Compare commits

..

1 Commits

Author SHA1 Message Date
0d310c083e fix(install): preserve user fleet data on re-seed + refresh active units (#631)
Some checks failed
ci/woodpecker/push/ci Pipeline was successful
ci/woodpecker/pr/ci Pipeline was canceled
CRITICAL data-loss in the routine update path. `mosaic update` auto-runs
install.sh keep-mode sync (#610); the rsync --delete honored PRESERVE_PATHS but
fleet/ was not listed, so the sync WIPED ~/.config/mosaic/fleet/roster.yaml (and
fleet/run, fleet/agents). Any user running `mosaic update` lost their fleet.

PRIMARY (data-loss):
- install.sh PRESERVE_PATHS += fleet/*.yaml, fleet/agents, fleet/run. The
  framework still SEEDS fleet/examples + fleet/roles + fleet/roster.schema.json
  (synced); the operator's roster, custom rosters, per-agent env, and heartbeat
  run dir are preserved.
- Made the cp (no-rsync) fallback GLOB-AWARE so fleet/*.yaml is preserved there
  too; fixed the restore to re-glob per pattern (restores only the user file,
  not the freshly-synced fleet/ dir).
- file-adapter.ts (TS installer): mirrored the preserve list for dual-installer
  parity. (syncDirectory is copy-only — never --delete — so it never had the
  bug; this is parity + belt-and-suspenders.)

SECONDARY (stale active units):
- refreshActiveFleetUnits(): the re-seed updates ~/.config/mosaic/systemd/user
  but systemd runs ~/.config/systemd/user, so shipped unit fixes (#627) did not
  take effect after update. `mosaic update` now copies the fresh mosaic-*.service
  → the active dir + daemon-reload (best-effort, only when a fleet is installed).

Verified: bash F6 fixture (roster/custom-yaml/agents/run survive + examples
refreshed + schema seeded), 20/20 migration matrix; TS file-adapter keep-mode
test; 2 refreshActiveFleetUnits unit tests. tsc/eslint/prettier/sanitize clean.

Refs #631

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EsgTQzV5YUGk1JtCLP4B83
2026-06-22 15:29:37 -05:00
60 changed files with 187 additions and 2211 deletions

7
.gitignore vendored
View File

@@ -15,10 +15,3 @@ infra/step-ca/dev-password
# Scratch dirs created by the framework git-wrapper shell test harnesses
.mosaic-test-work/
# Transient config files vite/vitest/esbuild write next to a *.config.ts while
# loading it, then unlink. They are untracked but were not ignored, so turbo's
# package traversal hashed them and intermittently failed CI with "Package
# traversal error: ... .timestamp-*.mjs: No such file or directory" when the
# file vanished mid-scan. Ignoring them removes the race.
*.timestamp-*.mjs

4
.npmrc
View File

@@ -1,5 +1 @@
@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

@@ -1,40 +0,0 @@
# Build & push the pre-baked CI base image (Dockerfile.ci) to the Gitea
# registry CI already publishes to. Reuses the exact kaniko + auth pattern
# from publish.yml (REGISTRY_USER/REGISTRY_PASS from_secret, /kaniko/.docker
# config.json). Other pipelines (ci.yml, publish.yml) pull `ci-base:latest`
# for their install step.
#
# Rebuild ONLY when the dependency set or the image recipe changes — a normal
# code push must not trigger a 25-min image build. `path` applies to push/PR
# events; `event: tag` (releases) rebuilds unconditionally so a tagged release
# always ships a fresh base.
when:
- event: tag
- event: [push, manual]
branch: main
path:
include:
- 'pnpm-lock.yaml'
- 'Dockerfile.ci'
steps:
build-ci-base:
image: gcr.io/kaniko-project/executor:debug
environment:
REGISTRY_USER:
from_secret: gitea_username
REGISTRY_PASS:
from_secret: gitea_password
CI_COMMIT_BRANCH: ${CI_COMMIT_BRANCH}
CI_COMMIT_TAG: ${CI_COMMIT_TAG}
CI_COMMIT_SHA: ${CI_COMMIT_SHA}
commands:
- mkdir -p /kaniko/.docker
- echo "{\"auths\":{\"git.mosaicstack.dev\":{\"username\":\"$REGISTRY_USER\",\"password\":\"$REGISTRY_PASS\"}}}" > /kaniko/.docker/config.json
- |
# Lockfile-hash tag: an immutable identity for the exact dep set baked
# into this image. `:latest` is the mutable pointer pipelines consume.
LOCK_HASH=$(sha256sum pnpm-lock.yaml | cut -c1-12)
DESTINATIONS="--destination git.mosaicstack.dev/mosaicstack/stack/ci-base:latest"
DESTINATIONS="$DESTINATIONS --destination git.mosaicstack.dev/mosaicstack/stack/ci-base:lock-$LOCK_HASH"
/kaniko/executor --context . --dockerfile Dockerfile.ci $DESTINATIONS

View File

@@ -1,9 +1,5 @@
# &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
# store. The install step resolves from the baked store (--prefer-offline)
# instead of paying a ~731s cold fetch + native compile every run.
variables:
- &node_image 'git.mosaicstack.dev/mosaicstack/stack/ci-base:latest'
- &node_image 'node:22-alpine'
- &enable_pnpm 'corepack enable'
when:
@@ -19,9 +15,8 @@ steps:
image: *node_image
commands:
- corepack enable
# python3/make/g++ are baked into ci-base; --prefer-offline resolves from
# the baked pnpm store.
- pnpm install --frozen-lockfile --prefer-offline
- apk add --no-cache python3 make g++
- pnpm install --frozen-lockfile
# Blocking gate: public framework package must contain no operator-specific
# personal data or private $HOME defaults. Runs early (no node_modules needed).
@@ -69,7 +64,8 @@ steps:
DATABASE_URL: postgresql://mosaic:mosaic@ci-postgres:5432/mosaic
commands:
- *enable_pnpm
# postgresql-client (pg_isready) is baked into ci-base.
# Install postgresql-client for pg_isready
- apk add --no-cache postgresql-client
# Wait up to 60s for CI postgres to be ready; fail fast if it never comes up.
- |
ready=0

View File

@@ -2,9 +2,7 @@
# Runs only on main branch push/tag
variables:
# Pre-baked CI base (see .woodpecker/ci-image.yml): node:24-alpine +
# toolchain + warm pnpm store. Kills the second cold install publish pays.
- &node_image 'git.mosaicstack.dev/mosaicstack/stack/ci-base:latest'
- &node_image 'node:22-alpine'
- &enable_pnpm 'corepack enable'
# Heavy kaniko image builds (~25 min) — gate them so a merge that only touches
# the npm-only CLI (@mosaicstack/mosaic) or docs does NOT rebuild the platform
@@ -33,8 +31,7 @@ steps:
image: *node_image
commands:
- corepack enable
# Resolve from the baked pnpm store instead of a cold network fetch.
- pnpm install --frozen-lockfile --prefer-offline
- pnpm install --frozen-lockfile
build:
image: *node_image

View File

@@ -1,45 +0,0 @@
# Pre-baked CI base image for Woodpecker pipelines.
#
# Purpose: eliminate the cold `pnpm install` that dominates every pipeline
# (~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
# already fetched at build time. `pnpm fetch` only populates the store from the
# lockfile — it does NOT run the native node-gyp builds (better-sqlite3,
# node-pty, sqlite3, canvas, sharp); those still compile at `pnpm install`,
# which is exactly why the musl toolchain stays baked into this image. A
# 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
# (see .woodpecker/ci-image.yml).
#
# Node version is pinned to 24 (Active LTS). This is the follow-up bump from
# node:22 — sequenced AFTER the CI cache work landed so the runtime change
# carries zero cache variables. node:26 stays held until it reaches LTS
# (Oct 2026); the Current line risks native-module (node-gyp) breakage on a
# 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
# postgresql-client used by the test step's pg_isready readiness probe. `bash`
# is baked here too — the sanitization step in ci.yml otherwise does a per-run
# `apk add bash`.
RUN apk add --no-cache python3 make g++ postgresql-client bash
# Pin pnpm to the repo's packageManager version via corepack.
RUN corepack enable && corepack prepare pnpm@10.6.2 --activate
WORKDIR /app
# Pin the store location so the pipeline can point `store-dir` at the same path.
ENV PNPM_HOME=/root/.local/share/pnpm
RUN pnpm config set store-dir /root/.local/share/pnpm/store
# Warm the store. `pnpm fetch` populates the content-addressable store with the
# dependency tarballs directly from the lockfile (no package.json / workspace
# needed), so a baked store stays valid until the lockfile changes. Note:
# `fetch` does NOT compile native modules — that happens later at `pnpm install`
# in the pipeline, against the toolchain baked above.
COPY pnpm-lock.yaml ./
RUN pnpm fetch --frozen-lockfile

View File

@@ -79,14 +79,6 @@ Active workstream is **W1 — Federation v1**. Workers should:
- Status: implemented + tested. FIX1 model_hint→MOSAIC_AGENT_MODEL→--model. FIX2 absent socket = default tmux socket (no -L) across parse/spawn/systemd-unit/observe (socketArgs helper, bare-empty shellEnvValue, conditional -L). 158 fleet tests green; shipped presets unaffected (explicit socket_name). Detail: scratchpads/fleet-standup-fixes.md.
## north-star doctrine consolidation — doc PR — feat/north-star-doctrine
- Status: applied Mos's consolidated merge-map to docs/fleet/north-star.md (budget governance + control plane/central register + 200k cap + delegation + unified-identity Fleet + role-based naming + tmux security + drift re-captures). Doctrine only; #622/#623/#625/#628 out-of-scope. Conflict checklist green. Detail: scratchpads/north-star-doctrine.md.
## #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.
## #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

@@ -7,10 +7,10 @@
## Problem
The durable tmux fleet runs on the isolated `mosaic-fleet` socket. That isolation
The durable tmux fleet runs on the isolated `mosaic-factory` socket. That isolation
(which protects the operator's default tmux) makes the fleet **invisible** to default
tooling, and truth is split across three planes no single command joins — systemd
(`systemctl --user`), tmux (`-L mosaic-fleet`), and the process tree (`pstree`).
(`systemctl --user`), tmux (`-L mosaic-factory`), and the process tree (`pstree`).
`agent tail` (`capture-pane`) returns **blank for full-screen TUIs**, and `agent send`
confirms only keystroke injection, not acceptance. Net: the operator has near-zero
observability and no safe way to watch a session.
@@ -56,7 +56,7 @@ observability and no safe way to watch a session.
## Acceptance criteria
- `mosaic fleet ps` shows all 5 live sessions on `mosaic-fleet` with correct
- `mosaic fleet ps` shows all 5 live sessions on `mosaic-factory` with correct
pane/pid/idle and flags the dogfood **drift** (`canary-pi` runtime=pi but pane runs
`dogfood-agent.py`) and the **boot-enable** gap (active but disabled).
- Killing one agent's pane flips its row to dead/stale within one `interval`.
@@ -72,7 +72,7 @@ observability and no safe way to watch a session.
- Unit/CLI specs in `packages/mosaic/src/commands/fleet.spec.ts` (and a new
`fleet-ps`/`watch`/`send-verify` spec) using the injected `CommandRunner` to assert
exact tmux/systemd command construction and JSON shape (tenant+host present).
- Situational: run against the live `mosaic-fleet` fleet; capture `fleet ps` output,
- Situational: run against the live `mosaic-factory` fleet; capture `fleet ps` output,
a kill-and-detect cycle, a read-only `watch`, and a `send --verify` pass/fail pair.
## Known limitations

View File

@@ -8,11 +8,11 @@
> Status: `not-started` | `in-progress` | `done` | `blocked` | `failed`
| id | status | description | depends_on | agent | pr | notes |
| ------------- | ----------- | ------------------------------------------------------------------------------------------------------------------ | --------------------- | ----------- | --- | --------------------------------------------------------------------------------------------------------------------------- |
| ------------- | ----------- | ------------------------------------------------------------------------------------------------------------------ | --------------------- | ----------- | --- | ----------------------------------------------------------------------------------------------------------------------------- |
| FLEET-OBS-000 | done | Plan: north-star + Phase-2 PRD + workstream scaffolding | — | lead | — | persisted 2026-06-20 on `feat/fleet-observability` |
| FLEET-OBS-001 | done | Heartbeat protocol v1 spec finalized in PRD + framework doc | FLEET-OBS-000 | lead | — | file-based `~/.config/mosaic/fleet/run/<agent>.hb`; spec in PRD |
| FLEET-OBS-002 | in-progress | Implement heartbeat responder in `dogfood-agent.py` | FLEET-OBS-001 | fleet-coder | — | dispatched to ad-hoc `mosaic yolo` fleet agent (dogfood) |
| FLEET-OBS-003 | done | `mosaic fleet ps` — join systemd+tmux+proc+idle+heartbeat; tenant+host tagged; drift + boot-enable flags; `--json` | FLEET-OBS-001 | worker | — | commit ab47831; LIVE-verified on mosaic-fleet; caught canary-pi DRIFT + BOOT-ENABLE. Polish: idleSeconds parse returns null |
| FLEET-OBS-003 | done | `mosaic fleet ps` — join systemd+tmux+proc+idle+heartbeat; tenant+host tagged; drift + boot-enable flags; `--json` | FLEET-OBS-001 | worker | — | commit ab47831; LIVE-verified on mosaic-factory; caught canary-pi DRIFT + BOOT-ENABLE. Polish: idleSeconds parse returns null |
| FLEET-OBS-004 | done | `mosaic agent watch <name>` — read-only join (no resize, no keystrokes) | FLEET-OBS-000 | worker | — | `attach -r`; verb wired |
| FLEET-OBS-005 | done | `mosaic agent send --verify` — delivery/acceptance receipt | FLEET-OBS-000 | worker | — | --verify flag; draft-heuristic verify |
| FLEET-OBS-006 | done | CLI specs for ps/watch/send-verify (tenant+host shape, command construction) | FLEET-OBS-003,004,005 | worker | — | 62 tests green (31 new); re-verified by lead |

