Compare commits
1 Commits
feat/h-nor
...
chore/ci-c
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
9da71bd861 |
7
.gitignore
vendored
7
.gitignore
vendored
@@ -15,10 +15,3 @@ infra/step-ca/dev-password
|
|||||||
|
|
||||||
# Scratch dirs created by the framework git-wrapper shell test harnesses
|
# Scratch dirs created by the framework git-wrapper shell test harnesses
|
||||||
.mosaic-test-work/
|
.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
|
|
||||||
|
|||||||
@@ -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
|
|
||||||
@@ -1,5 +1,5 @@
|
|||||||
# &node_image is the pre-baked CI base built by .woodpecker/ci-image.yml:
|
# &node_image is the pre-baked CI base built by .woodpecker/ci-image.yml:
|
||||||
# node:24-alpine + python3/make/g++/postgresql-client + pnpm + a warm pnpm
|
# node:22-alpine + python3/make/g++/postgresql-client + pnpm + a warm pnpm
|
||||||
# store. The install step resolves from the baked store (--prefer-offline)
|
# store. The install step resolves from the baked store (--prefer-offline)
|
||||||
# instead of paying a ~731s cold fetch + native compile every run.
|
# instead of paying a ~731s cold fetch + native compile every run.
|
||||||
variables:
|
variables:
|
||||||
|
|||||||
@@ -2,7 +2,7 @@
|
|||||||
# Runs only on main branch push/tag
|
# Runs only on main branch push/tag
|
||||||
|
|
||||||
variables:
|
variables:
|
||||||
# Pre-baked CI base (see .woodpecker/ci-image.yml): node:24-alpine +
|
# Pre-baked CI base (see .woodpecker/ci-image.yml): node:22-alpine +
|
||||||
# toolchain + warm pnpm store. Kills the second cold install publish pays.
|
# toolchain + warm pnpm store. Kills the second cold install publish pays.
|
||||||
- &node_image 'git.mosaicstack.dev/mosaicstack/stack/ci-base:latest'
|
- &node_image 'git.mosaicstack.dev/mosaicstack/stack/ci-base:latest'
|
||||||
- &enable_pnpm 'corepack enable'
|
- &enable_pnpm 'corepack enable'
|
||||||
|
|||||||
@@ -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
|
|
||||||
@@ -86,7 +86,3 @@ Active workstream is **W1 — Federation v1**. Workers should:
|
|||||||
## #631 — re-seed preserves user fleet data (CRITICAL) — fix/631-reseed-preserves-fleet-data
|
## #631 — re-seed preserves user fleet data (CRITICAL) — fix/631-reseed-preserves-fleet-data
|
||||||
|
|
||||||
- Status: implemented + tested. PRIMARY: install.sh PRESERVE_PATHS += fleet/\*.yaml + fleet/agents + fleet/run (glob-aware cp-fallback); TS parity. SECONDARY: refreshActiveFleetUnits propagates unit fixes to ~/.config/systemd/user on mosaic update. bash F6 + TS + unit tests green. Detail: scratchpads/631-reseed-preserves-fleet.md.
|
- Status: implemented + tested. PRIMARY: install.sh PRESERVE_PATHS += fleet/\*.yaml + fleet/agents + fleet/run (glob-aware cp-fallback); TS parity. SECONDARY: refreshActiveFleetUnits propagates unit fixes to ~/.config/systemd/user on mosaic update. bash F6 + TS + unit tests green. Detail: scratchpads/631-reseed-preserves-fleet.md.
|
||||||
|
|
||||||
## #633 — comms-block emitter + FLEET-LAUNCH runbook — feat/633-comms-block-runbook
|
|
||||||
|
|
||||||
- Status: implemented + tested (TDD). `mosaic fleet comms-block <role> [--host]` wraps resolveCommsBlock → readFleetCommsBlock; fails loud (stderr + exit 1) on unknown role / missing roster instead of silent empty. docs/fleet/FLEET-LAUNCH.md runbook: worker path + orchestrator .env fold (MOSAIC_AGENT_COMMAND; line-41 [-z] short-circuits line-44 yolo hardcode) + 3 launch gotchas + #632 preserve note + North-Star 4-field arc (harness ✅/model ✅ roster-native today; yolo + command/channels = PATH B #636). 177 fleet+comms tests green (6 new resolveCommsBlock cases). PATH A of the A→B→webUI arc. Detail: scratchpads/633-comms-block-runbook.md.
|
|
||||||
|
|||||||
@@ -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.
|
|
||||||
@@ -1,79 +0,0 @@
|
|||||||
# Mosaic Fleet — NORTH STAR
|
|
||||||
|
|
||||||
> **Generated file — do not edit by hand.**
|
|
||||||
> Projected deterministically from [`NORTH_STAR.yaml`](./NORTH_STAR.yaml) by the pure
|
|
||||||
> generator in `packages/mosaic/src/commands/fleet.ts` (`renderNorthStarMarkdown`).
|
|
||||||
> Edit the YAML, then regenerate. Self-contained Mosaic — no Hermes dependency.
