hatch (manual, ships now, #632-safe).
- B (#636) = roster-native launch-config: harness ✅ + model ✅ already there; add **yolo** (line-44
conditional `MOSAIC_AGENT_YOLO`) + **command/channels** (`generateAgentEnv` emission).
- webUI binds dropdowns/toggles to those four roster fields. One launcher, no new launch path.
## Results
- TDD: spec first (`comms-onboarding.spec.ts`, 6 new `resolveCommsBlock` cases) → red → implement → green.
- `fleet.spec.ts` subcommand-list assertion extended with `comms-block`.
- 177 fleet+comms tests green; typecheck clean; eslint clean; prettier clean.
## Risks / notes
- Pre-existing local-only failure `uninstall.spec.ts > removeFramework > handles missing mosaicHome
gracefully` (EACCES on `/nonexistent` as non-root) — unrelated to #633, passes in CI as root.
- Did NOT run `mosaic update` / anything auto-reseed: installed CLI still 0.0.40 (roster-wipe live
until mos-claude-0 ships 0.0.41). All work is in-repo + vitest, never touches the live mosaic home.

View File

@@ -12,10 +12,6 @@
# ambiguity about lanes or origin. Recipients replying should FLIP the # ambiguity about lanes or origin. Recipients replying should FLIP the
# preamble: [<dst> -> <src>] ... (this tool sends; it does not auto-reply). # preamble: [<dst> -> <src>] ... (this tool sends; it does not auto-reply).
# #
# Optionally tags the message with a TRIAGE CLASS (see -C / --class) so a
# comms daemon can route it (deliver-to-agent vs log-and-drop) from an exact
# field instead of re-deriving intent from the body.
#
# WHY A WRAPPER # WHY A WRAPPER
# Reliable submission into an interactive REPL (Claude Code / Codex) is fiddly: # Reliable submission into an interactive REPL (Claude Code / Codex) is fiddly:
# a trailing Enter is often swallowed and the message sits as an unsubmitted # a trailing Enter is often swallowed and the message sits as an unsubmitted
@@ -30,7 +26,6 @@
# agent-send.sh [-L socket] -s <dst_session> -m "message" # local target # 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 -s <dst_session> -m "message" # remote target
# agent-send.sh [-L socket] -H user@host -n <dst_hostname> -s <sess> -f msg.txt # agent-send.sh [-L socket] -H user@host -n <dst_hostname> -s <sess> -f msg.txt
# agent-send.sh -s mos-claude --class terminal-log -m "ACK — received"
# echo "msg" | agent-send.sh [-L socket] -H user@host -s <dst_session> # echo "msg" | agent-send.sh [-L socket] -H user@host -s <dst_session>
# #
# OPTIONS # OPTIONS
@@ -41,61 +36,27 @@
# Default: local hostname, or (remote) resolved via one ssh. # Default: local hostname, or (remote) resolved via one ssh.
# -m MESSAGE message text (single- or multi-line) # -m MESSAGE message text (single- or multi-line)
# -f FILE read message from FILE instead of -m # -f FILE read message from FILE instead of -m
# -C CLASS triage class for a comms daemon. One of:
# terminal-log log-only; never needs the agent's attention
# actionable carries a decision/blocker/gate — deliver
# human from a human operator — deliver
# reaction an emoji/ack reaction
# Long form: --class CLASS (or --class=CLASS). When SET, the
# preamble carries a ` class=<CLASS>` token INSIDE the bracket:
# [<src> -> <dst> class=terminal-log] <message>
# When OMITTED, NO token is emitted and the preamble is
# byte-for-byte identical to the classic format. Consumers MUST
# treat an absent class as 'actionable' (fail-safe: agent sees it).
# -S SRC_LABEL override source label "<host>:<session>" (default: auto) # -S SRC_LABEL override source label "<host>:<session>" (default: auto)
# -r N Enter-flush attempts passed through (default 2) # -r N Enter-flush attempts passed through (default 2)
# -v verbose: print pane tail after delivery # -v verbose: print pane tail after delivery
# -h help # -h help
# #
# PREAMBLE GRAMMAR (for consumers / daemons mirroring this producer)
# ^\[(\S+) -> (\S+?)(?: class=(terminal-log|actionable|human|reaction))?\] (.*)$
# group 1 = src label group 2 = dst host:session
# group 3 = class (absent => actionable) group 4 = message body
#
# EXIT CODES (passed through from send-message.sh) # EXIT CODES (passed through from send-message.sh)
# 0 delivered/queued · 1 target not found · 2 still draft · 3 usage error # 0 delivered/queued · 1 target not found · 2 still draft · 3 usage error
set -uo pipefail set -uo pipefail