View File

@@ -56,21 +56,13 @@ The Fleet inherits — does not re-invent — the MVP's hard requirements:
One **definition** is the source of truth; the **session** is how it runs.
| Layer | Owner | Phase-2 reality | Destination |
| -------------------------------- | ------------------------------------------------------------------------------------------- | ------------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------- |
| -------------------------------- | ------------------------------------------------------------------------------------------- | ------------------------------------------------------ | ------------------------------------------------------- |
| **Definition + identity + auth** | gateway / `mosaic-as` (scoped tokens, #541) | `roster.yaml` (tenant-tagged) | one definition; `mosaic agent --new` materializes it |
| **Tenancy boundary** | **Linux uid per tenant** (linger, own `systemd --user`, own socket, own `~/.config/mosaic`) | one tenant: `jarvis` = tenant zero | uid-per-tenant; federation aggregates across hosts |
| **Runtime** | per-tenant tmux session on isolated socket | dogfood stub sessions (live now on `mosaic-factory`) | claude/codex/pi/opencode TUIs |
| **Liveness** | **heartbeat protocol** every runtime answers | protocol defined + dogfood stub answers it | all runtimes answer; "healthy" ≠ "pane alive" |
| **Observation** | read-only `watch` (native tmux) + `pipe-pane` stream | CLI `watch`/`ps`; explicit opt-in `attach` for control | + auth-gated webUI streams |
| **Control plane** | **federation** across hosts × tenants | records already carry `tenant_id` + `host` | federated gateways expose fleet state; webUI in Phase 5 |
| **Central register** | Postgres `fleet` schema (gateway instance); access via gateway API only | _none in PoC_ (files + `roster.yaml`) | agents, missions, tasks, heartbeats, spend — single network-accessible SSOT; docs = generated projections |
| **Budget / spend governance** | **per-tenant budget policy** ingested by the orchestrator + routing layer | none today (spend is unmetered) | usage-vs-limit feedback ingested; spend auto-paced to the limit window; per-provider/per-account/concurrency/API-$ budgets enforced |
> **PoC socket hygiene:** the PoC fleet runs on the **default tmux socket** (no `-L`).
> The named production-isolation socket is **`mosaic-fleet`** (matches the product brand);
> an absent roster `socket_name` means the default socket everywhere (spawn, `fleet ps`,
> onboarding cheat-sheet). The legacy dogfood canary still runs on the old `mosaic-factory`
> socket pending migration.
## Operating model (inherited, not reinvented)
@@ -121,67 +113,6 @@ Every artifact, starting Phase 2, MUST:
3. Define **healthy = answered a heartbeat within N seconds**, never just "pane alive".
4. Make **observation read-only by default**; control is an explicit, separate, opt-in verb.
> **OPS INVARIANT — runtime agents need a real TTY.** Claude/Codex/pi/opencode agents
> cannot be bare-launched from a systemd `ExecStart`; a durable harness with a real PTY is
> required. This is **why `start-agent-session.sh` launches into tmux** and uses a
> `MOSAIC_AGENT_COMMAND` override rather than running the runtime directly under systemd.
## Budget & token governance (first-class fleet concern)
Spend is a fleet-level resource, not a per-agent afterthought. The fleet treats token
and API-dollar budget the way it treats liveness: a signal every runtime exposes and the
control plane is accountable for. This rides the same primitives as everything else —
`tenant_id` + `host` on every spend record, **read-only metering by default**, and the
**federation** layer as the cross-host aggregation point (W1) — so budgeting is zero-foreclosure
from day one even while one tenant exists.
**Two spend regimes, one policy surface:**
| Regime | Feedback signal | Fleet obligation |
| ------------------------------------------------------- | ------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------- |
| **OAuth-subscription runtimes** (Claude sub, Codex sub) | runtime exposes **current-usage-vs-limit** within a rolling limit window | **ingest** the signal per sub-account; **auto-pace** agentic spend so the window is not exhausted early |
| **API-token runtimes** (metered per token) | provider billing / token counts | enforce **hard $-spend ceilings**; on breach, **downgrade → queue → refuse** (below) |
**Auto-pacing law (OAuth subs) — EVEN-SPREAD default (Jason override, 2026-06-22):** the fleet
paces agentic token spend to consume the limit window **evenly over remaining time**:
target rate = _(remaining usage available)_ ÷ _(remaining time in the window)_. Example: 100% of
a 7-day window = **~14.285%/day**; the system tracks current usage and continuously re-splits the
remainder evenly to hold pace. **Anticipated token-spend-per-task is the budgeting informant**
tasks are scheduled against the daily pace, not run until the quota is gone. Rationale: spreading
delivery evenly beats rapidly exhausting usage and losing **multiple days of momentum**.
**Rapid pacing / overspend requires EXPLICIT user authorization;** absent it, even-spread holds.
Pacing is a control-plane decision, surfaced read-only before it throttles a lane.
**Hard-cap breach behavior (ladder):** when a budget ceiling is hit mid-work, the fleet
**downgrades first** (opus → sonnet → haiku, then Claude → Codex), **queues** the lane at the
cheapest floor until the window resets, and **refuses** only as a last resort. Refusal is never
the first response to a breach.
**Spend accounting, learning & telemetry:**
- **Multi-subscription auto-routing:** a tenant with multiple subscriptions may let the fleet
**auto-route work to the account with the most available usage** (within budget policy).
- **Historical spend learning:** every task's token spend is **recorded**; historical data
continuously updates known **spend-per-task**, **typical daily spend**, and projections — so
estimates self-correct and pacing stays on target.
- **Projected + actual spend on artifacts (Mosaic Stack mandate):** PRDs, missions, and task
decomposition **MUST note projected AND actual token spend** — a Mosaic Stack process standard
(template-level), tracked separately as **#622**.
- **Anonymized telemetry → mosaicstack.dev:** spend data is reported (anonymous) to the
mosaicstack.dev telemetry endpoint so other agents/fleets budget and optimize from real,
anonymized data. Product workstream, tracked separately as **#623**.
**User-settable budgets (the policy surface).** A tenant operator can set budgets for every
configured **provider** (per-provider ceilings), the **account-to-task mapping**, the **agentic
routing flow**, **concurrency** (the spend multiplier), and **hard API-token $-limits**. Budgets
are enforced at the orchestrator + routing boundary, not inside individual workers (a worker never
decides its own budget — see delegation discipline).
**Budget CLI UX (#558):** `mosaic budget set --reset-at` sets the window reset; reset-datetimes
carry **confidence tags** (`user` / `provider` / `estimated` / `unknown`); and **urgency/criticality
is a dispatch-gate modifier** — high-urgency work may override even-spread pacing **within
authorization**. (Also feeds the budgeting workstream, not only this doc.)
## Observation model
| Verb | Behavior |
@@ -196,83 +127,15 @@ authorization**. (Also feeds the budgeting workstream, not only this doc.)
> (blank for full-screen TUIs), and `attach` is read-write + resizes the session. The
> verbs above restore "join and observe" safely.
## Control plane & central register
### Why the register must be Postgres
The fleet is multi-host (w-jarvis + dragon-lin + future). A SQLite file is a local
file — it is not a network service and cannot be shared across hosts. Beyond topology,
Postgres MVCC eliminates the concurrent-writer corruption class Hermes hit with SQLite
under multi-agent access.
Access is exclusively through the **gateway API** (`apps/gateway` — typed, auth-gated,
scoped tokens). No agent or dispatcher pane ever holds a raw DB credential; a
compromised pane cannot corrupt or exfiltrate the register.
### Architecture (layers)
| Layer | Responsibility | Implementation |
| ---------------------- | ------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Register** | Source of truth: agents, missions, tasks, heartbeats, spend | Postgres `fleet` schema — existing stack instance (`@mosaicstack/db`) |
| **Access** | Typed, auth-gated API | Gateway `fleet/*` routes |
| **Dispatcher** | Brief classification, BOD review, planning/coding/review/test/deploy sequencing + gates → fleet task dispatch | **forge pipeline engine** (`runPipeline`/`resumePipeline`, brief classifier, BOD) **+ thin `forge-exec` adapter → `agent-send.sh`**; NOT a new daemon — forge is reused, only stage→agent dispatch is new |
| **Orchestrator (Mos)** | Goals, missions, judgment, user/PA interface | Context-light; sets intent → re-engages only for decisions |
### Dispatcher = forge (reuse, do not rebuild)
The dispatcher is **not new work**: it is `@mosaicstack/forge`, a fully-implemented
software-factory pipeline engine (brief → Board-of-Directors review → 3 planning stages →
coding → review/remediation → testing → deploy). Forge already provides
`runPipeline`/`resumePipeline`, a brief classifier, and a BOD persona loader, so the fleet
does **not** re-implement sequencing, gate logic, or brief classification. The only new
fleet-owned code is a thin **`forge-exec` TaskExecutor adapter** (`ForgeTask`
`agent-send.sh` to a named agent) — forge's single missing piece — tracked as a Gitea
issue and built post-PoC. The Postgres register backs forge's pipeline state (durable
`resumePipeline`, cross-host) in addition to cross-project missions/tasks/Kanban. The
north-star **'board' role IS forge's Board-of-Directors** — reused from forge, not a new
role implementation.
### Docs as projections
`docs/TASKS.md` and `MISSION-MANIFEST.md` are **generated projections** of the DB,
not hand-maintained. The dispatcher (or a scheduled job) renders Markdown from
`fleet.*` tables and commits the output. DB is authoritative; docs are for human
reference.
### Spend
`fleet.spend_ledger` records projected and actual token spend per agent/mission/task
(ties to issue #622). The dispatcher enforces budget caps before dispatching. Mos reads
the roll-up via API — no raw DB access, no context-bloating dumps.
### Federation
Cross-host fleet state flows through federated gateway queries (existing
`federation_peers` / `federation_grants` machinery). This is the existing north-star
invariant: **control plane rides federation (W1), not a bespoke broker.** No new
broker introduced.
### Scope
This is Phase 45 of this roadmap, materialized. It MUST NOT block the PoC (which
runs correctly on files + `roster.yaml`). Begin when Phase 2 heartbeat protocol is
stable and concurrent-agent count makes file coordination the bottleneck.
### Open sub-decision
Dedicated Postgres **instance** vs. dedicated **schema** in the existing instance.
Recommendation: dedicated schema, existing instance (a migration file, not new infra);
re-evaluate if isolation or write-volume demands it.
## Phased roadmap
| Phase | Outcome | Status |
| ---------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------- |
| ---------------------- | -------------------------------------------------------------------------------------------------------------------------------------------- | ------- |
| 01 | tmux PoC, hardening, published CLI v0.0.34 (#565#568) | ✅ done |
| **2 — Observability** | `fleet ps` (host+tenant aware join), heartbeat protocol + dogfood stub answers it, `agent watch` (read-only), `agent send --verify` receipts | ▶ now |
| 3 — Real runtimes | claude/codex/pi/opencode answer heartbeat; **hybrid lifecycle** (core always-on: **orchestrator + enhancer**; ephemeral workers per lane) | planned |
| 4 — Unified definition | one agent schema in gateway; `mosaic agent --new` → materialized per-tenant session; uid-tenant provisioning; **`fleet` schema migration + `forge-exec` TaskExecutor adapter (forge → `agent-send.sh`)** | planned |
| 5 — Control plane | federation-backed cross-host × cross-tenant fleet view; **webUI** (surface chosen then) for MVP-X1 parity; **central register live (spend ledger, docs-as-projections, multi-host Kanban)** | planned |
| 4 — Unified definition | one agent schema in gateway; `mosaic agent --new` → materialized per-tenant session; uid-tenant provisioning | planned |
| 5 — Control plane | federation-backed cross-host × cross-tenant fleet view; **webUI** (surface chosen then) for MVP-X1 parity | planned |
## Decisions of record (2026-06-20, with Jason)
@@ -301,57 +164,6 @@ re-evaluate if isolation or write-volume demands it.
- **Orchestrator chat connector:** the orchestrator is reachable over a user-chosen connector
(tmux now; Telegram/Discord/Matrix/Slack configurable). Validated live: **"Mos" orchestrator
on Discord** via the Claude Code discord channel plugin (w-jarvis).
- **Session context cap = 200k tokens (GLOBAL to all Claude sessions):** Claude Code sessions are
capped at a **max 200k-token context window**. Long-running sessions extended toward 1M tokens
have proven **worse in practice** (degraded steering, off-plan divergence); 200k is the standard.
**Enforcement split:** the _window_ lives in **`~/.claude/settings.json`** (host-global) as
`"autoCompactWindow": 200000` + `"autoCompactEnabled": true`; the _1M-disable_ lives in **launch
ENV** (`CLAUDE_CODE_DISABLE_1M_CONTEXT=1`, plus `CLAUDE_CODE_AUTO_COMPACT_WINDOW=200000`) wherever
a `[1m]` model can be selected (`mos-claude.service` + the fleet Claude launcher), so every Claude
agent is capped at spawn. (settings = window; env = 1M-disable.)
- **Worker context bound (#8):** workers are kept context-bounded via the **ephemeral-per-lane
lifecycle + native compaction**, not via the 200k knob. The explicit `autoCompactWindow` 200k knob
**stays Claude-specific** — the _principle_ (bounded context) extends to workers, the _knob_ does not.
- **Orchestrator delegation discipline:** the orchestrator **delegates all delivery work** to
subagents / workflows / ultracode / coder agents and confines its own context to \*\*orchestration
- the personal-assistant lane\*\*. Keeping delivery out of the orchestrator's window keeps its
context unpolluted and measurably reduces off-plan divergence. The orchestrator coordinates and
decides; it does not implement.
- **Budget governance is fleet doctrine:** token/API-dollar budgeting is a first-class fleet concern
(see "Budget & token governance"). OAuth-sub usage-vs-limit feedback is ingested per account, spend
is **auto-paced EVEN-SPREAD over remaining time** (rapid/overspend only on explicit authorization),
spend is **tracked historically** to self-correct per-task/daily estimates, multi-sub tenants may
**auto-route by available usage**, and operators set budgets per provider, per account-to-task
mapping, per routing flow, per concurrency level, and as hard API-$ ceilings.
- **Spend accounting is a Mosaic Stack process mandate:** PRDs, missions, and task decomposition
**MUST carry projected + actual token spend**; used locally for pacing and reported as **anonymized
telemetry to mosaicstack.dev**. The template standard (#622) and telemetry product (#623) are
tracked separately.
- **Unified identity = "Fleet" (Jason, 2026-06-22):** the product is **Mosaic Fleet** — one unified
user-facing identity and CLI surface. **forge** is the Fleet's **internal** delivery/orchestration
engine (not a separate product); the control-plane **Postgres register is the Fleet's register**;
workers/runtime are the **Fleet substrate**. **"factory" is RETIRED as a product term** — it was
only ever the software-factory concept (which forge implements) and the old `mosaic-factory` tmux
socket name. The production-isolation socket is now **`mosaic-fleet`** (matches the product brand);
the legacy dogfood canary remains on the old `mosaic-factory` socket pending migration. **Code stays
layered** (forge + fleet + control-plane as internal layers);
only the **identity + CLI surface unify under Fleet.**
- **Role-based session naming (Jason, 2026-06-22):** agent tmux sessions are named by **role**
(`orchestrator`, `enhancer`, `research`, `coder0-0`, …), not by persona. **Persona lives in
`SOUL.md`**; the front-end / Discord presents a **friendly alias** (e.g. "Mos" = the orchestrator's
alias). The session name is the stable addressing handle; the alias is presentation.
### Control plane & central register
- **Store:** Postgres (existing stack instance, dedicated `fleet` schema via `@mosaicstack/db`). SQLite rejected: (1) it is a local file — structurally incompatible with a multi-host fleet; (2) concurrent multi-agent writes caused repeated corruption in Hermes. "SQLite + access service" rejected as reinventing a DB server badly; "LLM agent gating DB access" rejected as slow, expensive, and a single point of failure.
- **Access:** gateway API only (`apps/gateway`, `fleet/*` routes). No raw DB credentials in any agent/dispatcher pane — directly mitigates the tmux attack-surface concern.
- **Dispatcher = forge (reuse, not a new build):** the dispatcher IS `@mosaicstack/forge`'s pipeline engine (`runPipeline`/`resumePipeline` + brief classifier + BOD persona loader), a fully-implemented software-factory pipeline (brief → BOD review → 3 planning stages → coding → review/remediation → testing → deploy). We do **not** design/build a new dispatcher and do **not** re-implement sequencing, gate logic, or brief classification. The only new fleet-owned piece is a thin **`forge-exec` TaskExecutor adapter** (suggested package `packages/forge-exec`) mapping a `ForgeTask``agent-send.sh` dispatch to a named fleet agent — forge's single missing piece. It is tracked as a Gitea issue and built **post-PoC** (not now).
- **Register backs forge:** the Postgres `fleet` register is genuinely new (neither forge nor the fleet has cross-project state). It BACKS forge's pipeline state (durable `resumePipeline`, cross-host) plus cross-project missions/tasks/Kanban.
- **'board' role = forge BOD:** the north-star role-library 'board' role IS forge's Board-of-Directors — reused, not reinvented.
- **Orchestration vs. dispatch:** Orchestrator (Mos) sets intent and handles judgment; forge works the mechanical pipeline (sequencing, gates, status transitions, spend ledger). LLM escalation reserved for judgment: mission decomposition, re-planning on failure.
- **Spend in the register:** `fleet.spend_ledger` tracks projected vs. actual tokens per agent/mission/task; ties to issue #622.
- **Docs as projections:** `docs/TASKS.md` and `MISSION-MANIFEST.md` become generated exports of the DB, not hand-maintained.
- **Sub-decision pending:** dedicated schema in existing PG instance (recommended) vs. dedicated PG instance. Revisit if isolation or write-volume demands it.
## Future enhancements (north-star, post-MVP — not on the MVP track)
@@ -361,16 +173,6 @@ re-evaluate if isolation or write-volume demands it.
A major enhancement over the current third-party channel plugin; **not required for the MVP**,
but a committed north-star target. `ASSUMPTION:` ships as a Mosaic-owned plugin so the fleet
controls Discord UX (threads, reactions, attachments, per-thread context) end-to-end.
- **Matrix on a local homeserver — strategic future transport.** **F4 (in progress) IS the Matrix
connector**: an orchestrator chat connector speaking the Matrix client-server API against a
self-hosted homeserver (Conduit default, Synapse alt). Matrix is named here as the strategic
future transport — peer to tmux/Discord, not superseded by them.
- **tmux fleet attack-surface hardening.** Many always-on tmux sessions are an attack surface;
`tmux send-keys` / socket access could enable malicious action against agents directly.
Mitigations to build toward: socket ownership/perms, per-tenant socket isolation (already an
invariant), authenticated `agent-send`, and an audit of who can write to any pane. **Post-MVP
unless a P0 surfaces.** The control-plane register reinforces this (gateway-API access = no raw
DB creds in panes). A not-started risk-assessment + mitigation-plan task rides the Fleet `TASKS.md`.
## Assumptions (veto-able)
@@ -382,30 +184,3 @@ re-evaluate if isolation or write-volume demands it.
- `ASSUMPTION:` Fleet is workstream **W-FLEET** under `mvp-20260312`; a rollup row in
`docs/TASKS.md` and a workstream declaration in `MISSION-MANIFEST.md` are proposed to
the MVP orchestrator, not written by this workstream.
- `ASSUMPTION:` OAuth-subscription runtimes (Claude sub, Codex sub) expose a machine-readable
current-usage-vs-limit signal the fleet can poll/ingest; if a provider exposes no such signal,
that provider's accounts fall back to API-style hard-ceiling budgeting only (no auto-pacing).
- `ASSUMPTION:` budget policy lives at the orchestrator + routing layer and is surfaced through the
same CLI→TUI→webUI parity (MVP-X1) as the rest of fleet state — not a separate budgeting daemon.
- `ASSUMPTION:` the 200k session cap is enforced by Claude Code settings/env composition (model
variant + `autoCompactWindow`), not by a Mosaic wrapper; a wrapper is the fallback only if the
harness later removes those knobs.
- `ASSUMPTION:` The central register (Postgres `fleet` schema + gateway API + forge as dispatcher) is
the Phase 45 control plane, begun after Phase 2 observability is proven. It is a dedicated
**W-FLEET** sub-workstream entry, not a separate mission. The dispatcher is `@mosaicstack/forge`
(reused, not a new daemon); the only new fleet-owned code is the thin **`forge-exec` TaskExecutor
adapter** (suggested package `packages/forge-exec`, `ForgeTask``agent-send.sh`), tracked as a
Gitea issue and built post-PoC.
---
> **Release procedure (drift re-capture, 2026-06-22):** `mosaic update` only propagates new fleet
> commands when the **CLI version is bumped** — without a version bump, fleet command changes never
> reach installed hosts. The release/version-bump procedure (bump → publish → `mosaic update`
> [→ `--relaunch`]) must be documented so fleet changes actually land. (Also feeds the budgeting
> workstream.)
>
> **Tracked separately (not in scope for this doc PR):** **#622** PRD/mission/task projected+actual
> spend template standard · **#623** anonymized spend telemetry → mosaicstack.dev (product) ·
> **#625** `tenant_id` roster-schema field (multi-tenant; invariant #1 home) · **#628** `forge-exec`
> TaskExecutor adapter (post-PoC). This PR records **doctrine only** — no implementation.