|
|
||||||
|
|
||||||
## Mission
|
|
||||||
|
|
||||||
A self-driving Mosaic system that 24/7 unattended converts a machine-readable goal set into merged, CI-green, budget-bounded change — looping plan→backlog→assign→execute→verify→merge→reassess — on Mosaic's OWN native backlog/dispatch engine. Mosaic is general-purpose: the user declares the system type they want (software delivery, personal assistant, research, business/operations, …) and the orchestrator provisions the matching persona roster and structure; the delivery fleet is one profile among many.
|
|
||||||
|
|
||||||
## Substrate
|
|
||||||
|
|
||||||
The Mosaic Backlog is the backlog of record + dispatch engine, built on Mosaic's native Postgres storage service (@mosaicstack/db drizzle; PGlite-embedded by default, full Postgres by config). NOT Hermes.
|
|
||||||
|
|
||||||
## Standing objectives
|
|
||||||
|
|
||||||
- **NS-1** — Single machine-readable source (this file) drives planning; prose docs are projections.
|
|
||||||
- **NS-2** — Every backlog item is an independently-shippable unit with stable id, priority, depends_on DAG, represented as a Mosaic Backlog card; spend tracked as advisory projection.
|
|
||||||
- **NS-3** — The supervisor guarantees movement: no idle agent while ready dependency-satisfied work exists; no empty backlog without a replan request; assignment via Mosaic native dispatch/claim.
|
|
||||||
- **NS-4** — Exactly one merge-gate approver; nothing reaches main except via pr-merge.sh after pr-ci-wait.sh success; Gitea branch protection is the backstop.
|
|
||||||
- **NS-5** — Every unit bounded by wall-clock TTL on its claim; token caps enforced only where a real meter exists, else advisory.
|
|
||||||
- **NS-6** — Context cleared between tasks for ephemeral runners (reset_between_tasks); persona+mission re-injected per task.
|
|
||||||
- **NS-7** — Meta-loop (session-review + enhancer) continuously proposes small fleet-improvement PRs.
|
|
||||||
- **NS-8** — Single operator-flippable PAUSE kill-switch (fleet/run/PAUSED) honored before every dispatch and every merge.
|
|
||||||
- **NS-9** — Mosaic is a general-purpose multi-agent system: the user declares the SYSTEM TYPE to run (e.g. software delivery, personal assistant, research, business/operations) and the orchestrator provisions the matching persona roster and org structure from a cross-domain baseline persona library; the delivery/coding fleet is one profile among many.
|
|
||||||
|
|
||||||
## Success criteria
|
|
||||||
|
|
||||||
- **AC-NS-1** — The supervisor keeps a two-agent floor (1 orchestrator + >=1 enhancer) healthy across reboot.
|
|
||||||
- **AC-NS-2** — A goal added to this YAML is decomposed to cards and either merged or escalated, with no human in the loop.
|
|
||||||
- **AC-NS-3** — No PR merges with failure/error/no-status/timeout CI, and none bypass pr-merge.sh.
|
|
||||||
- **AC-NS-4** — TTL is enforced on claims; token caps remain advisory until a real meter exists.
|
|
||||||
- **AC-NS-5** — Flipping fleet/run/PAUSED halts dispatch and merges within one tick.
|
|
||||||
- **AC-NS-6** — A user can declare a system type and the fleet provisions the matching persona roster + topology from the baseline library, with no code change.
|
|
||||||
- **AC-NS-7** — A user-customized persona (edited or added via the orchestrator) survives `mosaic update`: baseline reseed never clobbers user overrides.
|
|
||||||
|
|
||||||
## Workstreams
|
|
||||||
|
|
||||||
| id | title |
|
|
||||||
| --- | ----------------------------------------------------------------------------------------------------------- |
|
|
||||||
| A | Substrate — Mosaic Backlog on native Postgres storage service |
|
|
||||||
| B | Supervisor — movement guarantee, two-agent floor, dispatch/claim |
|
|
||||||
| C | Planner — goal decomposition into independently-shippable cards |
|
|
||||||
| D | Merge-gate — single approver, pr-merge.sh after CI wait |
|
|
||||||
| E | Meta-loop — session-review + enhancer improvement PRs |
|
|
||||||
| F | Safety-rails — TTL claims, advisory spend, PAUSE kill-switch |
|
|
||||||
| H | Personas & system profiles — cross-domain library, system-type provisioning, update-surviving customization |
|
|
||||||
|
|
||||||
## Goals (backlog projection)
|
|
||||||
|
|
||||||
| id | title | phase | priority | depends_on |
|
|
||||||
| --- | ------------------------------------------------------------------------------------------------------------------------------------------------- | ----- | ----------- | ---------- |
|
|
||||||
| A1 | Machine-readable NORTH_STAR.yaml + Markdown projection | 1 | must-have | — |
|
|
||||||
| A2 | Mosaic Backlog schema + storage-service card store (drizzle/PGlite) | 1 | must-have | A1 |
|
|
||||||
| A3a | Card lifecycle — create/claim/release with stable ids + depends_on DAG | 1 | must-have | A2 |
|
|
||||||
| A3b | TTL-bounded claim enforcement (wall-clock) on cards | 1 | must-have | A3a |
|
|
||||||
| A4 | Advisory spend projection per card (degrades to TTL, no real meter) | 1 | should-have | A3a |
|
|
||||||
| B1 | Supervisor tick — readiness scan, two-agent-floor health check | 2 | must-have | A3a |
|
|
||||||
| B2 | Native dispatch/claim — assign ready dependency-satisfied work | 2 | must-have | A3b, B1 |
|
|
||||||
| B3a | Planner decompose — goal added to YAML → cards | 2 | must-have | A2, B1 |
|
|
||||||
| B3b | Replan request on empty backlog; escalate on no-decompose | 2 | should-have | B3a |
|
|
||||||
| G1 | PAUSE kill-switch + merge-gate honored before dispatch and merge | 2 | must-have | B2 |
|
|
||||||
| H1 | Cross-domain baseline persona library (exec, marketing, ops, research, assistant + engineering roles) | 1 | must-have | A1 |
|
|
||||||
| H2 | System-type profiles — declarative mapping of system type to persona roster + topology | 2 | must-have | H1 |
|
|
||||||
| H3 | System-type provisioning — user declares type; orchestrator instantiates the matching roster + structure | 2 | must-have | H2 |
|
|
||||||
| H4 | Update-surviving persona customization — ad-hoc edits/additions persisted in a PRESERVE-protected override layer (baseline merged with overrides) | 2 | must-have | H1 |
|
|
||||||
|
|
||||||
## Assumptions (vetoable)
|
|
||||||
|
|
||||||
- **ASM-1** (vetoable) — The Mosaic Backlog on the native Postgres storage service is the backlog of record.