SELF_DIR=$(cd -- "$(dirname -- "$0")" && pwd) SELF_DIR=$(cd -- "$(dirname -- "$0")" && pwd)
# Sender is overridable via env purely for testing (inject a capture stub). The SENDER="$SELF_DIR/send-message.sh"
# default is the canonical send-message.sh beside this script; production callers
# never set AGENT_SEND_SENDER, so behavior is unchanged.
SENDER="${AGENT_SEND_SENDER:-$SELF_DIR/send-message.sh}"
# Translate the long option --class[=value] into "-C value" so getopts (which is
# short-option-only) can parse it. Every other argument passes through untouched,
# so callers that never use --class hit the exact original getopts path.
args=()
while [ $# -gt 0 ]; do
case "$1" in
--class) [ $# -ge 2 ] || { echo "ERROR: --class requires a value" >&2; exit 3; }
args+=(-C "$2"); shift 2 ;;
--class=*) args+=(-C "${1#*=}"); shift ;;
*) args+=("$1"); shift ;;
esac
done
set -- ${args[@]+"${args[@]}"}
DST_SESSION=""; SSH_TARGET=""; DST_HOST=""; MSG=""; FILE=""; SOCKET_NAME="" DST_SESSION=""; SSH_TARGET=""; DST_HOST=""; MSG=""; FILE=""; SOCKET_NAME=""
SRC_LABEL=""; RETRIES=2; VERBOSE=0; CLASS="" SRC_LABEL=""; RETRIES=2; VERBOSE=0
usage() { sed -n '2,/^set -uo pipefail/{/^set -uo pipefail/d;p}' "$0"; exit "${1:-3}"; } usage() { sed -n '2,44p' "$0"; exit "${1:-3}"; }
while getopts "L:s:H:n:m:f:S:r:C:vh" o; do while getopts "L:s:H:n:m:f:S:r:vh" o; do
case "$o" in case "$o" in
L) SOCKET_NAME=$OPTARG ;; L) SOCKET_NAME=$OPTARG ;;
s) DST_SESSION=$OPTARG ;; H) SSH_TARGET=$OPTARG ;; n) DST_HOST=$OPTARG ;; s) DST_SESSION=$OPTARG ;; H) SSH_TARGET=$OPTARG ;; n) DST_HOST=$OPTARG ;;
m) MSG=$OPTARG ;; f) FILE=$OPTARG ;; S) SRC_LABEL=$OPTARG ;; m) MSG=$OPTARG ;; f) FILE=$OPTARG ;; S) SRC_LABEL=$OPTARG ;;
C) CLASS=$OPTARG ;;
r) RETRIES=$OPTARG ;; v) VERBOSE=1 ;; h) usage 0 ;; *) usage 3 ;; r) RETRIES=$OPTARG ;; v) VERBOSE=1 ;; h) usage 0 ;; *) usage 3 ;;
esac esac
done done
@@ -103,17 +64,6 @@ done
[ -n "$DST_SESSION" ] || { echo "ERROR: -s DST_SESSION is required" >&2; usage 3; } [ -n "$DST_SESSION" ] || { echo "ERROR: -s DST_SESSION is required" >&2; usage 3; }
[ -x "$SENDER" ] || { echo "ERROR: send-message.sh not found beside this script" >&2; exit 3; } [ -x "$SENDER" ] || { echo "ERROR: send-message.sh not found beside this script" >&2; exit 3; }
# Validate the triage class only when one was given. An absent class emits NO
# token (preamble byte-identical to the classic format); the consumer defaults
# absent => actionable.
CLASS_TOKEN=""
if [ -n "$CLASS" ]; then
case "$CLASS" in
terminal-log|actionable|human|reaction) CLASS_TOKEN=" class=${CLASS}" ;;
*) echo "ERROR: invalid --class '$CLASS' (allowed: terminal-log, actionable, human, reaction)" >&2; exit 3 ;;
esac
fi
# Message body from -f / -m / stdin. # Message body from -f / -m / stdin.
if [ -n "$FILE" ]; then [ -r "$FILE" ] || { echo "ERROR: cannot read $FILE" >&2; exit 3; }; MSG=$(cat -- "$FILE") if [ -n "$FILE" ]; then [ -r "$FILE" ] || { echo "ERROR: cannot read $FILE" >&2; exit 3; }; MSG=$(cat -- "$FILE")
elif [ -z "$MSG" ] && [ ! -t 0 ]; then MSG=$(cat) elif [ -z "$MSG" ] && [ ! -t 0 ]; then MSG=$(cat)
@@ -140,7 +90,7 @@ if [ -z "$DST_HOST" ]; then
fi fi
fi fi
PREAMBLE="[${SRC_LABEL} -> ${DST_HOST}:${DST_SESSION}${CLASS_TOKEN}]" PREAMBLE="[${SRC_LABEL} -> ${DST_HOST}:${DST_SESSION}]"
FULL="${PREAMBLE} ${MSG}" FULL="${PREAMBLE} ${MSG}"
B64=$(printf '%s' "$FULL" | base64 -w0) B64=$(printf '%s' "$FULL" | base64 -w0)