View File

@@ -1,7 +1,7 @@
# Local Fleet Canary
The local fleet canary runs a small tmux-backed Mosaic agent fleet on an
isolated tmux socket. The default socket is `mosaic-fleet`; the commands do
isolated tmux socket. The default socket is `mosaic-factory`; the commands do
not use or stop the default tmux server.
## Files
@@ -67,7 +67,7 @@ mosaic agent tail canary-pi -n 80
These commands read the roster and target the configured tmux socket. The
generated systemd agent services use `start-agent-session.sh`; message delivery
uses the tmux send tools with `-L mosaic-fleet`.
uses the tmux send tools with `-L mosaic-factory`.
`mosaic agent send` is operator-origin traffic unless a caller explicitly says
otherwise. The CLI always passes a deterministic source label to
@@ -82,7 +82,7 @@ impersonating a known handoff lane. The lower-level inter-agent wrapper
Use these checks before expanding the roster:
```bash
tmux -L mosaic-fleet ls
tmux -L mosaic-factory ls
tmux ls
mosaic fleet verify
systemctl --user status mosaic-tmux-holder.service
@@ -90,7 +90,7 @@ systemctl --user status mosaic-tmux-holder.service
Expected results:
- `tmux -L mosaic-fleet ls` shows `_holder` and roster agent sessions.
- `tmux -L mosaic-factory ls` shows `_holder` and roster agent sessions.
- `tmux ls` shows only the default tmux server sessions and is not changed by
fleet start/stop operations.
- `mosaic fleet verify` checks exact session targets on the isolated socket.
@@ -108,7 +108,7 @@ Run this checklist before cutting or dogfooding a fleet release:
repeated `start` against the named socket; verify the default tmux server is
unchanged.
- Liveness verification: run `mosaic fleet verify` and confirm roster sessions
with `tmux -L mosaic-fleet ls` or exact `has-session` checks.
with `tmux -L mosaic-factory ls` or exact `has-session` checks.
- Package dry-run: run `npm pack --dry-run --json` from `packages/mosaic` and
confirm `framework/fleet`, `framework/systemd/user`,
`framework/tools/fleet`, and `framework/tools/tmux` assets are included.
@@ -140,5 +140,5 @@ This rollback leaves the default tmux server untouched. If a canary session is
still present after service stop, remove only the isolated socket server:
```bash
tmux -L mosaic-fleet kill-server
tmux -L mosaic-factory kill-server
```

View File

@@ -17,7 +17,7 @@ Implement enough product surface to use the fleet locally:
- roster schema and examples
- local canary docs and rollback instructions
- tests for CLI behavior where practical
- canary verification on named tmux socket `mosaic-fleet`
- canary verification on named tmux socket `mosaic-factory`
## Non-goals
@@ -30,7 +30,7 @@ Implement enough product surface to use the fleet locally:
- CLI can initialize a minimal roster outside product defaults.
- CLI can install user systemd units and fleet helper scripts to a configurable Mosaic home.
- CLI can start/stop/status/verify a canary fleet using `mosaic-fleet`.
- CLI can start/stop/status/verify a canary fleet using `mosaic-factory`.
- `mosaic agent send` uses existing named-socket/exact-target tmux tooling.
- `mosaic agent reset` targets only the named agent session on the named socket.
- Verification proves default tmux sessions remain untouched.

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

@@ -31,7 +31,7 @@ with a second agent on `dragon-lin`.
## Environment facts (verified 2026-06-20)
- Fleet is live on `W-jarvis` (uid 1000, `jarvis`, `Linger=yes`) on tmux socket
`mosaic-fleet`: `_holder`, `canary-pi`, `dogfood-coder`, `dogfood-orchestrator`,
`mosaic-factory`: `_holder`, `canary-pi`, `dogfood-coder`, `dogfood-orchestrator`,
`dogfood-reviewer`. All panes run `~/.config/mosaic/fleet/dogfood-agent.py` (stub),
including `canary-pi` (roster says runtime=pi → **drift**).
- Holder + `mosaic-agent@*` units are `active (exited)` but `UnitFileState=disabled`
@@ -56,7 +56,7 @@ with a second agent on `dragon-lin`.
with dragon-lin coder, commit docs, begin Phase-2 delivery (heartbeat + `fleet ps`).
- 2026-06-20 (session 2): Built Phase-2 CLI via worker (commit ab47831): `fleet ps`,
`agent watch`, `agent send --verify`, 62 tests. LIVE-verified `fleet ps` on
mosaic-fleet — correctly flagged canary-pi DRIFT + BOOT-ENABLE, tenant_id+host in JSON.
mosaic-factory — correctly flagged canary-pi DRIFT + BOOT-ENABLE, tenant_id+host in JSON.
Heartbeat responder added to dogfood-agent.py (FLEET-OBS-002) — `fleet ps` HB now
`healthy` for all 4 agents.
- Coordination: dual-engine-reviewed (Claude+Codex) and merged framework PRs #572

View File

@@ -11,14 +11,14 @@
## FIX 2 — socket default trap (absent ⇒ literal default socket, no -L everywhere)
- THE TRAP (3 sites): parseRosterText fallback was DEFAULT_SOCKET_NAME; systemd unit had
`Environment=MOSAIC_TMUX_SOCKET=mosaic-fleet` + `ExecStop ${…:-mosaic-fleet}`; start-agent-session
defaulted `:-mosaic-fleet`. All fixed → absent socket = '' = default tmux socket (no -L).
`Environment=MOSAIC_TMUX_SOCKET=mosaic-factory` + `ExecStop ${…:-mosaic-factory}`; start-agent-session
defaulted `:-mosaic-factory`. All fixed → absent socket = '' = default tmux socket (no -L).
- `socketArgs(name)` helper → `name ? ['-L', name] : []`; replaced all ~15 -L render sites in fleet.ts.
- shellEnvValue('') now emits a **bare** `VAR=` (not `''`) — unambiguous empty in systemd EnvironmentFile
(a quoted '' could become a literal socket named "''").
- start-agent-session.sh: `_tmux` wrapper passes -L only when socket set; mosaic-agent@.service: dropped the
socket default + conditional ExecStop. So spawn == observe == onboarding cheat-sheet.
- CONTAINMENT: all 6 shipped presets set socket_name: mosaic-fleet explicitly → unaffected; only
- CONTAINMENT: all 6 shipped presets set socket_name: mosaic-factory explicitly → unaffected; only
socket-less rosters (the PoC) get default-socket behavior. DEFAULT_SOCKET_NAME exported for explicit use.
## Verification

View File

@@ -1,66 +0,0 @@
# H1 — heartbeat readiness detection
## Objective
Add runtime-agnostic readiness classification to `mosaic fleet ps` so an agent can be reported as working/idle/stuck/stale/dead/unknown instead of treating pane liveness as progress.
## Scope
- `packages/mosaic/src/commands/fleet.ts`
- exported readiness state/types/default thresholds/helpers/classifier
- `AgentPsRow.readiness` additive JSON field
- table HB column and IDLE/STUCK flags
- `packages/mosaic/src/commands/fleet.spec.ts`
- pure classifier branch/boundary coverage
- threshold helper coverage
- legitimate render/JSON assertion updates for new HB text
## Acceptance Criteria
- Branches covered: dead, unknown, stale, busy working, null-idle working, stuck boundary, idle boundary, working below idle.
- Threshold env helpers default to 300s/900s and honor positive integer env values.
- `fleet ps` rows populate `readiness` for roster and unmanaged socket sessions.
- Table HB text becomes `<age>s/<readiness>` when heartbeat age exists; remains `unknown` when absent.
- Flags include `IDLE`/`STUCK` for matching readiness.
- Local gates green: `pnpm typecheck`, `pnpm lint`, `pnpm format:check`, fleet vitest.
- Pre-push queue guard passes; PR opened off `origin/main`; no merge by worker.
## Constraints / Assumptions
- Source branch: `origin/main` @ `e3adc6a`.
- No scope creep beyond readiness detection.
- `docs/TASKS.md` and `docs/fleet/TASKS.md` are orchestrator-owned; worker will not modify them.
- PRD alignment source: `docs/fleet/PRD.md` Phase 2 observability; this is a refinement of heartbeat observability, preserving existing unknown/stale behavior.
## Plan
1. Install dependencies with requested PNPM environment.
2. Add readiness types/helpers/classifier near heartbeat constants.
3. Add `readiness` to `AgentPsRow` and populate both row paths.
4. Update table render and flags.
5. Add unit tests and update affected ps render/JSON assertions.
6. Run build precheck + required gates.
7. Run automated independent review, remediate findings.
8. Queue guard, push, open PR.
## Progress
- 2026-06-24: Branch created from `origin/main` @ `e3adc6a`.
- 2026-06-24: Implemented readiness thresholds/classifier, JSON row field, HB column label, and IDLE/STUCK flags.
- 2026-06-24: Added classifier branch/boundary tests, threshold helper tests, JSON shape assertions, and readiness table rendering assertions.
## Verification Evidence
- `pnpm install --store-dir "$HOME/.pnpm-store"` — pass.
- `npx turbo build --filter=@mosaicstack/mosaic^...` — pass, 12/12 tasks successful.
- `pnpm typecheck` — pass, 41/41 tasks successful.
- `pnpm lint` — pass, 23/23 tasks successful.
- `pnpm format:check` — pass, all matched files use Prettier style.
- `pnpm --filter @mosaicstack/mosaic exec vitest run src/commands/fleet.spec.ts` — pass, 171 tests.
- `pnpm --filter @mosaicstack/mosaic test` — pass, 39 files / 547 tests; `fleet.spec.ts` 171 tests.
- `~/.config/mosaic/tools/codex/codex-code-review.sh --uncommitted` — approve, 0 findings (reviewed supplied diff; sandbox file-inspection limitation noted by tool).
## Risks / Blockers
- No current blocker.
- Review tool could not inspect repo files directly due sandbox wrapper limitation, but it reviewed the supplied diff and approved with no findings.

View File

@@ -1,53 +0,0 @@
# H1b — tmux pane idle signal wiring
## Objective
Feed `classifyReadiness()` a real idle signal on tmux 3.4 by deriving `idleSeconds` from the first available tmux timestamp source: pane activity, then window activity, then session activity.
## Scope
- `packages/mosaic/src/commands/fleet.ts`
- Extend `buildTmuxListPanesCommand()` format to include `#{window_activity}` and `#{session_activity}` after the existing fields.
- Update `parseTmuxListPanes()` to choose the first non-empty finite positive timestamp and clamp future idle values to 0.
- `packages/mosaic/src/commands/fleet.spec.ts`
- Cover pane/window/session activity parsing behavior, empty-field index alignment, null idle, future clamping, math correctness, and exact tmux format.
## Out of Scope
- No changes to `classifyReadiness()`, thresholds, `AgentPsRow`, or `fleet ps` rendering.
- No merge by worker; orchestrator routes review/merge.
- Workers do not modify `docs/TASKS.md`.
## PRD Alignment
Aligned with `docs/fleet/PRD.md` FR-1 and acceptance criteria for truthful `mosaic fleet ps` pane/pid/idle observability.
## Plan
1. Sync branch from latest `origin/main` and install dependencies with required pnpm env.
2. Add/confirm reproducer tests for tmux 3.4 empty `pane_activity` and new fallback behavior.
3. Implement the focused parser/format change only.
4. Run required build, baseline gates, fleet vitest, and independent review.
5. Run pre-push queue guard, push branch, and open PR to `main` with Mosaic wrapper.
## Progress
- 2026-06-24: Branch `fix/fleet-pane-idle-activity` created from `origin/main` @ `ec8dd7c` after fetching.
- 2026-06-24: Session-start generated local `.mosaic/orchestrator/*` changes on the previous release branch; stashed as `coder1 session-start state before H1b` to keep this branch clean.
- 2026-06-24: Added TDD coverage for the tmux 3.4 production case (`pane_activity` empty, `window_activity` populated), exact new list-panes format, null/future/multiple-source behavior.
- 2026-06-24: Implemented parser fallback without changing readiness classifier thresholds or render shape.
## Verification Evidence
- `pnpm install --store-dir "$HOME/.pnpm-store"` — pass.
- Reproducer before implementation: `pnpm --filter @mosaicstack/mosaic exec vitest run src/commands/fleet.spec.ts` — failed as expected (old format, no fallback, negative future idle).
- `npx turbo build --filter=@mosaicstack/mosaic^...` — pass, 12/12 tasks successful.
- `pnpm typecheck` — pass, 41/41 tasks successful.
- `pnpm lint` — pass, 23/23 tasks successful.
- `pnpm format:check` — pass, all matched files use Prettier style.
- `pnpm --filter @mosaicstack/mosaic exec vitest run src/commands/fleet.spec.ts` — pass, 176 tests.
- `~/.config/mosaic/tools/codex/codex-code-review.sh --uncommitted` — approve, 0 findings (reviewed supplied diff; sandbox file-inspection limitation noted by tool).
## Risks / Blockers
- No current blocker.

View File

@@ -1,70 +0,0 @@
# H2 — readiness semantics: available, not stuck
## Objective
Correct fleet readiness semantics so a healthy long-idle agent is reported as `available` (good/assignable) instead of `stuck` (fault). Reserve `stuck` in the type/JSON value space for future positive block evidence.
## Scope
- `packages/mosaic/src/commands/fleet.ts`
- replace `idle` readiness state with `available`
- keep `stuck` in the union but stop emitting it from idle-only heuristics
- remove stuck threshold helper/env handling
- remove IDLE/STUCK alarm flags from table rendering
- `packages/mosaic/src/commands/fleet.spec.ts`
- update classifier branch/boundary tests
- assert very long idle maps to `available`, not `stuck`
- update table/JSON assertions for available with no alarm flags
- remove stuck threshold helper tests
## Acceptance Criteria
- `classifyReadiness()` remains pure/total/never-throw and maps:
- dead/stale/unknown unchanged
- busy/null/undefined/non-finite idle to `working`
- idle >= activity threshold to `available`
- idle < activity threshold to `working`
- No idle-derived path emits `stuck`.
- `MOSAIC_HEARTBEAT_IDLE_THRESHOLD` remains backward compatible as the working→available activity threshold.
- `MOSAIC_HEARTBEAT_STUCK_THRESHOLD` and helper/default are removed.
- `fleet ps` keeps the idle-seconds column header `IDLE`, renders `available` in HB label, and does not add IDLE/STUCK warning flags.
- Local gates green: build precheck, typecheck, lint, format:check, fleet vitest.
- PR opened against `main`; no merge by worker.
## Constraints / Assumptions
- Source branch: `origin/main` @ `1020cfa`.
- `docs/TASKS.md` is orchestrator-owned; worker will not modify it.
- Documentation impact is captured in this scratchpad and PR description; no user/admin guide behavior beyond CLI readiness label semantics.
## Plan
1. Install dependencies with requested PNPM environment.
2. Inspect current H1/H1b readiness implementation and tests.
3. Update classifier types/helpers/rendering.
4. Update focused tests.
5. Run build precheck + required gates.
6. Run automated code review, remediate any findings.
7. Queue guard, push, open PR.
## Progress
- 2026-06-24: Branch created from `origin/main` @ `1020cfa`.
- 2026-06-24: Replaced idle-derived `idle`/`stuck` outputs with `available`; retained `stuck` in type union for future positive block evidence.
- 2026-06-24: Removed stuck threshold env/helper plumbing and IDLE/STUCK alarm flags.
- 2026-06-24: Updated classifier and table-render tests for available semantics.
## Verification Evidence
- `pnpm install --store-dir "$HOME/.pnpm-store"` — pass.
- `npx turbo build --filter=@mosaicstack/mosaic^...` — pass, 12/12 tasks successful.
- `pnpm typecheck` — pass, 41/41 tasks successful.
- `pnpm lint` — pass, 23/23 tasks successful.
- `pnpm format:check` — pass, all matched files use Prettier style.
- `pnpm --filter @mosaicstack/mosaic exec vitest run src/commands/fleet.spec.ts` — pass, 177 tests.
- `~/.config/mosaic/tools/codex/codex-code-review.sh --uncommitted` — approve, 0 findings (reviewed supplied diff; sandbox file-inspection limitation noted by tool).
## Risks / Blockers
- No current blocker.
- Review tool could not inspect repo files directly due sandbox wrapper limitation, but it reviewed the supplied diff and approved with no findings.

View File

@@ -1,19 +0,0 @@
# north-star doctrine consolidation (#620-adjacent doc PR)
- **Branch:** `feat/north-star-doctrine` (off main). Source: Mos's consolidated handoff + 2 drafts (budgeting/200k/delegation + control-plane). ONE conflict-free PR per the merge-map.
## Applied (merge-map, in order)
1. Stack table: +2 rows (Central register, Budget/spend governance) after Control plane + PoC-socket-hygiene note.
2. `## Budget & token governance` after Invariants (even-spread pacing [Jason override], hard-cap ladder, multi-sub auto-routing, historical learning, #558 CLI UX) + TTY OPS INVARIANT note.
3. `## Control plane & central register` after Observation model (Postgres fleet schema, gateway-API access, dispatcher = forge pipeline engine + forge-exec adapter [NOT a daemon], register backs forge, board = forge BOD).
4. Phased roadmap Phase 4/5 annotated (fleet schema migration + forge-exec; central register live).
5. Decisions of record (2026-06-22): doctrine §1(c) bullets (200k cap, worker bound #8, delegation, budget, spend mandate, unified identity Fleet, role-based session naming) + control-plane 6c `### Control plane & central register` subgroup.
6. Future enhancements: Matrix-future-transport (#10, F4 IS Matrix) + tmux security hardening (§5).
7. Assumptions: doctrine §1(d) (3) + control-plane 6e (1) + release-procedure note + tracked-separately note.
## Conflict checklist: all ✓
1 Decisions-2026-06-22; order Invariants→Budget→Observation→Control plane→Roadmap; 2 stack rows; even-spread (no opportunistic/HOLD); control-plane UNHELD; forge-exec = tracked #628 post-PoC; §7 drift re-captures all present (#8/#10/#558/TTY/release).
## Out of scope (cited in doc + PR): #622 (spend template std), #623 (telemetry product), #625 (tenant_id schema), #628 (forge-exec adapter). Doctrine only — no implementation.

View File

@@ -28,7 +28,6 @@ export default tseslint.config(
'apps/web/e2e/helpers/*.ts',
'apps/web/playwright.config.ts',
'apps/gateway/vitest.config.ts',
'packages/db/vitest.config.ts',
'packages/storage/vitest.config.ts',
'packages/mosaic/__tests__/*.ts',
'tools/federation-harness/*.ts',

View File

@@ -4,22 +4,5 @@ export default defineConfig({
test: {
globals: true,
environment: 'node',
// The migration suite spins up a real PGlite (WASM Postgres) instance per
// test and applies the full drizzle migration set. Each case legitimately
// takes ~5s locally and considerably longer on CI, where turbo runs many
// packages' test suites concurrently. The 5s vitest default then expires
// mid-migration and the run fails as a phantom "Test timed out in 5000ms"
// (often surfacing the underlying WASM `memory access out of bounds` when
// the heap is starved). Give migrations real headroom.
testTimeout: 120_000,
hookTimeout: 120_000,
// Each PGlite instance carries a multi-hundred-MB WASM heap. Running test
// files in parallel forks multiplies that peak and is what tips the CI
// runner into the WASM OOM. A single fork keeps only one instance resident
// at a time — slightly slower, but deterministic.
pool: 'forks',
poolOptions: {
forks: { singleFork: true },
},
},
});

View File

@@ -8,7 +8,7 @@ package, normally at:
~/.config/mosaic/fleet/roster.yaml
```
The default tmux socket is `mosaic-fleet` so fleet commands do not touch the
The default tmux socket is `mosaic-factory` so fleet commands do not touch the
default tmux server.
## Examples