|
|
||||||
- **ASM-2** (vetoable) — Claude gate roles have no native busy status, so readiness = pane-idle + heartbeat.
|
|
||||||
- **ASM-3** (vetoable) — Two-agent floor = 1 orchestrator + >=1 enhancer.
|
|
||||||
- **ASM-4** (vetoable) — Baseline personas ship in framework/fleet/roles/ (reseeded on update); user overrides live in a separate PRESERVE_PATHS-protected layer and win on merge.
|
|
||||||
|
|
||||||
## Spend
|
|
||||||
|
|
||||||
- **advisory:** true
|
|
||||||
- No per-task token meter yet; budgets degrade to TTL. Spend is tracked only as an advisory projection alongside each card.
|
|
||||||
@@ -1,215 +0,0 @@
|
|||||||
# Mosaic Fleet — NORTH_STAR (machine-readable source of truth)
|
|
||||||
#
|
|
||||||
# This file is the single machine-readable source of truth for fleet planning.
|
|
||||||
# Prose docs (including NORTH_STAR.md) are deterministic PROJECTIONS of this file.
|
|
||||||
# Regenerate the Markdown projection with the pure generator in
|
|
||||||
# packages/mosaic/src/commands/fleet.ts (renderNorthStarMarkdown). Edit the YAML,
|
|
||||||
# never the .md.
|
|
||||||
#
|
|
||||||
# Self-contained Mosaic. NO Hermes runtime dependency. The backlog of record is
|
|
||||||
# the Mosaic Backlog on Mosaic's OWN native Postgres storage service.
|
|
||||||
|
|
||||||
version: 1
|
|
||||||
|
|
||||||
mission: >-
|
|
||||||
A self-driving Mosaic system that 24/7 unattended converts a machine-readable
|
|
||||||
goal set into merged, CI-green, budget-bounded change — looping
|
|
||||||
plan→backlog→assign→execute→verify→merge→reassess — on Mosaic's OWN native
|
|
||||||
backlog/dispatch engine. Mosaic is general-purpose: the user declares the
|
|
||||||
system type they want (software delivery, personal assistant, research,
|
|
||||||
business/operations, …) and the orchestrator provisions the matching persona
|
|
||||||
roster and structure; the delivery fleet is one profile among many.
|
|
||||||
|
|
||||||
substrate:
|
|
||||||
note: >-
|
|
||||||
The Mosaic Backlog is the backlog of record + dispatch engine, built on
|
|
||||||
Mosaic's native Postgres storage service (@mosaicstack/db drizzle;
|
|
||||||
PGlite-embedded by default, full Postgres by config). NOT Hermes.
|
|
||||||
|
|
||||||
standing_objectives:
|
|
||||||
- id: NS-1
|
|
||||||
text: >-
|
|
||||||
Single machine-readable source (this file) drives planning; prose docs are
|
|
||||||
projections.
|
|
||||||
- id: NS-2
|
|
||||||
text: >-
|
|
||||||
Every backlog item is an independently-shippable unit with stable id,
|
|
||||||
priority, depends_on DAG, represented as a Mosaic Backlog card; spend
|
|
||||||
tracked as advisory projection.
|
|
||||||
- id: NS-3
|
|
||||||
text: >-
|
|
||||||
The supervisor guarantees movement: no idle agent while ready
|
|
||||||
dependency-satisfied work exists; no empty backlog without a replan
|
|
||||||
request; assignment via Mosaic native dispatch/claim.
|
|
||||||
- id: NS-4
|
|
||||||
text: >-
|
|
||||||
Exactly one merge-gate approver; nothing reaches main except via
|
|
||||||
pr-merge.sh after pr-ci-wait.sh success; Gitea branch protection is the
|
|
||||||
backstop.
|
|
||||||
- id: NS-5
|
|
||||||
text: >-
|
|
||||||
Every unit bounded by wall-clock TTL on its claim; token caps enforced
|
|
||||||
only where a real meter exists, else advisory.