View File

@@ -1,97 +0,0 @@
#!/usr/bin/env bash
# agent-send.test.sh — regression + grammar lock for agent-send.sh --class.
#
# Strategy: inject a capture stub via AGENT_SEND_SENDER that decodes the -b
# base64 payload and prints the FULL message (preamble + body) so we can assert
# the exact bytes on the wire. Local path only (no ssh), -n pins the dst host so
# the preamble is deterministic across machines.
#
# Guarantees locked here:
# 1. REGRESSION BAR — no --class => preamble byte-for-byte identical to classic.
# 2. --class <c> => ` class=<c>` token emitted inside the bracket.
# 3. --class=<c> (equals form) parses identically to the space form.
# 4. -C <c> short form parses identically.
# 5. invalid class => exit 3, nothing sent.
# 6. --class with no value => exit 3.
# 7. the documented consumer regex parses producer output for every class.
set -uo pipefail
HERE=$(cd -- "$(dirname -- "$0")" && pwd)
TOOL="$HERE/agent-send.sh"
# Capture stub: stands in for send-message.sh. Decodes -b and prints the payload.
STUB=$(mktemp)
trap 'rm -f "$STUB"' EXIT
cat >"$STUB" <<'STUB_EOF'
#!/usr/bin/env bash
set -uo pipefail
b64=""
while getopts "t:b:r:v" o; do case "$o" in b) b64=$OPTARG ;; *) : ;; esac; done
printf '%s' "$b64" | base64 -d
STUB_EOF
chmod +x "$STUB"
PASS=0; FAIL=0
ok() { PASS=$((PASS+1)); printf 'ok %s\n' "$1"; }
no() { FAIL=$((FAIL+1)); printf 'FAIL %s\n %s\n' "$1" "$2"; }
# Run the tool with the stub injected; echoes captured payload on stdout.
run() { AGENT_SEND_SENDER="$STUB" bash "$TOOL" -S a:src -n dsthost "$@"; }
# Documented consumer grammar — the daemon will mirror exactly this.
GRAMMAR='^\[(\S+) -> (\S+) class=(terminal-log|actionable|human|reaction)\] (.*)$'
GRAMMAR_NOCLASS='^\[(\S+) -> (\S+)\] (.*)$'
# 1. REGRESSION BAR: classic preamble, byte-for-byte.
got=$(run -s mos -m "hello world")
want='[a:src -> dsthost:mos] hello world'
[ "$got" = "$want" ] && ok "regression: no --class is byte-identical" \
|| no "regression: no --class is byte-identical" "got=[$got] want=[$want]"
# 2. --class space form emits the token.
got=$(run -s mos --class terminal-log -m "ACK")
want='[a:src -> dsthost:mos class=terminal-log] ACK'
[ "$got" = "$want" ] && ok "--class terminal-log emits token" \
|| no "--class terminal-log emits token" "got=[$got] want=[$want]"
# 3. --class=value equals form.
got=$(run -s mos --class=actionable -m "decide X")
want='[a:src -> dsthost:mos class=actionable] decide X'
[ "$got" = "$want" ] && ok "--class=actionable (equals form)" \
|| no "--class=actionable (equals form)" "got=[$got] want=[$want]"
# 4. -C short form.
got=$(run -s mos -C human -m "from a person")
want='[a:src -> dsthost:mos class=human] from a person'
[ "$got" = "$want" ] && ok "-C human (short form)" \
|| no "-C human (short form)" "got=[$got] want=[$want]"
# 5. invalid class => exit 3, no send.
if out=$(run -s mos --class bogus -m "x" 2>/dev/null); then
no "invalid class rejected" "expected non-zero exit, got 0 (out=[$out])"
else
rc=$?
[ "$rc" = 3 ] && [ -z "$out" ] && ok "invalid class => exit 3, nothing sent" \
|| no "invalid class => exit 3, nothing sent" "rc=$rc out=[$out]"
fi
# 6. --class with no value => exit 3.
if run -s mos -m "x" --class 2>/dev/null; then
no "--class with no value rejected" "expected non-zero exit, got 0"
else
[ "$?" = 3 ] && ok "--class with no value => exit 3" || no "--class with no value => exit 3" "wrong rc"
fi
# 7. consumer grammar parses every class + classic line.
for c in terminal-log actionable human reaction; do
line=$(run -s mos --class "$c" -m "body $c")
[[ "$line" =~ $GRAMMAR ]] && [ "${BASH_REMATCH[3]}" = "$c" ] && [ "${BASH_REMATCH[4]}" = "body $c" ] \
&& ok "grammar parses class=$c" || no "grammar parses class=$c" "line=[$line]"
done
classic=$(run -s mos -m "plain body")
[[ "$classic" =~ $GRAMMAR_NOCLASS ]] && [ "${BASH_REMATCH[3]}" = "plain body" ] \
&& ok "grammar (no-class) parses classic line" || no "grammar (no-class) parses classic line" "line=[$classic]"
echo "---"
echo "PASS=$PASS FAIL=$FAIL"
[ "$FAIL" -eq 0 ]