View File

@@ -1,7 +1,7 @@
version: 1
transport: tmux
tmux:
socket_name: mosaic-fleet
socket_name: mosaic-factory
holder_session: _holder
defaults:
working_directory: ~

View File

@@ -1,7 +1,7 @@
version: 1
transport: tmux
tmux:
socket_name: mosaic-fleet
socket_name: mosaic-factory
holder_session: _holder
defaults:
working_directory: ~

View File

@@ -1,7 +1,7 @@
version: 1
transport: tmux
tmux:
socket_name: mosaic-fleet
socket_name: mosaic-factory
holder_session: _holder
defaults:
working_directory: ~

View File

@@ -1,7 +1,7 @@
version: 1
transport: tmux
tmux:
socket_name: mosaic-fleet
socket_name: mosaic-factory
holder_session: _holder
defaults:
working_directory: ~/src

View File

@@ -1,7 +1,7 @@
version: 1
transport: tmux
tmux:
socket_name: mosaic-fleet
socket_name: mosaic-factory
holder_session: _holder
defaults:
working_directory: ~/src

View File

@@ -1,7 +1,7 @@
version: 1
transport: tmux
tmux:
socket_name: mosaic-fleet
socket_name: mosaic-factory
holder_session: _holder
defaults:
working_directory: ~

View File

@@ -1,38 +0,0 @@
# Board — fleet role definition
The **board** is the fleet's **deliberation panel** (`class: board`). It is the
forge **Board-of-Directors** reused as a fleet role — a multi-lens review body
(moonshot, contrarian, technical, business, financial) that owns the mission's
direction, not its execution.
It is a **front-office** role: it sets and guards intent, then steps back.
## Mandate
1. **Own `NORTH_STAR.yaml`** — the single source of truth for goals, assumptions,
and projections. The board is the only role that ratifies edits to it.
2. **Ratify or veto goals and assumptions** — every new objective or load-bearing
assumption passes the board's lenses before the fleet commits resources to it.
3. **Hold the lenses** — moonshot (is the ambition right?), contrarian (what breaks
this?), technical (is it buildable?), business (does it matter?), financial
(can we afford it, in tokens and dollars?).
4. **Re-deliberate on drift** — when results diverge from the north star, the board
reconvenes, re-ratifies or vetoes, and updates `NORTH_STAR.yaml`.
## Boundaries
- **Does NOT write product/source code.**
- **Does NOT merge.**
- **Does NOT decompose, plan phases, or dispatch tasks** — it ratifies the
_what_ and _why_; planner and decomposition own the _how_.
The board deliberates and decides direction; it never touches the working tree or
the merge path. When it approves a goal, the planner expands it.
## Persona
A standing panel of senior voices, each arguing from a fixed vantage. The board is
deliberately slow and adversarial — its value is catching the expensive mistake
before a single agent-hour is spent on it.
> Doctrine: `docs/fleet/north-star.md` ('board' role = forge BOD; role library).

View File

@@ -1,36 +0,0 @@
# Code — fleet role definition
The **code** role is the fleet's primary **executor** (`class: code`). It picks up
one decomposition card and implements it to green CI on a branch, then opens a PR.
It is an **execution** role: one card, one branch, one PR.
## Mandate
1. **Implement one card to green CI** — take a single backlog card and make the
change it describes, on a dedicated branch, until the project's gates
(typecheck, lint, format, tests) pass.
2. **Open the PR via `pr-create.sh`** — once gates are green, open exactly one
pull request for the card using the standard `pr-create.sh` wrapper.
3. **Stay in card scope** — touch only the files the card calls for. No scope
creep, no opportunistic refactors outside the card's boundary.
4. **One card = one PR** — honor the decomposition contract: a card becomes a
single focused PR, never two, and a PR never bundles two cards.
## Boundaries
- **Does NOT merge.** Opening the PR is the end of the code role's authority; the
**merge-gate** role is the only approver/merger.
- **Does NOT approve or self-review** — correctness sign-off belongs to the
**review** and **security-review** roles.
- **Does NOT decompose or re-plan** — if a card is wrong or too large, it escalates
rather than silently re-scoping.
The code role writes the change and opens the PR; it never touches the merge path.
## Persona
The focused builder. It takes one well-scoped card, drives it to green, opens a
clean PR, and hands off — never reaching past the card it was given.
> Doctrine: `docs/fleet/north-star.md` (role library).

View File

@@ -1,38 +0,0 @@
# Decomposition — fleet role definition
The **decomposition** role splits the planner's FRs into **one-PR-each cards**,
wired together with `depends_on` link edges, ready for the code role to pick up.
It is a **front-office** role.
## Mandate
1. **Drive the native `mosaic fleet backlog`** — decomposition is the operator of
Mosaic's own backlog; it creates and links cards there, on Mosaic's storage
layer. It does NOT hand-roll a parallel splitter and does NOT call any external
kanban service.
2. **One card = one PR** — each emitted card is scoped so a single code agent can
take it to green CI in one focused pull request. No card spans two PRs; no PR
spans two cards.
3. **Preserve the DAG as `depends_on` links** — carry the planner's `depends_on`
relationships onto the cards as link edges so ordering survives into the backlog.
4. **Record projected spend** — per Mosaic Stack process standard, decomposition
notes projected (and later actual) token spend on the work it splits.
## Boundaries
- **Does NOT write product/source code.**
- **Does NOT merge.**
- **Does NOT start work** — it produces cards and stops. Picking up a card and
implementing it is the **code** role's job.
Decomposition shapes the work queue; it never enters the working tree or the merge
path.
## Persona
The work-breakdown specialist. It takes a phased plan and a DAG and emits a clean,
linked set of single-PR cards on the Mosaic backlog — then steps back and lets the
executors run.
> Doctrine: `docs/fleet/north-star.md` (role library); spend accounting is a process mandate.

View File

@@ -1,39 +0,0 @@
# Documentation — fleet role definition
The **documentation** role is the fleet's **prose maintainer**
(`class: documentation`). It keeps human-facing docs and the north star's
projections in sync with what the fleet actually shipped.
It is an **execution** role: docs and projections, not product code.
## Mandate
1. **Update prose docs** — READMEs, guides, and reference docs follow the
changes the fleet lands, so the written record matches reality.
2. **Update `NORTH_STAR.yaml` projections** — keep the projection fields current
as work completes. (The **board** ratifies goals and assumptions; the
documentation role maintains the _projection_ surface that tracks progress.)
3. **Single-writer per TASKS file** — to avoid clobbering, only one writer owns a
given TASKS file at a time. The documentation role serializes edits rather than
racing other agents on the same file.
4. **Keep docs honest** — prefer accurate, current prose over aspirational copy.
## Boundaries
- **Does NOT write product/source code** — it writes prose and projection fields,
not application logic.
- **Does NOT merge.** Doc changes go through the same PR + **merge-gate** path as
any other change.
- **Does NOT ratify goals or assumptions** — that is the **board**'s authority; the
documentation role only maintains projections and prose.
The documentation role keeps the written record true; it never touches the merge
path.
## Persona
The scribe of record. It makes sure the docs and the north star's projections
describe the system as it actually is, and it never lets two writers fight over one
TASKS file.
> Doctrine: `docs/fleet/north-star.md` (role library).

View File

@@ -1,42 +0,0 @@
# Merge-gate — fleet role definition
The **merge-gate** is the fleet's **sole approver and auto-merger**
(`class: merge-gate`). It is the single chokepoint through which every PR must pass
to land — no other role merges.
It is a **gate** role: the one and only merge path.
## Mandate
1. **Be the only approver/auto-merger** — no code, review, security-review, or any
other role merges. Approval-to-land flows through the merge-gate alone.
2. **Use the wrapped scripts as the ONLY merge path** — the merge-gate merges
**exclusively** by calling **`pr-merge.sh`** (the merge action, which carries the
authoritative forbidden-path guard) and **`pr-ci-wait.sh`** (to wait for green
CI before merging). These two scripts are the _only_ sanctioned merge path.
3. **Never call the raw API** — the merge-gate **does NOT** call `tea`, the raw
Gitea/forge HTTP API, or any other merge mechanism directly. Only `pr-merge.sh`
and `pr-ci-wait.sh`.
4. **Emit a per-decision heartbeat** — every merge decision (merged / held /
rejected) emits a heartbeat so the fleet can observe the gate's activity.
5. **Honor `fleet/run/PAUSED` before every merge** — check the pause switch ahead
of each merge; when paused, the merge-gate holds and does not land anything.
## Boundaries
- **Does NOT write product/source code.**
- **Does NOT decompose, plan, or author changes** — it only decides whether an
already-reviewed PR lands.
- **Does NOT merge via any path other than `pr-merge.sh` + `pr-ci-wait.sh`** — no
raw `tea`/Gitea API, ever.
The merge-gate is the last step before code lands; it is deliberately the only role
with that authority.
## Persona
The single, accountable gatekeeper. It waits for green CI (`pr-ci-wait.sh`),
respects the pause switch, merges only through `pr-merge.sh`, and records every
decision — so the fleet has exactly one trustworthy door to production.
> Doctrine: `docs/fleet/north-star.md` (role library); merge path: `pr-merge.sh` + `pr-ci-wait.sh`; forbidden paths: `pr-merge.sh` guard.

View File

@@ -1,38 +0,0 @@
# Operator — fleet role definition
The **operator** is the fleet's **escalation and control surface**
(`class: operator`). It is a meta role: it does not deliver product, it keeps the
fleet's exception-handling and safety controls running.
It is a **meta** role: control plane, not delivery.
## Mandate
1. **Consume escalations** — it is the destination for escalations raised by other
roles (e.g. the **rebase** role's genuine conflicts, blocked work, stuck cards).
2. **Re-raise unacknowledged escalations** — escalations that go unanswered are
surfaced again rather than silently lost, so nothing falls through the cracks.
3. **Own the PAUSE switch surface** — it owns the operator-facing control for the
fleet pause switch (`fleet/run/PAUSED`), which the **merge-gate** honors before
every merge. The operator can pause and resume the fleet.
4. **Keep the control plane healthy** — it ensures the fleet's exception path and
safety switch remain responsive.
## Boundaries
- **Does NOT write product/source code.**
- **Does NOT merge.** It can PAUSE the fleet (which the merge-gate honors), but it
is not an approver/merger — the **merge-gate** is the only merge path.
- **Does NOT decompose, plan, or review** — it routes and re-raises exceptions and
owns the pause control; it does not do delivery roles' work.
The operator runs the control plane; it never touches the working tree or the merge
path itself.
## Persona
The on-call dispatcher. It makes sure every escalation is seen and re-seen until
handled, and it holds the one switch that can stop the fleet when something is
wrong.
> Doctrine: `docs/fleet/north-star.md` (role library); pause switch: `fleet/run/PAUSED`.

View File

@@ -1,40 +0,0 @@
# Planner — fleet role definition
The **planner** turns ratified objectives into an executable **plan** — phased
functional requirements (FRs) wired into a `depends_on` DAG.
> **Alias:** the planner role IS the existing **orchestrator** class. The
> orchestrator _plays_ planner; this file documents the planning contract, it does
> **not** introduce a competing class. The two-agent floor (orchestrator +
> enhancer) is preserved — do not split planner into a separate persistent agent
> that would break it.
It is a **front-office** role.
## Mandate
1. **Expand objectives into phased FRs** — take a board-ratified goal and break it
into functional requirements, grouped into phases.
2. **Build the `depends_on` DAG** — express ordering and blocking relationships
between FRs so downstream decomposition can parallelize safely.
3. **Emit a plan, not tasks** — the planner's output is the phased FR/DAG
document. Splitting FRs into one-PR-each cards is the **decomposition** role's job.
4. **Re-plan on failure** — when execution diverges, the planner (orchestrator)
re-sequences the DAG rather than letting agents improvise.
## Boundaries
- **Does NOT write product/source code.**
- **Does NOT merge.**
- **Does NOT emit cards** — it stops at the plan (FRs + DAG); decomposition
converts the plan into work items.
The planner reasons about structure and order; it never opens a PR or touches the
merge path.
## Persona
The architect of the mission's shape. It thinks in phases and dependencies, hands
a clean DAG to decomposition, and keeps the orchestrator/enhancer floor intact.
> Doctrine: `docs/fleet/north-star.md` (two-agent floor + role library).