|
|
||||||
- id: NS-6
|
|
||||||
text: >-
|
|
||||||
Context cleared between tasks for ephemeral runners
|
|
||||||
(reset_between_tasks); persona+mission re-injected per task.
|
|
||||||
- id: NS-7
|
|
||||||
text: >-
|
|
||||||
Meta-loop (session-review + enhancer) continuously proposes small
|
|
||||||
fleet-improvement PRs.
|
|
||||||
- id: NS-8
|
|
||||||
text: >-
|
|
||||||
Single operator-flippable PAUSE kill-switch (fleet/run/PAUSED) honored
|
|
||||||
before every dispatch and every merge.
|
|
||||||
- id: NS-9
|
|
||||||
text: >-
|
|
||||||
Mosaic is a general-purpose multi-agent system: the user declares the
|
|
||||||
SYSTEM TYPE to run (e.g. software delivery, personal assistant, research,
|
|
||||||
business/operations) and the orchestrator provisions the matching persona
|
|
||||||
roster and org structure from a cross-domain baseline persona library; the
|
|
||||||
delivery/coding fleet is one profile among many.
|
|
||||||
|
|
||||||
success_criteria:
|
|
||||||
- id: AC-NS-1
|
|
||||||
text: >-
|
|
||||||
The supervisor keeps a two-agent floor (1 orchestrator + >=1 enhancer)
|
|
||||||
healthy across reboot.
|
|
||||||
- id: AC-NS-2
|
|
||||||
text: >-
|
|
||||||
A goal added to this YAML is decomposed to cards and either merged or
|
|
||||||
escalated, with no human in the loop.
|
|
||||||
- id: AC-NS-3
|
|
||||||
text: >-
|
|
||||||
No PR merges with failure/error/no-status/timeout CI, and none bypass
|
|
||||||
pr-merge.sh.
|
|
||||||
- id: AC-NS-4
|
|
||||||
text: >-
|
|
||||||
TTL is enforced on claims; token caps remain advisory until a real meter
|
|
||||||
exists.
|
|
||||||
- id: AC-NS-5
|
|
||||||
text: >-
|
|
||||||
Flipping fleet/run/PAUSED halts dispatch and merges within one tick.
|
|
||||||
- id: AC-NS-6
|
|
||||||
text: >-
|
|
||||||
A user can declare a system type and the fleet provisions the matching
|
|
||||||
persona roster + topology from the baseline library, with no code change.
|
|
||||||
- id: AC-NS-7
|
|
||||||
text: >-
|
|
||||||
A user-customized persona (edited or added via the orchestrator) survives
|
|
||||||
`mosaic update`: baseline reseed never clobbers user overrides.
|
|
||||||
|
|
||||||
workstreams:
|
|
||||||
- id: A
|
|
||||||
title: Substrate — Mosaic Backlog on native Postgres storage service
|
|
||||||
- id: B
|
|
||||||
title: Supervisor — movement guarantee, two-agent floor, dispatch/claim
|
|
||||||
- id: C
|
|
||||||
title: Planner — goal decomposition into independently-shippable cards
|
|
||||||
- id: D
|
|
||||||
title: Merge-gate — single approver, pr-merge.sh after CI wait
|
|
||||||
- id: E
|
|
||||||
title: Meta-loop — session-review + enhancer improvement PRs
|
|
||||||
- id: F
|
|
||||||
title: Safety-rails — TTL claims, advisory spend, PAUSE kill-switch
|
|
||||||
- id: H
|
|
||||||
title: Personas & system profiles — cross-domain library, system-type provisioning, update-surviving customization
|
|
||||||
|
|
||||||
goals:
|
|
||||||
- id: A1
|
|
||||||
title: Machine-readable NORTH_STAR.yaml + Markdown projection
|
|
||||||
phase: 1
|
|
||||||
priority: must-have
|
|
||||||
depends_on: []
|
|
||||||
- id: A2
|
|
||||||
title: Mosaic Backlog schema + storage-service card store (drizzle/PGlite)
|
|
||||||
phase: 1
|
|
||||||
priority: must-have
|
|
||||||
depends_on: [A1]
|
|
||||||
- id: A3a
|
|
||||||
title: Card lifecycle — create/claim/release with stable ids + depends_on DAG
|
|
||||||
phase: 1
|
|
||||||
priority: must-have
|
|
||||||
depends_on: [A2]
|
|
||||||
- id: A3b
|
|
||||||
title: TTL-bounded claim enforcement (wall-clock) on cards
|
|
||||||
phase: 1
|
|
||||||
priority: must-have
|
|
||||||
depends_on: [A3a]
|
|
||||||
- id: A4
|
|
||||||
title: Advisory spend projection per card (degrades to TTL, no real meter)
|
|
||||||
phase: 1
|
|
||||||
priority: should-have
|
|
||||||
depends_on: [A3a]
|
|
||||||
- id: B1
|
|
||||||
title: Supervisor tick — readiness scan, two-agent-floor health check
|
|
||||||
phase: 2
|
|
||||||
priority: must-have
|
|
||||||
depends_on: [A3a]
|
|
||||||
- id: B2
|
|
||||||
title: Native dispatch/claim — assign ready dependency-satisfied work
|
|
||||||
phase: 2
|
|
||||||
priority: must-have
|
|
||||||