View File

@@ -1,6 +1,6 @@
{ {
"name": "@mosaicstack/mosaic", "name": "@mosaicstack/mosaic",
"version": "0.0.41", "version": "0.0.40",
"repository": { "repository": {
"type": "git", "type": "git",
"url": "https://git.mosaicstack.dev/mosaicstack/stack.git", "url": "https://git.mosaicstack.dev/mosaicstack/stack.git",

View File

@@ -95,7 +95,6 @@ describe('registerFleetCommand', () => {
expect(agent).toBeDefined(); expect(agent).toBeDefined();
expect(agent!.options.map((option) => option.long)).toContain('--list'); expect(agent!.options.map((option) => option.long)).toContain('--list');
expect(agent!.commands.map((command) => command.name()).sort()).toEqual([ expect(agent!.commands.map((command) => command.name()).sort()).toEqual([
'comms-block',
'reset', 'reset',
'roster', 'roster',
'send', 'send',

View File

@@ -7,7 +7,6 @@ import { spawn } from 'node:child_process';
import * as readline from 'node:readline'; import * as readline from 'node:readline';
import type { Command } from 'commander'; import type { Command } from 'commander';
import YAML from 'yaml'; import YAML from 'yaml';
import { resolveCommsBlock } from '../fleet/comms-onboarding.js';
/** /**
* A function that spawns a command with inherited stdio (TTY passthrough). * A function that spawns a command with inherited stdio (TTY passthrough).
@@ -1360,23 +1359,6 @@ export function registerFleetAgentCommands(
} }
}); });
agentCommand
.command('comms-block <role>')
.description(
"Print the Fleet Comms cheat-sheet for a roster role (preview a peer's peer-reach view)",
)
.option('--host <host>', 'Override the fleet host (preview a cross-host peer view)')
.action((role: string, opts: { host?: string }) => {
const mosaicHome = resolveMosaicHomeFromCommand(agentCommand, deps.mosaicHome);
const res = resolveCommsBlock(mosaicHome, role, opts.host);
if (!res.ok) {
console.error(`[mosaic] comms-block: ${res.error}`);
process.exitCode = 1;
return;
}
console.log(res.output);
});
agentCommand agentCommand
.command('status [agent]') .command('status [agent]')
.description('Show tmux status for the local fleet or one agent') .description('Show tmux status for the local fleet or one agent')