View File

@@ -1,37 +0,0 @@
# Rebase — fleet role definition
The **rebase** role is the fleet's **freshness keeper** (`class: rebase`). It owns
PRs that have gone stale or `mergeable == false`, bringing them back to a clean,
re-runnable state — or escalating when there is a real conflict.
It is an **execution** role: it operates on existing PR branches.
## Mandate
1. **Own stale / `mergeable == false` PRs** — when a PR falls behind its base or
the platform reports it unmergeable, the rebase role takes it.
2. **Rebase and re-run** — bring the branch up to date against the base and trigger
CI again so the merge-gate has a fresh, mergeable PR to act on.
3. **Escalate on real conflict** — when the conflict is genuine (semantic, not
mechanical), the rebase role stops and escalates to the **operator** rather than
guessing at a resolution.
4. **Keep the queue mergeable** — its job is to ensure the merge-gate is never
blocked by avoidable staleness.
## Boundaries
- **Does NOT merge.** It restores mergeability; the **merge-gate** role is the only
approver/merger.
- **Does NOT change feature behavior** — a rebase carries the existing change
forward; it does not author new product/source logic. Behavioral fixes go back to
the **code** role.
- **Does NOT force-resolve genuine conflicts** — it escalates them.
The rebase role keeps PR branches fresh; it never approves or merges.
## Persona
The janitor of the merge queue. It quietly keeps branches current and re-runnable,
and knows when a conflict is beyond a mechanical rebase and must be escalated.
> Doctrine: `docs/fleet/north-star.md` (role library).

View File

@@ -1,38 +0,0 @@
# Review — fleet role definition
The **review** role is the fleet's **correctness reviewer** (`class: review`). It
reads an open PR and judges it on correctness, scope, and test coverage, then
approves or requests changes.
It is an **execution** role: one open PR per pass.
## Mandate
1. **Judge correctness** — does the change do what its card says, correctly, without
introducing regressions?
2. **Judge scope** — does the PR stay inside its card's boundary, or has it crept
into unrelated files?
3. **Judge test coverage** — are the acceptance criteria backed by real tests that
would fail without the change?
4. **Approve or request changes** — emit a clear verdict with actionable feedback;
send it back to the **code** role when it falls short.
## Boundaries
- **Does NOT merge.** Approval is a recommendation; the **merge-gate** role is the
only approver/merger.
- **Does NOT write product/source code** — it reviews; it does not author the fix.
Remediation goes back to the **code** role.
- **Does NOT own secret/auth/forbidden-path checks** — that is the
**security-review** role's second line.
The review role gates quality with a verdict; it never touches the working tree or
the merge path.
## Persona
The careful reader. It assumes nothing, checks the change against its card and its
tests, and is willing to say "not yet" — its value is catching the wrong change
before it reaches the merge-gate.
> Doctrine: `docs/fleet/north-star.md` (role library).

View File

@@ -1,39 +0,0 @@
# Security-review — fleet role definition
The **security-review** role is the fleet's **second line of review**
(`class: security-review`). Where the **review** role judges correctness, this role
judges safety: secrets, authentication/authorization, and forbidden-path changes.
It is an **execution** role: one open PR per pass.
## Mandate
1. **Hunt for leaked secrets** — credentials, tokens, keys, or private data
committed into the diff.
2. **Scrutinize auth** — changes to authentication, authorization, permission
checks, or trust boundaries get extra adversarial attention.
3. **Enforce forbidden paths** — flag edits to protected files/areas. The
**authoritative forbidden-path list lives in code** — the `pr-merge.sh` guard —
not in this prompt. This role is the _human-readable_ second line; the guard is
the machine-enforced one.
4. **Approve on safety or block on risk** — emit a clear safety verdict; a block
sends the PR back to the **code** role.
## Boundaries
- **Does NOT merge.** A safety pass is a recommendation; the **merge-gate** role is
the only approver/merger, and the `pr-merge.sh` guard is the enforced gate.
- **Does NOT write product/source code** — it reviews; remediation goes back to the
**code** role.
- **Does NOT redefine the forbidden-path list** — it defers to the `pr-merge.sh`
guard as the source of truth.
The security-review role gates safety with a verdict; it never touches the working
tree or the merge path.
## Persona
The adversary on your side. It reads every diff asking "how does this get exploited
or leak?" — the second, security-focused pair of eyes before the merge-gate.
> Doctrine: `docs/fleet/north-star.md` (role library); forbidden paths: `pr-merge.sh` guard.

View File

@@ -1,37 +0,0 @@
# Session-review — fleet role definition
The **session-review** role runs the fleet's **post-task retrospective**
(`class: session-review`). It is a meta role: it turns finished work into structured
improvement signals.
It is a **meta** role: learning, not delivery.
## Mandate
1. **Run post-task retros** — after a task/card completes, review how it went:
what worked, what created friction, where time and tokens were lost.
2. **Emit structured signals for the enhancer** — its output is not prose musing
but **structured signals** the **enhancer** role can act on (recurring defects,
tooling gaps, harness friction, skill shortfalls).
3. **Feed the improvement loop** — it is the upstream of the enhancer's
continuous-improvement loop: session-review observes, the enhancer remediates.
4. **Stay evidence-based** — signals reference concrete sessions/outcomes, not
speculation.
## Boundaries
- **Does NOT write product/source code.**
- **Does NOT merge.**
- **Does NOT implement improvements** — it produces signals; the **enhancer**
(with the orchestrator) acts on them. Session-review diagnoses; it does not fix.
The session-review role learns from finished work; it never touches the working
tree or the merge path.
## Persona
The retrospective analyst. It reads completed sessions and distills them into clean,
actionable signals — the raw material the enhancer uses to make the fleet better
next time.
> Doctrine: `docs/fleet/north-star.md` (role library); consumed by the enhancer role.

View File

@@ -1,37 +0,0 @@
# Site-tester — fleet role definition
The **site-tester** role is the fleet's **runtime verifier** (`class: site-tester`).
Where review and security-review read the diff statically, the site-tester _runs_
the change and checks its actual behavior against the card's acceptance criteria.
It is an **execution** role: behavioral verification per PR/card.
## Mandate
1. **Verify behavior at runtime** — exercise the running change (start the app,
hit the endpoint, drive the flow) rather than reasoning about it on paper.
2. **Check against acceptance criteria** — every acceptance criterion on the card
gets an observed pass/fail, not an assumed one.
3. **Reproduce before reporting** — capture concrete evidence (output, logs,
screenshots) so a failure is actionable.
4. **Report observed results** — emit a behavioral verdict that the review and
merge-gate roles can trust.
## Boundaries
- **Does NOT merge.** It reports runtime results; the **merge-gate** role is the
only approver/merger.
- **Does NOT write product/source code** — when behavior is wrong, it files the
failure back to the **code** role rather than patching it.
- **Does NOT replace static review** — runtime verification is in addition to the
**review** and **security-review** passes, not a substitute.
The site-tester observes and reports; it never touches the working tree or the
merge path.
## Persona
The skeptic who insists on running it. It trusts observed behavior over claimed
behavior, and turns "should work" into "verified works" — or a concrete bug report.
> Doctrine: `docs/fleet/north-star.md` (role library).

View File

@@ -18,11 +18,11 @@
"properties": {
"socket_name": {
"type": "string",
"default": "mosaic-fleet"
"default": "mosaic-factory"
},
"socketName": {
"type": "string",
"default": "mosaic-fleet"
"default": "mosaic-factory"
},
"holder_session": {
"type": "string",

View File

@@ -25,9 +25,7 @@ INSTALL_MODE="${MOSAIC_INSTALL_MODE:-prompt}"
# User-created content in these paths survives rsync --delete.
#
# fleet/* — the framework SEEDS only fleet/examples, fleet/roles, and
# fleet/roster.schema.json (synced normally — every fleet/roles/*.md role contract
# lands automatically via this sync, so no per-file entry is needed). The user's
# own fleet files MUST
# fleet/roster.schema.json (synced normally). The user's own fleet files MUST
# survive `mosaic update` (which runs this sync automatically): the active
# roster (`fleet/roster.yaml` + any other `fleet/*.yaml`), per-agent env
# (`fleet/agents/`), and heartbeat run dir (`fleet/run/`). Without these, an

View File

@@ -33,7 +33,7 @@ Per-agent overrides live outside the package in:
Example:
```dotenv
MOSAIC_TMUX_SOCKET=mosaic-fleet
MOSAIC_TMUX_SOCKET=mosaic-factory
MOSAIC_AGENT_RUNTIME=claude
MOSAIC_AGENT_WORKDIR=$HOME/src/your-project
# Optional escape hatch for PoC/canary agents:
@@ -50,8 +50,8 @@ 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-fleet ls
tmux -L mosaic-factory ls
```
Do not use `tmux kill-server` without `-L mosaic-fleet`; this pattern is meant
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

@@ -6,7 +6,7 @@ After=default.target
[Service]
Type=oneshot
RemainAfterExit=yes
Environment=MOSAIC_TMUX_SOCKET=mosaic-fleet
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'

View File

@@ -3,7 +3,7 @@ set -euo pipefail
AGENT_NAME=${1:-${MOSAIC_AGENT_NAME:-}}
# Absent socket ⇒ the LITERAL default tmux socket (no -L). The roster's
# socket_name is honored when set; absent never silently becomes mosaic-fleet
# socket_name is honored when set; absent never silently becomes mosaic-factory
# (spawn stays consistent with the onboarding cheat-sheet + fleet ps observe).
MOSAIC_TMUX_SOCKET=${MOSAIC_TMUX_SOCKET:-}
MOSAIC_AGENT_RUNTIME=${MOSAIC_AGENT_RUNTIME:-pi}
@@ -122,85 +122,6 @@ fi
mkdir -p "$MOSAIC_AGENT_WORKDIR"
# ── Pre-trust the workdir for the Claude runtime ─────────────────────────────
# Claude Code shows a one-time "Is this a project you trust?" folder-trust gate
# the first time it opens a directory. A fleet-launched agent has no human to
# answer it, so the pane stalls forever at the prompt while its heartbeat keeps
# reporting "healthy" (the pane process IS alive — it's just blocked).
#
# IMPORTANT: --dangerously-skip-permissions does NOT bypass this gate, and
# neither does `trustedProjectDirectories` in settings.json (verified empirically
# 2026-06-24). The ONLY thing the gate honors is the per-project record in
# ~/.claude.json: projects["<dir>"].hasTrustDialogAccepted == true (exactly what
# answering the prompt writes). So we pre-seed that record here.
#
# Idempotent, atomic, best-effort: any failure is non-fatal (the agent still
# launches — worst case it stalls on the gate, i.e. the pre-fix status quo).
# Only the claude runtime needs this; codex/pi have no such gate.
_ensure_claude_workdir_trusted() {
local workdir="$1"
# The path claude keys on is the resolved cwd it is launched in.
local rp
rp=$(cd "$workdir" 2>/dev/null && pwd -P) || rp="$workdir"
# ~/.claude.json lives next to the claude config dir; honor CLAUDE_CONFIG_DIR.
local claude_json="${MOSAIC_CLAUDE_JSON:-${CLAUDE_CONFIG_DIR:+$CLAUDE_CONFIG_DIR/.claude.json}}"
claude_json="${claude_json:-$HOME/.claude.json}"
if ! command -v python3 >/dev/null 2>&1; then
echo "WARNING: python3 not found; cannot pre-trust '$rp' for claude (agent may stall on the folder-trust gate)" >&2
return 1
fi
# Serialize concurrent agent launches that share ~/.claude.json (flock if available).
local lock="${claude_json}.mosaic-lock"
_seed() {
MOSAIC_CJ="$claude_json" MOSAIC_TRUST_DIR="$rp" python3 - <<'PY'
import json, os, sys, tempfile
cj = os.environ["MOSAIC_CJ"]
d = os.environ["MOSAIC_TRUST_DIR"]
try:
data = json.load(open(cj)) if os.path.exists(cj) else {}
if not isinstance(data, dict):
data = {}
except Exception:
# Never corrupt an unreadable/partial file — bail without writing.
sys.exit(2)
projects = data.setdefault("projects", {})
entry = projects.get(d)
if not isinstance(entry, dict):
entry = {}
projects[d] = entry
if entry.get("hasTrustDialogAccepted") is True:
sys.exit(0) # already trusted — nothing to do
entry["hasTrustDialogAccepted"] = True
tmp_dir = os.path.dirname(cj) or "."
fd, tmp = tempfile.mkstemp(dir=tmp_dir, prefix=".claude.json.mosaic.")
try:
with os.fdopen(fd, "w") as f:
json.dump(data, f, indent=2)
os.replace(tmp, cj) # atomic
except Exception:
try:
os.unlink(tmp)
except OSError:
pass
sys.exit(3)
PY
}
if command -v flock >/dev/null 2>&1; then
( flock 9; _seed ) 9>"$lock" 2>/dev/null || _seed
else
_seed
fi
}
case "$MOSAIC_AGENT_RUNTIME" in
claude)
_ensure_claude_workdir_trusted "$MOSAIC_AGENT_WORKDIR" \
|| echo "WARNING: could not pre-trust workdir for claude agent $AGENT_NAME" >&2
;;
esac
# ── Launch the tmux session (no exec — we continue to wire the heartbeat) ────
_tmux new-session -d -s "$AGENT_NAME" -c "$MOSAIC_AGENT_WORKDIR" \
bash -c "$PANE_SHELL_SNIPPET"

View File

@@ -128,8 +128,8 @@ PY
merge_gitea_with_api() {
local host="$1" api_url token basic_auth body_file raw_code payload
api_url="https://${host}/api/v1/repos/${OWNER}/${REPO}/pulls/${PR_NUMBER}/merge"
mkdir -p "${AGENT_WORK_ROOT:-${HOME:-/tmp}/mosaic/agent-work}"
body_file=$(mktemp "${AGENT_WORK_ROOT:-${HOME:-/tmp}/mosaic/agent-work}/pr-merge-api-response.XXXXXX")
mkdir -p "${AGENT_WORK_ROOT:-/home/hermes/agent-work}"
body_file=$(mktemp "${AGENT_WORK_ROOT:-/home/hermes/agent-work}/pr-merge-api-response.XXXXXX")
payload='{"Do":"squash"}'
token=$(get_gitea_token "$host" || true)
@@ -214,8 +214,8 @@ case "$PLATFORM" in
TEA_LOGIN="$(get_gitea_login_for_host "$HOST" || true)"
if [[ -n "$TEA_LOGIN" ]]; then
mkdir -p "${AGENT_WORK_ROOT:-${HOME:-/tmp}/mosaic/agent-work}"
TEA_ERROR_FILE=$(mktemp "${AGENT_WORK_ROOT:-${HOME:-/tmp}/mosaic/agent-work}/pr-merge-tea-error.XXXXXX")
mkdir -p "${AGENT_WORK_ROOT:-/home/hermes/agent-work}"
TEA_ERROR_FILE=$(mktemp "${AGENT_WORK_ROOT:-/home/hermes/agent-work}/pr-merge-tea-error.XXXXXX")
if tea pr merge "$PR_NUMBER" --style squash --repo "$OWNER/$REPO" --login "$TEA_LOGIN" 2> "$TEA_ERROR_FILE"; then
rm -f "$TEA_ERROR_FILE"
elif is_known_tea_empty_identity_failure "$TEA_ERROR_FILE"; then

View File

@@ -4,7 +4,7 @@
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
WORK_ROOT="${AGENT_WORK_ROOT:-${HOME:-/tmp}/mosaic/agent-work}"
WORK_ROOT="${AGENT_WORK_ROOT:-/home/hermes/agent-work}"
SANDBOX="$WORK_ROOT/pr-merge-empty-uid-test-$$"
MOCK_BIN="$SANDBOX/bin"
REPO_DIR="$SANDBOX/repo"