depends_on: [A3b, B1]
|
|
||||||
- id: B3a
|
|
||||||
title: Planner decompose — goal added to YAML → cards
|
|
||||||
phase: 2
|
|
||||||
priority: must-have
|
|
||||||
depends_on: [A2, B1]
|
|
||||||
- id: B3b
|
|
||||||
title: Replan request on empty backlog; escalate on no-decompose
|
|
||||||
phase: 2
|
|
||||||
priority: should-have
|
|
||||||
depends_on: [B3a]
|
|
||||||
- id: G1
|
|
||||||
title: PAUSE kill-switch + merge-gate honored before dispatch and merge
|
|
||||||
phase: 2
|
|
||||||
priority: must-have
|
|
||||||
depends_on: [B2]
|
|
||||||
- id: H1
|
|
||||||
title: Cross-domain baseline persona library (exec, marketing, ops, research, assistant + engineering roles)
|
|
||||||
phase: 1
|
|
||||||
priority: must-have
|
|
||||||
depends_on: [A1]
|
|
||||||
- id: H2
|
|
||||||
title: System-type profiles — declarative mapping of system type to persona roster + topology
|
|
||||||
phase: 2
|
|
||||||
priority: must-have
|
|
||||||
depends_on: [H1]
|
|
||||||
- id: H3
|
|
||||||
title: System-type provisioning — user declares type; orchestrator instantiates the matching roster + structure
|
|
||||||
phase: 2
|
|
||||||
priority: must-have
|
|
||||||
depends_on: [H2]
|
|
||||||
- id: H4
|
|
||||||
title: Update-surviving persona customization — ad-hoc edits/additions persisted in a PRESERVE-protected override layer (baseline merged with overrides)
|
|
||||||
phase: 2
|
|
||||||
priority: must-have
|
|
||||||
depends_on: [H1]
|
|
||||||
|
|
||||||
assumptions:
|
|
||||||
- id: ASM-1
|
|
||||||
vetoable: true
|
|
||||||
text: >-
|
|
||||||
The Mosaic Backlog on the native Postgres storage service is the backlog
|
|
||||||
of record.
|
|
||||||
- id: ASM-2
|
|
||||||
vetoable: true
|
|
||||||
text: >-
|
|
||||||
Claude gate roles have no native busy status, so readiness = pane-idle +
|
|
||||||
heartbeat.
|
|
||||||
- id: ASM-3
|
|
||||||
vetoable: true
|
|
||||||
text: 'Two-agent floor = 1 orchestrator + >=1 enhancer.'
|
|
||||||
- id: ASM-4
|
|
||||||
vetoable: true
|
|
||||||
text: >-
|
|
||||||
Baseline personas ship in framework/fleet/roles/ (reseeded on update);
|
|
||||||
user overrides live in a separate PRESERVE_PATHS-protected layer and win
|
|
||||||
on merge.
|
|
||||||
|
|
||||||
spend:
|
|
||||||
advisory: true
|
|
||||||
note: >-
|
|
||||||
No per-task token meter yet; budgets degrade to TTL. Spend is tracked only
|
|
||||||
as an advisory projection alongside each card.
|
|
||||||
@@ -1,138 +0,0 @@
|
|||||||
# Fleet Backlog Conventions
|
|
||||||
|
|
||||||
The **backlog** is Mosaic's native backlog-of-record for fleet work. It is built
|
|
||||||
end-to-end on Mosaic's own storage layer (`@mosaicstack/db`, drizzle/Postgres)
|
|
||||||
and surfaced as `mosaic fleet backlog <sub> --json`.
|
|
||||||
|
|
||||||
> **Mosaic-native, no Hermes.** This backlog REPLACES the former Hermes adapter.
|
|
||||||
> There is **no** runtime dependency on Hermes, `hermes kanban`, or `~/.hermes`
|
|
||||||
> anywhere in this feature. Anything previously delegated to Hermes is recreated
|
|
||||||
> here on Mosaic's own Postgres storage layer.
|
|
||||||
|
|
||||||
## Storage tier — PGlite by default, Postgres by config
|
|
||||||
|
|
||||||
The backlog uses the existing Mosaic storage layer; there is **no** new database
|
|
||||||
engine (no sqlite, no raw client).
|
|
||||||
|
|
||||||
| Condition | Tier | Data location |
|
|
||||||
| ------------------------------ | -------------------- | -------------------------------- |
|
|
||||||
| `DATABASE_URL` set | Full server Postgres | the configured database |
|
|
||||||
| `PGLITE_DATA_DIR` set (no URL) | Embedded PGlite | that directory |
|
|
||||||
| neither (default) | Embedded PGlite | `~/.config/mosaic/fleet/backlog` |
|
|
||||||
|
|
||||||
PGlite is real Postgres semantics in-process — including the row locks the atomic
|
|
||||||
claim relies on — so the **same code** runs on a laptop (embedded, single-host
|
|
||||||
default) and on a full Postgres deployment. Switching tiers is config-only.
|
|
||||||
|
|
||||||
The schema (`backlog` table) is created automatically on first CLI use:
|
|
||||||
`runMigrations()` for Postgres, `runPgliteMigrations()` for embedded PGlite.