View File

@@ -7,7 +7,6 @@ import {
buildFleetCommsBlock, buildFleetCommsBlock,
renderPeerReach, renderPeerReach,
readFleetCommsBlock, readFleetCommsBlock,
resolveCommsBlock,
type CommsPeer, type CommsPeer,
} from './comms-onboarding.js'; } from './comms-onboarding.js';
@@ -186,53 +185,3 @@ describe('readFleetCommsBlock — situational (the context a spawned agent gets)
expect(readFleetCommsBlock(mkdtempSync(join(tmpdir(), 'noroster-')), 'orchestrator')).toBe(''); expect(readFleetCommsBlock(mkdtempSync(join(tmpdir(), 'noroster-')), 'orchestrator')).toBe('');
}); });
}); });
describe('resolveCommsBlock — `mosaic fleet comms-block <role>` emitter semantics', () => {
// The emitter wraps readFleetCommsBlock but must NEVER print an empty string silently:
// an unknown role / missing roster has to fail loud (caller maps !ok → stderr + exit 1)
// so `mosaic fleet comms-block bogus` is a visible error, not a confusing no-op. The
// success path returns the block verbatim for `mosaic fleet comms-block <peer>` previews.
let home: string;
beforeEach(() => {
home = mkdtempSync(join(tmpdir(), 'mosaic-commsblk-'));
mkdirSync(join(home, 'fleet'), { recursive: true });
writeFileSync(join(home, 'fleet', 'roster.yaml'), ROSTER);
});
afterEach(() => rmSync(home, { recursive: true, force: true }));
it('returns ok + the cheat-sheet for a roster member', () => {
const res = resolveCommsBlock(home, 'orchestrator', 'w-jarvis');
expect(res.ok).toBe(true);
expect(res.output).toContain('# Fleet Comms');
expect(res.output).toContain('| enhancer |');
expect(res.error).toBeUndefined();
});
it('fails loud (not ok + error naming the role) for a non-member — never silently empty', () => {
const res = resolveCommsBlock(home, 'stranger', 'w-jarvis');
expect(res.ok).toBe(false);
expect(res.output).toBe('');
expect(res.error).toContain('stranger');
});
it('fails loud when no roster exists at the mosaic home', () => {
const noRoster = mkdtempSync(join(tmpdir(), 'mosaic-noroster-'));
const res = resolveCommsBlock(noRoster, 'orchestrator', 'w-jarvis');
expect(res.ok).toBe(false);
expect(res.error).toBeTruthy();
rmSync(noRoster, { recursive: true, force: true });
});
it('fails loud for a missing role argument', () => {
const res = resolveCommsBlock(home, undefined, 'w-jarvis');
expect(res.ok).toBe(false);
expect(res.error).toBeTruthy();
});
it('honors a host override so a peer can preview its own cross-host view', () => {
// coder0-0 viewing with its own host → its self-identity line uses that host.
const res = resolveCommsBlock(home, 'coder0-0', '10.1.10.37');
expect(res.ok).toBe(true);
expect(res.output).toContain('`[10.1.10.37:coder0-0]`');
});
});

View File

@@ -179,48 +179,5 @@ export function readFleetCommsBlock(
}); });
} }
/** Result of resolving a comms-block emit request — see `mosaic fleet comms-block`. */
export interface CommsBlockResult {
/** True when a cheat-sheet was produced; false maps to stderr + non-zero exit. */
ok: boolean;
/** The Fleet-Comms cheat-sheet (empty unless ok). */
output: string;
/** Operator-facing reason when !ok. */
error?: string;
}
/**
* Resolve the Fleet-Comms cheat-sheet for an explicit <role>, backing the
* `mosaic fleet comms-block <role>` command. Unlike readFleetCommsBlock — which
* returns '' on any miss so composeContract can no-op silently during a launch —
* this NEVER silently emits empty: an unknown role or missing roster yields
* ok:false + an operator-facing reason, so the CLI surfaces it (stderr + exit 1)
* rather than printing nothing. That makes it safe to preview any peer's view,
* e.g. `mosaic fleet comms-block coder0-0`.
*/
export function resolveCommsBlock(
mosaicHome: string,
role: string | undefined,
fleetHost?: string,
): CommsBlockResult {
if (!role) {
return { ok: false, output: '', error: 'comms-block requires a <role> argument' };
}
const block = fleetHost
? readFleetCommsBlock(mosaicHome, role, fleetHost)
: readFleetCommsBlock(mosaicHome, role);
if (!block) {
const rosterPath = join(mosaicHome, 'fleet', 'roster.yaml');
return {
ok: false,
output: '',
error: existsSync(rosterPath)
? `role "${role}" is not a member of the fleet roster at ${rosterPath}`
: `no fleet roster at ${rosterPath}`,
};
}
return { ok: true, output: block };
}
/** Default mosaic home (mirrors launch.ts), for callers that don't pass one. */ /** Default mosaic home (mirrors launch.ts), for callers that don't pass one. */
export const DEFAULT_MOSAIC_HOME_FOR_COMMS = join(homedir(), '.config', 'mosaic'); export const DEFAULT_MOSAIC_HOME_FOR_COMMS = join(homedir(), '.config', 'mosaic');