View File

@@ -2,20 +2,12 @@
when:
- event: [push, pull_request, manual]
# Dependencies are installed ONCE in the `install` step and every downstream
# step depends on it, reusing the populated node_modules from the shared
# workspace volume. Do NOT re-run `npm ci` per step — that pays the full cold
# install (network fetch + native rebuilds) N times and is the dominant cost
# in a pipeline.
#
# For best results, replace `&node_image` with a pre-baked CI base image that
# ships your toolchain (python3/make/g++ for native modules) and a warm npm
# cache, then keep `--prefer-offline` so installs resolve from the cache. See
# the Mosaic Stack repo's Dockerfile.ci + .woodpecker/ci-image.yml for the
# baked-image pattern.
variables:
- &node_image 'node:20-alpine'
- &gitleaks_image 'ghcr.io/gitleaks/gitleaks:v8.24.0'
- &install_deps |
corepack enable
npm ci --ignore-scripts
steps:
# Secret scanning (runs in parallel with install, no deps)
@@ -25,18 +17,15 @@ steps:
- gitleaks git --redact --verbose --log-opts="HEAD~1..HEAD"
depends_on: []
# Single cached install. Every other step depends on this and reuses the
# node_modules it produces in the shared workspace.
install:
image: *node_image
commands:
- corepack enable
- npm ci --ignore-scripts --prefer-offline
depends_on: []
- *install_deps
security-audit:
image: *node_image
commands:
- *install_deps
- npm audit --audit-level=high
depends_on:
- install
@@ -46,6 +35,7 @@ steps:
environment:
SKIP_ENV_VALIDATION: 'true'
commands:
- *install_deps
- npm run lint
depends_on:
- install
@@ -55,6 +45,7 @@ steps:
environment:
SKIP_ENV_VALIDATION: 'true'
commands:
- *install_deps
- npm run type-check
depends_on:
- install
@@ -64,6 +55,7 @@ steps:
environment:
SKIP_ENV_VALIDATION: 'true'
commands:
- *install_deps
- npm run test -- --coverage --coverageThreshold='{"global":{"branches":80,"functions":80,"lines":80,"statements":80}}'
depends_on:
- install
@@ -74,6 +66,7 @@ steps:
SKIP_ENV_VALIDATION: 'true'
NODE_ENV: 'production'
commands:
- *install_deps
- npm run build
depends_on:
- lint