|
|
||||||
|
|
||||||
### Update safety
|
|
||||||
|
|
||||||
The embedded PGlite store lives under `~/.config/mosaic/fleet/backlog`, which is
|
|
||||||
listed in `PRESERVE_PATHS` in `packages/mosaic/framework/install.sh`. This means
|
|
||||||
`mosaic update` (which runs the framework sync with `rsync --delete`) will **not**
|
|
||||||
wipe the operator's backlog — same protection as the roster, per-agent env, and
|
|
||||||
heartbeat run dir.
|
|
||||||
|
|
||||||
## Card schema
|
|
||||||
|
|
||||||
A card is one row in the `backlog` table:
|
|
||||||
|
|
||||||
| Column | Type | Notes |
|
|
||||||
| ------------------- | ------------------- | ------------------------------------------------------------- |
|
|
||||||
| `id` | text (PK) | Stable, caller-supplied id (e.g. `A4`, `fleet-001`). |
|
|
||||||
| `title` | text | Required. |
|
|
||||||
| `body` | text (nullable) | Free-form description. |
|
|
||||||
| `phase` | text (nullable) | Board/phase grouping (see below). |
|
|
||||||
| `priority` | int (default 0) | **Higher = sooner.** Claim picks the max-priority ready card. |
|
|
||||||
| `status` | enum | `ready` \| `claimed` \| `blocked` \| `done`. |
|
|
||||||
| `depends_on` | jsonb `string[]` | DAG edges — ids of cards this one depends on. |
|
|
||||||
| `claim_owner` | text (nullable) | Owner token of the active claim. |
|
|
||||||
| `claim_ttl_seconds` | int (nullable) | TTL of the active claim. |
|
|
||||||
| `claimed_at` | timestamptz (null) | When the claim was taken. `claimed_at + ttl` = expiry. |
|
|
||||||
| `attempts` | int (default 0) | Incremented each time the card is claimed. |
|
|
||||||
| `idempotency_key` | text (unique, null) | Dedups `create`; NULLs are distinct in Postgres. |
|
|
||||||
| `acceptance` | jsonb (nullable) | Acceptance criteria (array of strings or object). |
|
|
||||||
| `created_at` | timestamptz | |
|
|
||||||
| `updated_at` | timestamptz | |
|
|
||||||
|
|
||||||
`depends_on` is modeled as a `jsonb` array column rather than a separate edge
|
|
||||||
table. Justification: it matches the repo's existing style (e.g. `tasks.tags`,
|
|
||||||
`agents.skills`, `routing_rules.conditions` are all jsonb arrays), keeps a card
|
|
||||||
self-contained, and the DAG is small (per-card dependency lists), so a join table
|
|
||||||
would add ceremony without benefit.
|
|
||||||
|
|
||||||
### Board / phase convention
|
|
||||||
|
|
||||||
`phase` is a free-form grouping string used as the board column / milestone label
|
|
||||||
(e.g. `M1`, `fleet`, `infra`). `list --phase <phase>` filters to one board lane.
|
|
||||||
`priority` orders cards **within** the ready pool regardless of phase.
|
|
||||||
|
|
||||||
## Status lifecycle
|
|
||||||
|
|
||||||
```
|
|
||||||
create
|
|
||||||
│
|
|
||||||
▼
|
|
||||||
┌──────► ready ───── claim ─────► claimed ───── complete ─────► done
|
|
||||||
│ │ │
|
|
||||||
│ block reclaim (TTL expiry or --id)
|
|
||||||
│ ▼ │
|
|
||||||
│ blocked └──────────────────────────┘ (back to ready)
|
|
||||||
└──────────┘ (reclaim / re-create can return a card to ready)
|
|
||||||
```
|
|
||||||
|
|
||||||
- **ready** — eligible to be claimed once every `depends_on` card is `done`.
|
|
||||||
- **claimed** — a worker holds it; `claim_owner` + `claimed_at` set.
|
|
||||||
- **blocked** — explicitly parked; never auto-claimed.
|
|
||||||
- **done** — completed; satisfies dependents.
|
|
||||||
|
|
||||||
## Atomic claim (`FOR UPDATE SKIP LOCKED`) + TTL
|
|
||||||
|
|
||||||
`claim` is atomic. Inside a single transaction it locks candidate `ready` rows
|
|
||||||
with `SELECT ... FOR UPDATE SKIP LOCKED` (via the drizzle `sql` operator), picks
|
|
||||||
the highest-priority deps-satisfied card, and flips it to `claimed`. Because a row
|
|
||||||
already locked by a concurrent claimer is **skipped**, two claimers can **never**
|
|
||||||
both win the same card — the loser falls through to the next candidate or gets
|
|
||||||
`null`. (Proven by the concurrency tests in `packages/db/src/backlog.spec.ts`.)
|
|
||||||
|
|
||||||
- **Deps gate:** a card is only claimable when every id in `depends_on` is `done`.
|
|
||||||
- **TTL:** `claim --ttl <sec>` (default **900s**) records `claim_ttl_seconds`.
|
|
||||||
- **reclaim:** releases claims whose `claimed_at + ttl` is in the past (expired)
|
|
||||||
back to `ready`, clearing the claim fields. `reclaim --id <id>` force-releases a
|
|
||||||
specific card regardless of expiry. This is how a crashed worker's card returns
|
|
||||||
to the pool.
|
|
||||||
|
|
||||||
## CLI — `mosaic fleet backlog <sub> --json`
|
|
||||||
|
|
||||||
All subcommands support `--json`.