View File

@@ -35,7 +35,7 @@ delivers reliably to local OR remote panes.
agent-send.sh -s <dst_session> -m "message"
# Local target on a Mosaic fleet socket
agent-send.sh -L mosaic-fleet -s '=coder0' -m "message"
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"
@@ -58,9 +58,9 @@ commands do not fall back to tmux's prefix matching behavior.
Durable Mosaic fleets should use a dedicated tmux socket, for example:
```bash
tmux -L mosaic-fleet ls
agent-send.sh -L mosaic-fleet -s '=coder0' -m "status?"
send-message.sh -L mosaic-fleet -t '=coder0' -m "raw pane message"
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

View File

@@ -12,10 +12,6 @@
# ambiguity about lanes or origin. Recipients replying should FLIP the
# 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
# Reliable submission into an interactive REPL (Claude Code / Codex) is fiddly:
# 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] -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 -s mos-claude --class terminal-log -m "ACK — received"
# echo "msg" | agent-send.sh [-L socket] -H user@host -s <dst_session>
#
# OPTIONS
@@ -41,61 +36,27 @@
# Default: local hostname, or (remote) resolved via one ssh.
# -m MESSAGE message text (single- or multi-line)
# -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)
# -r N Enter-flush attempts passed through (default 2)
# -v verbose: print pane tail after delivery
# -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)
# 0 delivered/queued · 1 target not found · 2 still draft · 3 usage error
set -uo pipefail
SELF_DIR=$(cd -- "$(dirname -- "$0")" && pwd)
# Sender is overridable via env purely for testing (inject a capture stub). The
# default is the canonical send-message.sh beside this script; production callers
# never set AGENT_SEND_SENDER, so behavior is unchanged.
SENDER="${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[@]}"}
SENDER="$SELF_DIR/send-message.sh"
DST_SESSION=""; SSH_TARGET=""; DST_HOST=""; MSG=""; FILE=""; SOCKET_NAME=""
SRC_LABEL=""; RETRIES=2; VERBOSE=0; CLASS=""
usage() { sed -n '2,/^set -uo pipefail/{/^set -uo pipefail/d;p}' "$0"; exit "${1:-3}"; }
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:C:vh" o; do
while getopts "L: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 ;;
C) CLASS=$OPTARG ;;
r) RETRIES=$OPTARG ;; v) VERBOSE=1 ;; h) usage 0 ;; *) usage 3 ;;
esac
done
@@ -103,17 +64,6 @@ done
[ -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; }
# 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.
if [ -n "$FILE" ]; then [ -r "$FILE" ] || { echo "ERROR: cannot read $FILE" >&2; exit 3; }; MSG=$(cat -- "$FILE")
elif [ -z "$MSG" ] && [ ! -t 0 ]; then MSG=$(cat)
@@ -140,7 +90,7 @@ if [ -z "$DST_HOST" ]; then
fi
fi
PREAMBLE="[${SRC_LABEL} -> ${DST_HOST}:${DST_SESSION}${CLASS_TOKEN}]"
PREAMBLE="[${SRC_LABEL} -> ${DST_HOST}:${DST_SESSION}]"
FULL="${PREAMBLE} ${MSG}"
B64=$(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",
"version": "0.0.44",
"version": "0.0.40",
"repository": {
"type": "git",
"url": "https://git.mosaicstack.dev/mosaicstack/stack.git",

View File

@@ -30,7 +30,6 @@ import {
refreshActiveFleetUnits,
readRosterAgentNames,
buildRelaunchCommands,
checkFrameworkDrift,
FRAMEWORK_RESEED_PACKAGE,
} from './runtime/update-checker.js';
import { runWizard } from './wizard.js';
@@ -419,48 +418,6 @@ program
// checkForAllUpdates imported statically above
const { execSync } = await import('node:child_process');
// Re-seed the framework from the freshly-installed package, propagate shipped
// systemd unit fixes to the active units, and (opt-in) relaunch durable
// agents. Shared by the "packages updated" and the "framework drift" paths.
const reseedFramework = (reason: string): void => {
console.log(reason);
const reseed = runFrameworkReseed();
if (!reseed.ok) {
console.error(
`\n⚠ Framework re-seed skipped: ${reseed.reason ?? 'unknown'}.\n` +
' Activate manually: bash "$(npm root -g)/@mosaicstack/mosaic/framework/install.sh" ' +
'(MOSAIC_SYNC_ONLY=1 MOSAIC_INSTALL_MODE=keep)',
);
return;
}
console.log('✔ Framework re-seeded.');
// Propagate shipped systemd unit fixes to the ACTIVE units (re-seed only
// touches ~/.config/mosaic/systemd/user; systemd runs ~/.config/systemd/user).
const units = refreshActiveFleetUnits();
if (units.refreshed.length > 0) {
console.log(`✔ Refreshed ${units.refreshed.length} active systemd unit(s).`);
}
const agents = readRosterAgentNames();
if (agents.length === 0) return;
if (opts.relaunch) {
console.log(`\nRelaunching ${agents.length} fleet agent(s) to pick up the new runtime…`);
for (const restart of buildRelaunchCommands(agents)) {
try {
execSync(restart.join(' '), { stdio: 'inherit', timeout: 30_000 });
} catch {
console.error(` ⚠ failed to restart agent — run: ${restart.join(' ')}`);
}
}
console.log('✔ Agents relaunched.');
} else {
console.log(
`\n ${agents.length} fleet agent(s) are still running the previous runtime. ` +
'Restart them to activate the update:\n mosaic update --relaunch ' +
'(or: mosaic fleet restart <agent>)',
);
}
};
console.log('Checking for updates…');
const results = checkForAllUpdates({ skipCache: true });
@@ -475,18 +432,6 @@ program
process.exit(1);
}
console.log('\n✔ All packages up to date.');
// #642: the CLI may have been upgraded outside `mosaic update` (e.g. a
// direct `npm i -g`), leaving the framework files stale even though no
// package is reported outdated. Detect that via the framework version and
// re-seed so shipped launcher/runtime fixes still activate.
const drift = checkFrameworkDrift();
if (drift.drifted && opts.reseed !== false) {
reseedFramework(
`\nFramework drift detected (on-disk v${drift.installed} < bundled v${drift.bundled}) — ` +
'the CLI was updated outside `mosaic update`. Re-seeding framework files into ' +
'~/.config/mosaic (data-safe; keeps your edits)…',
);
}
return;
}
@@ -511,17 +456,52 @@ program
// F3-m3 / R13: the CLI is updated, but the framework files in
// ~/.config/mosaic/ are still the previous version. Re-seed them from the
// freshly-installed package so shipped launcher/runtime changes ACTIVATE.
// Re-seed when the framework-bearing package itself updated OR the on-disk
// framework is older than the freshly-installed one (#642 — e.g. only
// sibling packages were outdated but the CLI was already ahead).
// Only when the framework-bearing package itself updated.
const mosaicUpdated = outdated.some(
(r: { package: string }) => r.package === FRAMEWORK_RESEED_PACKAGE,
);
const drift = checkFrameworkDrift();
if ((mosaicUpdated || drift.drifted) && opts.reseed !== false) {
reseedFramework(
if (mosaicUpdated && opts.reseed !== false) {
console.log(
'\nRe-seeding framework files into ~/.config/mosaic (data-safe; keeps your edits)…',
);
const reseed = runFrameworkReseed();
if (reseed.ok) {
console.log('✔ Framework re-seeded.');
// Propagate shipped systemd unit fixes to the ACTIVE units (re-seed only
// touches ~/.config/mosaic/systemd/user; systemd runs ~/.config/systemd/user).
const units = refreshActiveFleetUnits();
if (units.refreshed.length > 0) {
console.log(`✔ Refreshed ${units.refreshed.length} active systemd unit(s).`);
}
const agents = readRosterAgentNames();
if (agents.length > 0) {
if (opts.relaunch) {
console.log(
`\nRelaunching ${agents.length} fleet agent(s) to pick up the new runtime…`,
);
for (const restart of buildRelaunchCommands(agents)) {
try {
execSync(restart.join(' '), { stdio: 'inherit', timeout: 30_000 });
} catch {
console.error(` ⚠ failed to restart agent — run: ${restart.join(' ')}`);
}
}
console.log('✔ Agents relaunched.');
} else {
console.log(
`\n ${agents.length} fleet agent(s) are still running the previous runtime. ` +
'Restart them to activate the update:\n mosaic update --relaunch ' +
'(or: mosaic fleet restart <agent>)',
);
}
}
} else {
console.error(
`\n⚠ Framework re-seed skipped: ${reseed.reason ?? 'unknown'}.\n` +
' Activate manually: bash "$(npm root -g)/@mosaicstack/mosaic/framework/install.sh" ' +
'(MOSAIC_SYNC_ONLY=1 MOSAIC_INSTALL_MODE=keep)',
);
}
}
});

View File

@@ -19,20 +19,17 @@ import {
buildSystemdShowCommand,
buildTmuxListPanesCommand,
buildTmuxListSessionsCommand,
classifyReadiness,
classifySendResult,
countOrchestrators,
countEnhancers,
detectDrift,
enableFleetUnits,
FLEET_PROFILES,
HEARTBEAT_IDLE_THRESHOLD_SECONDS,
generateAgentEnv,
getDefaultOperatorSourceLabel,
getDefaultTenantAndHost,
getRosterAgent,
heartbeatPath,
idleThresholdSeconds,
isSendAccepted,
loadFleetRoster,
mergeAgentEnv,
@@ -98,7 +95,6 @@ describe('registerFleetCommand', () => {
expect(agent).toBeDefined();
expect(agent!.options.map((option) => option.long)).toContain('--list');
expect(agent!.commands.map((command) => command.name()).sort()).toEqual([
'comms-block',
'reset',
'roster',
'send',
@@ -136,14 +132,14 @@ describe('fleet roster parsing', () => {
const roster = await loadFleetRoster(rosterPath);
expect(roster.tmux.socketName).toBe(''); // absent ⇒ default socket (no -L), not mosaic-fleet
expect(roster.tmux.socketName).toBe(''); // absent ⇒ default socket (no -L), not mosaic-factory
expect(roster.tmux.holderSession).toBe('_holder');
expect(roster.agents).toHaveLength(1);
expect(getRosterAgent(roster, 'canary-pi').runtime).toBe('pi');
});
it('socketArgs: named socket → -L <name>; empty → no -L (default socket)', () => {
expect(socketArgs('mosaic-fleet')).toEqual(['-L', 'mosaic-fleet']);
expect(socketArgs('mosaic-factory')).toEqual(['-L', 'mosaic-factory']);
expect(socketArgs('')).toEqual([]);
});
@@ -156,14 +152,14 @@ describe('fleet roster parsing', () => {
'version: 1',
'transport: tmux',
'tmux:',
' socket_name: mosaic-fleet',
' socket_name: mosaic-factory',
'agents:',
' - name: canary-pi',
' runtime: pi',
].join('\n'),
);
const roster = await loadFleetRoster(rosterPath);
expect(roster.tmux.socketName).toBe('mosaic-fleet');
expect(roster.tmux.socketName).toBe('mosaic-factory');
expect(buildTmuxListSessionsCommand(roster.tmux.socketName)).toContain('-L');
});
@@ -193,7 +189,7 @@ describe('fleet roster parsing', () => {
JSON.stringify({
version: 1,
transport: 'tmux',
tmux: { socket_name: 'mosaic-fleet' },
tmux: { socket_name: 'mosaic-factory' },
defaults: { working_directory: '/srv/mosaic' },
agents: [{ name: 'coder0', runtime: 'codex', class: 'implementer' }],
}),
@@ -206,7 +202,7 @@ describe('fleet roster parsing', () => {
'MOSAIC_AGENT_RUNTIME=codex',
'MOSAIC_AGENT_MODEL=',
'MOSAIC_AGENT_WORKDIR=/srv/mosaic',
'MOSAIC_TMUX_SOCKET=mosaic-fleet',
'MOSAIC_TMUX_SOCKET=mosaic-factory',
'',
].join('\n'),
);
@@ -217,7 +213,7 @@ describe('fleet roster parsing', () => {
'MOSAIC_AGENT_NAME=coder0',
'MOSAIC_AGENT_RUNTIME=codex',
'MOSAIC_AGENT_WORKDIR=/srv/new',
'MOSAIC_TMUX_SOCKET=mosaic-fleet',
'MOSAIC_TMUX_SOCKET=mosaic-factory',
'',
].join('\n');
const existing = [
@@ -235,7 +231,7 @@ describe('fleet roster parsing', () => {
'MOSAIC_AGENT_NAME=coder0',
'MOSAIC_AGENT_RUNTIME=codex',
'MOSAIC_AGENT_WORKDIR=/srv/new',
'MOSAIC_TMUX_SOCKET=mosaic-fleet',
'MOSAIC_TMUX_SOCKET=mosaic-factory',
'MOSAIC_AGENT_COMMAND=/home/jarvis/.config/mosaic/fleet/canary.sh',
'# site note',
'',
@@ -328,7 +324,7 @@ describe('fleet roster parsing', () => {
const localCanary = await loadFleetRoster(join(examplesDir, 'local-canary.yaml'));
expect(minimal.agents.map((agent) => agent.name)).toEqual(['canary-pi']);
expect(localCanary.tmux.socketName).toBe('mosaic-fleet');
expect(localCanary.tmux.socketName).toBe('mosaic-factory');
expect(localCanary.agents.map((agent) => agent.name)).toEqual(['lead', 'coder0', 'reviewer0']);
expect(localCanaryText).not.toMatch(/usc|ultron|secrev/i);
});
@@ -353,11 +349,11 @@ describe('fleet command construction', () => {
it('builds socket-scoped agent send commands', () => {
const paths = resolveFleetPaths('/home/test/.config/mosaic');
expect(
buildAgentSendCommand(paths, 'coder0', 'hello', 'mosaic-fleet', 'operator:mosaic-cli'),
buildAgentSendCommand(paths, 'coder0', 'hello', 'mosaic-factory', 'operator:mosaic-cli'),
).toEqual([
'/home/test/.config/mosaic/tools/tmux/agent-send.sh',
'-L',
'mosaic-fleet',
'mosaic-factory',
'-S',
'operator:mosaic-cli',
'-s',
@@ -845,15 +841,15 @@ describe('fleet ps — command construction', () => {
});
it('builds exact tmux list-panes command with the correct format string', () => {
expect(buildTmuxListPanesCommand('canary-pi', 'mosaic-fleet')).toEqual([
expect(buildTmuxListPanesCommand('canary-pi', 'mosaic-factory')).toEqual([
'tmux',
'-L',
'mosaic-fleet',
'mosaic-factory',
'list-panes',
'-t',
'=canary-pi:0.0',
'-F',
'#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity} #{window_activity} #{session_activity}',
'#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity}',
]);
});
@@ -936,125 +932,6 @@ describe('fleet ps — heartbeat parsing', () => {
});
});
describe('fleet ps — readiness thresholds', () => {
const savedIdle = process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD;
afterEach(() => {
if (savedIdle === undefined) delete process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD;
else process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD = savedIdle;
});
it('uses the default activity threshold when env is unset', () => {
delete process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD;
expect(idleThresholdSeconds()).toBe(HEARTBEAT_IDLE_THRESHOLD_SECONDS);
});
it('honors a positive integer activity threshold from env', () => {
process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD = '120';
expect(idleThresholdSeconds()).toBe(120);
});
it('falls back to the default for invalid activity thresholds', () => {
process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD = '0';
expect(idleThresholdSeconds()).toBe(HEARTBEAT_IDLE_THRESHOLD_SECONDS);
});
});
describe('fleet ps — readiness classification', () => {
const thresholds = { idleThresholdSeconds: 300 };
it('reports dead when the pane is not alive', () => {
expect(
classifyReadiness(
{ paneAlive: false, hbHealth: 'healthy', hbStatus: 'busy', idleSeconds: 0 },
thresholds,
),
).toBe('dead');
});
it('reports unknown when heartbeat health is unknown', () => {
expect(
classifyReadiness(
{ paneAlive: true, hbHealth: 'unknown', hbStatus: null, idleSeconds: 0 },
thresholds,
),
).toBe('unknown');
});
it('reports stale when heartbeat health is stale', () => {
expect(
classifyReadiness(
{ paneAlive: true, hbHealth: 'stale', hbStatus: 'busy', idleSeconds: 1_000 },
thresholds,
),
).toBe('stale');
});
it('reports working when heartbeat status is busy, even after the activity threshold', () => {
expect(
classifyReadiness(
{ paneAlive: true, hbHealth: 'healthy', hbStatus: 'busy', idleSeconds: 2_000 },
thresholds,
),
).toBe('working');
});
it('reports working when pane idle seconds are null', () => {
expect(
classifyReadiness(
{ paneAlive: true, hbHealth: 'healthy', hbStatus: 'ok', idleSeconds: null },
thresholds,
),
).toBe('working');
});
it('reports working when pane idle seconds are undefined', () => {
expect(
classifyReadiness({ paneAlive: true, hbHealth: 'healthy', hbStatus: 'ok' }, thresholds),
).toBe('working');
});
it('reports working when pane idle seconds are non-finite', () => {
expect(
classifyReadiness(
{ paneAlive: true, hbHealth: 'healthy', hbStatus: 'ok', idleSeconds: Number.NaN },
thresholds,
),
).toBe('working');
});
it('reports available at the activity threshold boundary', () => {
expect(
classifyReadiness(
{ paneAlive: true, hbHealth: 'healthy', hbStatus: 'ok', idleSeconds: 300 },
thresholds,
),
).toBe('available');
});
it('reports working below the activity threshold', () => {
expect(
classifyReadiness(
{ paneAlive: true, hbHealth: 'healthy', hbStatus: 'ok', idleSeconds: 299 },
thresholds,
),
).toBe('working');
});
it('reports very long idle as available, not stuck', () => {
const readiness = classifyReadiness(
{ paneAlive: true, hbHealth: 'healthy', hbStatus: 'ok', idleSeconds: 100_000 },
thresholds,
);
expect(readiness).toBe('available');
expect(readiness).not.toBe('stuck');
});
});
describe('fleet ps — systemd show parsing', () => {
it('parses ActiveState, SubState, UnitFileState from systemctl show output', () => {
const output = 'ActiveState=active\nSubState=running\nUnitFileState=enabled\n';
@@ -1075,11 +952,9 @@ describe('fleet ps — systemd show parsing', () => {
describe('fleet ps — tmux list-panes parsing', () => {
const NOW_MS = 1_700_000_000_000;
it('uses pane_activity when present', () => {
const paneActivityEpoch = Math.floor((NOW_MS - 30_000) / 1000); // 30s ago
const windowActivityEpoch = Math.floor((NOW_MS - 60_000) / 1000); // 60s ago
const sessionActivityEpoch = Math.floor((NOW_MS - 90_000) / 1000); // 90s ago
const output = `12345 claude 0 ${paneActivityEpoch} ${windowActivityEpoch} ${sessionActivityEpoch}\n`;
it('parses alive pane with pid, command, and idle time', () => {
const activityEpoch = Math.floor((NOW_MS - 30_000) / 1000); // 30s ago
const output = `12345 claude 0 ${activityEpoch}\n`;
const result = parseTmuxListPanes(output, NOW_MS);
expect(result.pid).toBe(12345);
expect(result.command).toBe('claude');
@@ -1087,45 +962,8 @@ describe('fleet ps — tmux list-panes parsing', () => {
expect(result.idleSeconds).toBe(30);
});
it('uses window_activity when pane_activity is empty', () => {
const windowActivityEpoch = Math.floor((NOW_MS - 45_000) / 1000); // 45s ago
const sessionActivityEpoch = Math.floor((NOW_MS - 90_000) / 1000); // 90s ago
const output = `12345 node 0 ${windowActivityEpoch} ${sessionActivityEpoch}\n`;
expect(output).toContain('0 '); // empty pane_activity preserves index alignment
const result = parseTmuxListPanes(output, NOW_MS);
expect(result.pid).toBe(12345);
expect(result.command).toBe('node');
expect(result.dead).toBe(false);
expect(result.idleSeconds).toBe(45);
});
it('uses session_activity when pane_activity and window_activity are empty', () => {
const sessionActivityEpoch = Math.floor((NOW_MS - 75_000) / 1000); // 75s ago
const output = `12345 node 0 ${sessionActivityEpoch}\n`;
const result = parseTmuxListPanes(output, NOW_MS);
expect(result.idleSeconds).toBe(75);
});
it('reports null idleSeconds when all activity sources are empty', () => {
const output = '12345 node 0 \n';
const result = parseTmuxListPanes(output, NOW_MS);
expect(result.idleSeconds).toBeNull();
});
it('computes exact idle seconds from now minus epoch seconds', () => {
const activityEpoch = 1_699_999_877;
const result = parseTmuxListPanes(`12345 claude 0 ${activityEpoch} 0 0\n`, NOW_MS);
expect(result.idleSeconds).toBe(123);
});
it('clamps future activity epochs to 0 idle seconds', () => {
const futureActivityEpoch = Math.floor((NOW_MS + 30_000) / 1000);
const result = parseTmuxListPanes(`12345 claude 0 ${futureActivityEpoch} 0 0\n`, NOW_MS);
expect(result.idleSeconds).toBe(0);
});
it('reports dead pane when pane_dead=1', () => {
const output = `0 bash 1 0 0 0\n`;
const output = `0 bash 1 0\n`;
const result = parseTmuxListPanes(output, NOW_MS);
expect(result.dead).toBe(true);
});
@@ -1329,7 +1167,7 @@ describe('fleet install — auto-enable units for boot-survival', () => {
const minimalRoster: FleetRoster = {
version: 1,
transport: 'tmux',
tmux: { socketName: 'mosaic-fleet', holderSession: '_holder' },
tmux: { socketName: 'mosaic-factory', holderSession: '_holder' },
defaults: { workingDirectory: '~/src' },
runtimes: { codex: { resetCommand: '/clear' } },
agents: [{ name: 'coder0', runtime: 'codex', className: 'worker' }],
@@ -1351,7 +1189,7 @@ describe('fleet install — auto-enable units for boot-survival', () => {
const minimalRoster: FleetRoster = {
version: 1,
transport: 'tmux',
tmux: { socketName: 'mosaic-fleet', holderSession: '_holder' },
tmux: { socketName: 'mosaic-factory', holderSession: '_holder' },
defaults: { workingDirectory: '~/src' },
runtimes: { codex: { resetCommand: '/clear' } },
agents: [{ name: 'coder0', runtime: 'codex', className: 'worker' }],
@@ -1378,7 +1216,7 @@ describe('fleet install — auto-enable units for boot-survival', () => {
const minimalRoster: FleetRoster = {
version: 1,
transport: 'tmux',
tmux: { socketName: 'mosaic-fleet', holderSession: '_holder' },
tmux: { socketName: 'mosaic-factory', holderSession: '_holder' },
defaults: { workingDirectory: '~/src' },
runtimes: { codex: { resetCommand: '/clear' } },
agents: [{ name: 'coder0', runtime: 'codex', className: 'worker' }],
@@ -1485,9 +1323,8 @@ describe('fleet ps — JSON output shape (FR-6)', () => {
// boot-enable warning: active + disabled
expect(row.bootEnableWarning).toBe(true);
// heartbeat missing → unknown readiness preserves existing display semantics
// heartbeat missing → unknown
expect(row.heartbeat.health).toBe('unknown');
expect(row.readiness).toBe('unknown');
expect(row.name).toBe('canary-pi');
expect(row.runtime).toBe('pi');
@@ -1549,94 +1386,12 @@ describe('fleet ps — command sequences issued', () => {
});
});
describe('fleet ps — readiness table output', () => {
it('renders available in HB column without idle/stuck alarm flags', async () => {
const home = await mkdtemp(join(tmpdir(), 'mosaic-fleet-'));
const rosterPath = join(home, 'fleet', 'roster.yaml');
const runDir = join(home, 'fleet', 'run');
await mkdir(runDir, { recursive: true });
await writeFile(
rosterPath,
[
'version: 1',
'transport: tmux',
'agents:',
' - name: working-agent',
' runtime: pi',
' - name: available-agent',
' runtime: pi',
].join('\n'),
);
const nowMs = 1_700_000_000_000;
const workingActivityEpoch = Math.floor((nowMs - 2_000) / 1000);
const availableActivityEpoch = Math.floor((nowMs - 40_000) / 1000);
const hbTs = new Date(nowMs - 1_000).toISOString();
await writeFile(join(runDir, 'working-agent.hb'), `ts=${hbTs}\npid=111\nstatus=ok\n`);
await writeFile(join(runDir, 'available-agent.hb'), `ts=${hbTs}\npid=222\nstatus=ok\n`);
const savedIdle = process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD;
process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD = '5';
const dateNow = vi.spyOn(Date, 'now').mockReturnValue(nowMs);
const runner: CommandRunner = async (command, args) => {
const full = [command, ...args].join(' ');
if (full.includes('list-sessions')) {
return { stdout: 'working-agent\navailable-agent\n', stderr: '', exitCode: 0 };
}
if (full.includes('=working-agent:0.0')) {
return { stdout: `111 pi 0 ${workingActivityEpoch}\n`, stderr: '', exitCode: 0 };
}
if (full.includes('=available-agent:0.0')) {
return { stdout: `222 pi 0 ${availableActivityEpoch}\n`, stderr: '', exitCode: 0 };
}
if (full.includes('systemctl') && full.includes('show')) {
return {
stdout: 'ActiveState=active\nSubState=running\nUnitFileState=enabled\n',
stderr: '',
exitCode: 0,
};
}
return { stdout: '', stderr: '', exitCode: 0 };
};
const lines: string[] = [];
const origLog = console.log;
console.log = (msg: string) => {
lines.push(msg);
};
const program = new Command();
program.exitOverride();
registerFleetCommand(program, { runner, mosaicHome: home });
try {
await program.parseAsync(['node', 'mosaic', 'fleet', 'ps']);
} finally {
console.log = origLog;
dateNow.mockRestore();
if (savedIdle === undefined) delete process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD;
else process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD = savedIdle;
await rm(home, { recursive: true, force: true });
}
const workingLine = lines.find((line) => line.includes('working-agent'));
const availableLine = lines.find((line) => line.includes('available-agent'));
expect(workingLine).toBeDefined();
expect(workingLine).toContain('1s/working');
expect(availableLine).toBeDefined();
expect(availableLine).toContain('1s/available');
expect(availableLine).not.toMatch(/\bIDLE\b/);
expect(availableLine).not.toMatch(/\bSTUCK\b/);
});
});
describe('buildTmuxListSessionsCommand', () => {
it('builds exact list-sessions command with session_name format', () => {
expect(buildTmuxListSessionsCommand('mosaic-fleet')).toEqual([
expect(buildTmuxListSessionsCommand('mosaic-factory')).toEqual([
'tmux',
'-L',
'mosaic-fleet',
'mosaic-factory',
'list-sessions',
'-F',
'#{session_name}',
@@ -1758,7 +1513,6 @@ describe('fleet ps — unmanaged socket sessions', () => {
// driftFlag must be false for unmanaged (no roster runtime to compare)
expect(unmanagedRow.driftFlag).toBe(false);
expect(unmanagedRow.readiness).toBe('unknown');
});
it('shows UNMANAGED flag in table output for unmanaged sessions', async () => {
@@ -1888,11 +1642,11 @@ describe('fleet ps — unmanaged socket sessions', () => {
describe('agent watch', () => {
it('builds exact grouped-viewer creation command', () => {
expect(
buildAgentWatchCreateViewerCommand('canary-pi', 'canary-pi-watch-123', 'mosaic-fleet'),
buildAgentWatchCreateViewerCommand('canary-pi', 'canary-pi-watch-123', 'mosaic-factory'),
).toEqual([
'tmux',
'-L',
'mosaic-fleet',
'mosaic-factory',
'new-session',
'-d',
'-t',
@@ -1903,10 +1657,10 @@ describe('agent watch', () => {
});
it('builds exact viewer attach command (read-only)', () => {
expect(buildAgentWatchAttachCommand('canary-pi-watch-123', 'mosaic-fleet')).toEqual([
expect(buildAgentWatchAttachCommand('canary-pi-watch-123', 'mosaic-factory')).toEqual([
'tmux',
'-L',
'mosaic-fleet',
'mosaic-factory',
'attach',
'-r',
'-t',
@@ -1915,10 +1669,10 @@ describe('agent watch', () => {
});
it('builds exact viewer kill command', () => {
expect(buildAgentWatchKillViewerCommand('canary-pi-watch-123', 'mosaic-fleet')).toEqual([
expect(buildAgentWatchKillViewerCommand('canary-pi-watch-123', 'mosaic-factory')).toEqual([
'tmux',
'-L',
'mosaic-fleet',
'mosaic-factory',
'kill-session',
'-t',
'canary-pi-watch-123',
@@ -2015,10 +1769,10 @@ describe('agent watch', () => {
describe('agent send --verify', () => {
it('builds exact verify capture-pane command', () => {
expect(buildAgentVerifyAcceptedCommand('canary-pi', 'mosaic-fleet', 5)).toEqual([
expect(buildAgentVerifyAcceptedCommand('canary-pi', 'mosaic-factory', 5)).toEqual([
'tmux',
'-L',
'mosaic-fleet',
'mosaic-factory',
'capture-pane',
'-t',
'=canary-pi:0.0',
@@ -2730,7 +2484,7 @@ describe('fleet add/remove — pure helpers', () => {
const baseRoster: FleetRoster = {
version: 1,
transport: 'tmux',
tmux: { socketName: 'mosaic-fleet', holderSession: '_holder' },
tmux: { socketName: 'mosaic-factory', holderSession: '_holder' },
defaults: { workingDirectory: '~/src' },
runtimes: { codex: { resetCommand: '/clear' } },
agents: [
@@ -2856,7 +2610,7 @@ describe('fleet add/remove — pure helpers', () => {
await writeFile(rosterPath, yaml);
const loaded = await loadFleetRoster(rosterPath);
expect(loaded.agents.map((a) => a.name)).toEqual(['orchestrator', 'coder0']);
expect(loaded.tmux.socketName).toBe('mosaic-fleet');
expect(loaded.tmux.socketName).toBe('mosaic-factory');
expect(loaded.agents[0]!.className).toBe('orchestrator');
} finally {
await rm(dir, { recursive: true, force: true });

View File

@@ -7,7 +7,6 @@ import { spawn } from 'node:child_process';
import * as readline from 'node:readline';
import type { Command } from 'commander';
import YAML from 'yaml';
import { resolveCommsBlock } from '../fleet/comms-onboarding.js';
/**
* A function that spawns a command with inherited stdio (TTY passthrough).
@@ -123,7 +122,7 @@ type FleetServiceAction = 'start' | 'stop' | 'restart' | 'status';
* rosters/callers that explicitly want isolation; it is NO LONGER the silent
* fallback for a socket-less roster (that now resolves to the default socket).
*/
export const DEFAULT_SOCKET_NAME = 'mosaic-fleet';
export const DEFAULT_SOCKET_NAME = 'mosaic-factory';
const DEFAULT_HOLDER_SESSION = '_holder';
const DEFAULT_WORKING_DIRECTORY = '~/src';
@@ -131,7 +130,7 @@ const DEFAULT_WORKING_DIRECTORY = '~/src';
* tmux `-L` args for a socket name. An empty/absent socket ⇒ the LITERAL default
* tmux socket (no `-L`), so spawn, observe (`fleet ps`/watch), and the onboarding
* cheat-sheet all agree. A named socket ⇒ `-L <name>`. `DEFAULT_SOCKET_NAME`
* remains a constant for callers that explicitly want mosaic-fleet; it is no
* remains a constant for callers that explicitly want mosaic-factory; it is no
* longer the silent fallback for a socket-less roster.
*/
export function socketArgs(socketName: string): string[] {
@@ -394,7 +393,6 @@ export function buildAgentTailCommand(agentName: string, lines: number, socketNa
// ---------------------------------------------------------------------------
export const HEARTBEAT_INTERVAL_MS = 15_000;
export const HEARTBEAT_IDLE_THRESHOLD_SECONDS = 300;
/**
* Heartbeat interval in ms, honoring MOSAIC_HEARTBEAT_INTERVAL (seconds) so the
@@ -405,57 +403,8 @@ export function heartbeatIntervalMs(): number {
const sec = Number.parseInt(process.env.MOSAIC_HEARTBEAT_INTERVAL ?? '', 10);
return Number.isFinite(sec) && sec > 0 ? sec * 1000 : HEARTBEAT_INTERVAL_MS;
}
/** Activity threshold in seconds, honoring MOSAIC_HEARTBEAT_IDLE_THRESHOLD. */
export function idleThresholdSeconds(): number {
const sec = Number.parseInt(process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD ?? '', 10);
return Number.isFinite(sec) && sec > 0 ? sec : HEARTBEAT_IDLE_THRESHOLD_SECONDS;
}
export const HEARTBEAT_HEALTHY_MULTIPLIER = 3;
export type ReadinessState = 'working' | 'available' | 'stuck' | 'stale' | 'dead' | 'unknown';
export interface ReadinessSignals {
paneAlive: boolean;
hbHealth: 'healthy' | 'stale' | 'unknown';
hbStatus: 'ok' | 'busy' | null;
idleSeconds: number | null;
}
export interface ReadinessThresholds {
idleThresholdSeconds: number;
}
/**
* Classify whether an agent is progressing based on already-parsed heartbeat/tmux signals.
* Best-effort and runtime-agnostic: it never probes, never throws, and preserves existing
* unknown/stale behavior when heartbeat data is absent or old.
*/
export function classifyReadiness(
signals: Partial<ReadinessSignals> | null | undefined,
thresholds: Partial<ReadinessThresholds> | null | undefined = {},
): ReadinessState {
try {
if (signals?.paneAlive !== true) return 'dead';
if (signals.hbHealth === 'unknown' || signals.hbHealth === undefined) return 'unknown';
if (signals.hbHealth === 'stale') return 'stale';
if (signals.hbStatus === 'busy') return 'working';
if (signals.idleSeconds === null || signals.idleSeconds === undefined) return 'working';
const idleSeconds = Number.isFinite(signals.idleSeconds) ? signals.idleSeconds : null;
if (idleSeconds === null) return 'working';
const idleThreshold = Number.isFinite(thresholds?.idleThresholdSeconds)
? Number(thresholds?.idleThresholdSeconds)
: idleThresholdSeconds();
// Follow-up: stuck pending per-agent assignment awareness: assigned task + idle past threshold => stuck.
if (idleSeconds >= idleThreshold) return 'available';
return 'working';
} catch {
return 'unknown';
}
}
export interface HeartbeatInfo {
ts: Date | null;
pid: number | null;
@@ -479,7 +428,6 @@ export interface AgentPsRow {
paneCommand: string | null;
idleSeconds: number | null;
heartbeat: HeartbeatInfo;
readiness: ReadinessState;
/** roster runtime !== actual pane command */
driftFlag: boolean;
/** active but UnitFileState=disabled */
@@ -512,7 +460,7 @@ export function buildSystemdShowCommand(agentName: string): string[] {
/**
* Returns the tmux list-panes command for an agent pane.
* Format: `#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity} #{window_activity} #{session_activity}`
* Format: `#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity}`
*/
export function buildTmuxListPanesCommand(agentName: string, socketName = ''): string[] {
return [
@@ -522,7 +470,7 @@ export function buildTmuxListPanesCommand(agentName: string, socketName = ''): s
'-t',
`=${agentName}:0.0`,
'-F',
'#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity} #{window_activity} #{session_activity}',
'#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity}',
];
}
@@ -622,8 +570,8 @@ export function parseSystemdShow(output: string): {
}
/**
* Parse the output of `tmux list-panes -F '#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity} #{window_activity} #{session_activity}'`
* Activity fields are Unix epoch timestamps (seconds), ordered most precise to coarsest.
* Parse the output of `tmux list-panes -F '#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity}'`
* pane_activity is a Unix epoch timestamp (seconds).
*/
export function parseTmuxListPanes(
output: string,
@@ -633,17 +581,15 @@ export function parseTmuxListPanes(
if (!line) {
return { pid: null, command: null, dead: true, idleSeconds: null };
}
// format: <pid> <command> <dead(0|1)> <pane_activity> <window_activity> <session_activity>
// format: <pid> <command> <dead(0|1)> <activity_epoch>
const parts = line.split(' ');
const pid = parts[0] ? (Number.isFinite(Number(parts[0])) ? Number(parts[0]) : null) : null;
const command = parts[1] ?? null;
const dead = parts[2] === '1';
const activityEpoch = parts
.slice(3, 6)
.map((part) => (part ? Number(part) : NaN))
.find((epoch) => Number.isFinite(epoch) && epoch > 0);
const idleSeconds = activityEpoch
? Math.max(0, Math.floor((nowMs - activityEpoch * 1000) / 1000))
const activityEpoch = parts[3] ? Number(parts[3]) : NaN;
const idleSeconds =
Number.isFinite(activityEpoch) && activityEpoch > 0
? Math.floor((nowMs - activityEpoch * 1000) / 1000)
: null;
return { pid, command, dead, idleSeconds };
}
@@ -1075,9 +1021,6 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
const nowMs = Date.now();
const rows: AgentPsRow[] = [];
const readinessThresholds = {
idleThresholdSeconds: idleThresholdSeconds(),
};
// Build the set of roster agent names for quick lookup when filtering socket sessions.
const rosterAgentNames = new Set(roster.agents.map((a) => a.name));
@@ -1108,17 +1051,6 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
const bootEnableWarning =
sysInfo.ActiveState === 'active' && sysInfo.UnitFileState === 'disabled';
const paneAlive = !paneInfo.dead;
const readiness = classifyReadiness(
{
paneAlive,
hbHealth: hb.health,
hbStatus: hb.status,
idleSeconds: paneInfo.idleSeconds,
},
readinessThresholds,
);
rows.push({
name: agent.name,
tenant_id,
@@ -1126,12 +1058,11 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
runtime: agent.runtime,
systemdActive: sysInfo.ActiveState,
systemdEnabled: sysInfo.UnitFileState,
paneAlive,
paneAlive: !paneInfo.dead,
panePid: paneInfo.pid,
paneCommand: paneInfo.command,
idleSeconds: paneInfo.idleSeconds,
heartbeat: hb,
readiness,
driftFlag,
bootEnableWarning,
managed: true,
@@ -1178,17 +1109,6 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
const bootEnableWarning =
sysInfo.ActiveState === 'active' && sysInfo.UnitFileState === 'disabled';
const paneAlive = !paneInfo.dead;
const readiness = classifyReadiness(
{
paneAlive,
hbHealth: hb.health,
hbStatus: hb.status,
idleSeconds: paneInfo.idleSeconds,
},
readinessThresholds,
);
rows.push({
name: sessionName,
tenant_id,
@@ -1197,12 +1117,11 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
runtime: 'unknown',
systemdActive: sysInfo.ActiveState,
systemdEnabled: sysInfo.UnitFileState,
paneAlive,
paneAlive: !paneInfo.dead,
panePid: paneInfo.pid,
paneCommand: paneInfo.command,
idleSeconds: paneInfo.idleSeconds,
heartbeat: hb,
readiness,
// No roster runtime to compare — drift is not meaningful for unmanaged sessions
driftFlag: false,
bootEnableWarning,
@@ -1244,7 +1163,7 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
const idle = row.idleSeconds !== null ? `${row.idleSeconds}s` : '-';
const hbAge =
row.heartbeat.ageMs !== null
? `${Math.round(row.heartbeat.ageMs / 1000)}s/${row.readiness}`
? `${Math.round(row.heartbeat.ageMs / 1000)}s/${row.heartbeat.health}`
: `unknown`;
const model = row.heartbeat.model ?? '-';
const flags: string[] = [];
@@ -1440,23 +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
.command('status [agent]')
.description('Show tmux status for the local fleet or one agent')
@@ -1787,7 +1689,7 @@ function normalizeRoster(raw: RawFleetRoster): FleetRoster {
transport: 'tmux',
tmux: {
// Absent socket_name ⇒ '' (the literal default tmux socket, no -L) — NOT
// mosaic-fleet. Shipped presets set socket_name explicitly, so they are
// mosaic-factory. Shipped presets set socket_name explicitly, so they are
// unaffected; only socket-less rosters get default-socket behavior.
socketName: stringValue(
raw.tmux?.socket_name ?? raw.tmux?.socketName,

View File

@@ -7,7 +7,6 @@ import {
buildFleetCommsBlock,
renderPeerReach,
readFleetCommsBlock,
resolveCommsBlock,
type CommsPeer,
} from './comms-onboarding.js';
@@ -49,9 +48,9 @@ describe('parseRosterAgents', () => {
it('parses an optional per-agent socket', () => {
const peers = parseRosterAgents(
['agents:', ' - name: a', ' class: worker', ' socket: mosaic-fleet'].join('\n'),
['agents:', ' - name: a', ' class: worker', ' socket: mosaic-factory'].join('\n'),
);
expect(peers[0]).toMatchObject({ name: 'a', socket: 'mosaic-fleet' });
expect(peers[0]).toMatchObject({ name: 'a', socket: 'mosaic-factory' });
});
it('stops at the next top-level key', () => {
@@ -100,9 +99,9 @@ describe('renderPeerReach — same-host vs cross-host', () => {
});
it('emits -L <socket> for a named socket', () => {
const peer: CommsPeer = { name: 'coder0', className: 'implementer', socket: 'mosaic-fleet' };
const peer: CommsPeer = { name: 'coder0', className: 'implementer', socket: 'mosaic-factory' };
expect(renderPeerReach(peer, 'w-jarvis', send)).toBe(
`${send} -L mosaic-fleet -s coder0 -m "…"`,
`${send} -L mosaic-factory -s coder0 -m "…"`,
);
});
@@ -112,10 +111,10 @@ describe('renderPeerReach — same-host vs cross-host', () => {
className: 'implementer',
host: '10.1.10.37',
ssh: 'jwoltje@10.1.10.37',
socket: 'mosaic-fleet',
socket: 'mosaic-factory',
};
expect(renderPeerReach(peer, 'w-jarvis', send)).toBe(
`${send} -L mosaic-fleet -H jwoltje@10.1.10.37 -s coder0-0 -m "…"`,
`${send} -L mosaic-factory -H jwoltje@10.1.10.37 -s coder0-0 -m "…"`,
);
});
});
@@ -186,53 +185,3 @@ describe('readFleetCommsBlock — situational (the context a spawned agent gets)
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. */
export const DEFAULT_MOSAIC_HOME_FOR_COMMS = join(homedir(), '.config', 'mosaic');

View File

@@ -8,9 +8,6 @@ import {
readRosterAgentNames,
runFrameworkReseed,
refreshActiveFleetUnits,
readInstalledFrameworkVersion,
readBundledFrameworkVersion,
checkFrameworkDrift,
} from './update-checker.js';
import { existsSync, readFileSync } from 'node:fs';
@@ -126,73 +123,3 @@ describe('refreshActiveFleetUnits', () => {
expect(existsSync(join(configHome, 'systemd', 'user', 'mosaic-agent@.service'))).toBe(false);
});
});
/**
* #642: re-seed when the on-disk framework is older than the bundled one even
* if no package is reported outdated (CLI upgraded outside `mosaic update`).
*/
describe('framework drift detection', () => {
let home: string; // stand-in for ~/.config/mosaic
let fw: string; // stand-in for the bundled framework root
beforeEach(() => {
const root = mkdtempSync(join(tmpdir(), 'mosaic-drift-'));
home = join(root, 'mosaic');
fw = join(root, 'framework');
mkdirSync(home, { recursive: true });
mkdirSync(fw, { recursive: true });
});
afterEach(() => {
rmSync(join(home, '..'), { recursive: true, force: true });
});
const writeInstalled = (v: string) => writeFileSync(join(home, '.framework-version'), v);
const writeBundled = (v: string) =>
writeFileSync(join(fw, 'install.sh'), `#!/usr/bin/env bash\nFRAMEWORK_VERSION=${v}\n`);
describe('readInstalledFrameworkVersion', () => {
it('returns undefined when the version file is absent', () => {
expect(readInstalledFrameworkVersion(home)).toBeUndefined();
});
it('parses the integer (tolerating surrounding whitespace)', () => {
writeInstalled(' 3\n');
expect(readInstalledFrameworkVersion(home)).toBe(3);
});
it('returns undefined for non-numeric content', () => {
writeInstalled('not-a-number\n');
expect(readInstalledFrameworkVersion(home)).toBeUndefined();
});
});
describe('readBundledFrameworkVersion', () => {
it('returns undefined when install.sh is absent', () => {
expect(readBundledFrameworkVersion(fw)).toBeUndefined();
});
it('parses FRAMEWORK_VERSION=<n> from install.sh', () => {
writeBundled('4');
expect(readBundledFrameworkVersion(fw)).toBe(4);
});
});
describe('checkFrameworkDrift', () => {
it('reports drift when on-disk is older than bundled', () => {
writeInstalled('3');
writeBundled('4');
expect(checkFrameworkDrift(home, fw)).toEqual({ drifted: true, installed: 3, bundled: 4 });
});
it('no drift when versions match', () => {
writeInstalled('4');
writeBundled('4');
expect(checkFrameworkDrift(home, fw)).toMatchObject({ drifted: false });
});
it('no drift when on-disk is newer than bundled', () => {
writeInstalled('5');
writeBundled('4');
expect(checkFrameworkDrift(home, fw)).toMatchObject({ drifted: false });
});
it('no drift (conservative) when a version cannot be read', () => {
writeBundled('4'); // installed version file missing
expect(checkFrameworkDrift(home, fw)).toMatchObject({ drifted: false, bundled: 4 });
});
});
});

View File

@@ -521,75 +521,6 @@ export function runFrameworkReseed(
}
}
// ─── Framework drift detection (#642) ────────────────────────────────────────
//
// `mosaic update` only re-seeds the framework when the @mosaicstack/mosaic
// package itself is upgraded *within that command*. When the CLI is upgraded
// some OTHER way — a direct `npm i -g @mosaicstack/mosaic`, or an upgrade run
// where only sibling packages were outdated — the framework files in
// ~/.config/mosaic stay stale and shipped launcher/runtime fixes never
// activate. Comparing the on-disk framework schema version against the version
// bundled in the installed package detects exactly that situation.
/** Read the framework schema version recorded on disk (~/.config/mosaic/.framework-version). */
export function readInstalledFrameworkVersion(
mosaicHome = join(homedir(), '.config', 'mosaic'),
): number | undefined {
const vf = join(mosaicHome, '.framework-version');
if (!existsSync(vf)) return undefined;
try {
const n = parseInt(readFileSync(vf, 'utf-8').trim(), 10);
return Number.isFinite(n) ? n : undefined;
} catch {
return undefined;
}
}
/**
* Read the framework schema version shipped in the installed package by parsing
* `FRAMEWORK_VERSION=<n>` out of the bundled install.sh (the authoritative
* source the installer writes to .framework-version).
*/
export function readBundledFrameworkVersion(
frameworkRoot = resolveBundledFrameworkRoot(),
): number | undefined {
const installer = join(frameworkRoot, 'install.sh');
if (!existsSync(installer)) return undefined;
try {
const m = readFileSync(installer, 'utf-8').match(/^\s*FRAMEWORK_VERSION=(\d+)/m);
const raw = m?.[1];
if (!raw) return undefined;
const n = parseInt(raw, 10);
return Number.isFinite(n) ? n : undefined;
} catch {
return undefined;
}
}
export interface FrameworkDrift {
/** True only when both versions are known AND the on-disk one is older. */
drifted: boolean;
installed?: number;
bundled?: number;
}
/**
* Detect whether the on-disk framework is older than the framework bundled in
* the installed CLI (#642). Conservative: if either version can't be read the
* result is no-drift, so a missing/unreadable version file never triggers an
* unexpected re-seed.
*/
export function checkFrameworkDrift(
mosaicHome = join(homedir(), '.config', 'mosaic'),
frameworkRoot = resolveBundledFrameworkRoot(),
): FrameworkDrift {
const installed = readInstalledFrameworkVersion(mosaicHome);
const bundled = readBundledFrameworkVersion(frameworkRoot);
const drifted =
typeof installed === 'number' && typeof bundled === 'number' && installed < bundled;
return { drifted, installed, bundled };
}
/**
* Best-effort parse of the fleet roster for agent names (used to relaunch
* durable agents after a re-seed). Returns [] when no roster exists.