|
|
||||||
|
|
||||||
| Subcommand | Purpose |
|
|
||||||
| --------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------- |
|
|
||||||
| `create --id --title [--body --phase --priority --depends-on --acceptance --idempotency-key]` | Create a card; `idempotency_key` dedups (repeat returns the existing card). |
|
|
||||||
| `list [--status --phase --ready-only]` | List cards. `--ready-only` = status `ready` AND all deps `done`. |
|
|
||||||
| `claim --owner [--ttl <sec> --id <id>]` | Atomically claim the highest-priority ready card (or `--id`). Returns the card or `null`. |
|
|
||||||
| `reclaim [--id <id>]` | Release expired claims (or a specific card) back to `ready`. |
|
|
||||||
| `link --from --to` | Add a `depends_on` edge (`--from` depends on `--to`). |
|
|
||||||
| `stats` | Counts by status, oldest-ready age, expired-claim count. |
|
|
||||||
| `block --id` | Set a card to `blocked`. |
|
|
||||||
| `complete --id` | Set a card to `done` (releases any claim). |
|
|
||||||
|
|
||||||
### Example
|
|
||||||
|
|
||||||
```sh
|
|
||||||
# Seed two cards, the second depends on the first.
|
|
||||||
mosaic fleet backlog create --id A1 --title "schema" --priority 5
|
|
||||||
mosaic fleet backlog create --id A2 --title "service" --depends-on A1 --priority 9
|
|
||||||
|
|
||||||
# A2 is gated on A1, so claim returns A1 first.
|
|
||||||
mosaic fleet backlog claim --owner worker-1 --ttl 600 --json
|
|
||||||
|
|
||||||
# Finish A1; now A2 is ready.
|
|
||||||
mosaic fleet backlog complete --id A1
|
|
||||||
mosaic fleet backlog list --ready-only --json
|
|
||||||
|
|
||||||
# Recover stalled work.
|
|
||||||
mosaic fleet backlog reclaim --json
|
|
||||||
```
|
|
||||||
@@ -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.
|
|
||||||
@@ -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.
|
|
||||||
@@ -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.
|
|
||||||
@@ -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.
|
|
||||||
@@ -28,7 +28,6 @@ export default tseslint.config(
|
|||||||
'apps/web/e2e/helpers/*.ts',
|
'apps/web/e2e/helpers/*.ts',
|
||||||
'apps/web/playwright.config.ts',
|
'apps/web/playwright.config.ts',
|
||||||
'apps/gateway/vitest.config.ts',
|
'apps/gateway/vitest.config.ts',
|
||||||
'packages/db/vitest.config.ts',
|
|
||||||
'packages/storage/vitest.config.ts',
|
'packages/storage/vitest.config.ts',
|
||||||
'packages/mosaic/__tests__/*.ts',
|
'packages/mosaic/__tests__/*.ts',
|
||||||
'tools/federation-harness/*.ts',
|
'tools/federation-harness/*.ts',
|
||||||
|
|||||||
@@ -1,22 +0,0 @@
|
|||||||
CREATE TYPE "public"."backlog_status" AS ENUM('ready', 'claimed', 'blocked', 'done');--> statement-breakpoint
|
|
||||||
CREATE TABLE "backlog" (
|
|
||||||
"id" text PRIMARY KEY NOT NULL,
|
|
||||||
"title" text NOT NULL,
|
|
||||||
"body" text,
|
|
||||||
"phase" text,
|
|
||||||
"priority" integer DEFAULT 0 NOT NULL,
|
|
||||||
"status" "backlog_status" DEFAULT 'ready' NOT NULL,
|
|
||||||
"depends_on" jsonb DEFAULT '[]'::jsonb NOT NULL,
|
|
||||||
"claim_owner" text,
|
|
||||||
"claim_ttl_seconds" integer,
|
|
||||||
"claimed_at" timestamp with time zone,
|
|
||||||
"attempts" integer DEFAULT 0 NOT NULL,
|
|
||||||
"idempotency_key" text,
|
|
||||||
"acceptance" jsonb,
|
|
||||||
"created_at" timestamp with time zone DEFAULT now() NOT NULL,
|
|
||||||
"updated_at" timestamp with time zone DEFAULT now() NOT NULL
|
|
||||||
);
|
|
||||||
--> statement-breakpoint
|
|
||||||
CREATE INDEX "backlog_status_priority_idx" ON "backlog" USING btree ("status","priority");--> statement-breakpoint
|
|
||||||
CREATE INDEX "backlog_status_claimed_at_idx" ON "backlog" USING btree ("status","claimed_at");--> statement-breakpoint
|
|
||||||
CREATE UNIQUE INDEX "backlog_idempotency_key_idx" ON "backlog" USING btree ("idempotency_key");
|
|
||||||
File diff suppressed because it is too large
Load Diff
@@ -78,13 +78,6 @@
|
|||||||
"when": 1745366400000,
|
"when": 1745366400000,
|
||||||
"tag": "0010_federation_enrollment_tokens",
|
"tag": "0010_federation_enrollment_tokens",
|
||||||
"breakpoints": true
|
"breakpoints": true
|
||||||
},
|
|
||||||
{
|
|
||||||
"idx": 11,
|
|
||||||
"version": "7",
|
|
||||||
"when": 1782310438919,
|
|
||||||
"tag": "0011_bitter_gateway",
|
|
||||||
"breakpoints": true
|
|
||||||
}
|
}
|
||||||
]
|
]
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -1,263 +0,0 @@
|
|||||||
import { afterEach, beforeEach, describe, expect, it } from 'vitest';
|
|
||||||
import { sql } from 'drizzle-orm';
|
|
||||||
import { createPgliteDb } from './client-pglite.js';
|
|
||||||
import { runPgliteMigrations } from './migrate.js';
|
|
||||||
import type { DbHandle } from './client.js';
|
|
||||||
import { BacklogService } from './backlog.js';
|
|
||||||
import { backlog } from './schema.js';
|
|
||||||
|
|
||||||
// Helper: backdate a claim's claimed_at by 1 hour so it is past any short TTL.
|
|
||||||
function sqlBackdate(id: string) {
|
|
||||||
return sql`UPDATE ${backlog} SET claimed_at = now() - interval '1 hour' WHERE ${backlog.id} = ${id}`;
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Real Postgres semantics, no external server: embedded in-memory PGlite.
|
|
||||||
* The migration path creates the `backlog` table (and every other table) so the
|
|
||||||
* service runs against the actual generated schema, including the row locks the
|
|
||||||
* atomic-claim path depends on.
|
|
||||||
*/
|
|
||||||
async function freshService(): Promise<{ handle: DbHandle; svc: BacklogService }> {
|
|
||||||
const handle = createPgliteDb('memory://');
|
|
||||||
await runPgliteMigrations(handle);
|
|
||||||
return { handle, svc: new BacklogService(handle.db) };
|
|
||||||
}
|
|
||||||
|
|
||||||
describe('BacklogService', () => {
|
|
||||||
let handle: DbHandle;
|
|
||||||
let svc: BacklogService;
|
|
||||||
|
|
||||||
beforeEach(async () => {
|
|
||||||
({ handle, svc } = await freshService());
|
|
||||||
});
|
|
||||||
|
|
||||||
afterEach(async () => {
|
|
||||||
await handle.close();
|
|
||||||
});
|
|
||||||
|
|
||||||
it('create then list returns the card', async () => {
|
|
||||||
await svc.create({ id: 'c1', title: 'First card', phase: 'M1', priority: 5 });
|
|
||||||
const all = await svc.list();
|
|
||||||
expect(all).toHaveLength(1);
|
|
||||||
expect(all[0]).toMatchObject({ id: 'c1', title: 'First card', phase: 'M1', status: 'ready' });
|
|
||||||
});
|
|
||||||
|
|
||||||
it('idempotency_key dedups create', async () => {
|
|
||||||
const a = await svc.create({ id: 'c1', title: 'one', idempotencyKey: 'k-1' });
|
|
||||||
const b = await svc.create({ id: 'c2', title: 'two', idempotencyKey: 'k-1' });
|
|
||||||
expect(b.id).toBe(a.id);
|
|
||||||
const all = await svc.list();
|
|
||||||
expect(all).toHaveLength(1);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('list filters by status and phase', async () => {
|
|
||||||
await svc.create({ id: 'c1', title: 'a', phase: 'M1' });
|
|
||||||
await svc.create({ id: 'c2', title: 'b', phase: 'M2' });
|
|
||||||
await svc.block('c2');
|
|
||||||
expect(await svc.list({ phase: 'M1' })).toHaveLength(1);
|
|
||||||
expect(await svc.list({ status: 'blocked' })).toHaveLength(1);
|
|
||||||
expect((await svc.list({ status: 'blocked' }))[0]!.id).toBe('c2');
|
|
||||||
});
|
|
||||||
|
|
||||||
describe('atomic claim', () => {
|
|
||||||
it('two concurrent claimers on one card => exactly one wins', async () => {
|
|
||||||
await svc.create({ id: 'only', title: 'the one', priority: 10 });
|
|
||||||
|
|
||||||
// Two independent claimers race for the single ready card on the same db.
|
|
||||||
// The atomic claim path (`FOR UPDATE SKIP LOCKED` inside a transaction)
|
|
||||||
// guarantees the loser's locked row is skipped, so it can never also flip
|
|
||||||
// the card to claimed — it gets the next candidate (none) and returns null.
|
|
||||||
const svcA = new BacklogService(handle.db);
|
|
||||||
const svcB = new BacklogService(handle.db);
|
|
||||||
|
|
||||||
const [a, b] = await Promise.all([
|
|
||||||
svcA.claim({ owner: 'worker-A' }),
|
|
||||||
svcB.claim({ owner: 'worker-B' }),
|
|
||||||
]);
|
|
||||||
|
|
||||||
const winners = [a, b].filter((c) => c !== null);
|
|
||||||
expect(winners).toHaveLength(1);
|
|
||||||
expect(winners[0]!.id).toBe('only');
|
|
||||||
expect(winners[0]!.status).toBe('claimed');
|
|
||||||
expect(['worker-A', 'worker-B']).toContain(winners[0]!.claimOwner);
|
|
||||||
|
|
||||||
const card = await svc.get('only');
|
|
||||||
expect(card!.status).toBe('claimed');
|
|
||||||
expect(card!.attempts).toBe(1);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('many concurrent claimers on N cards => no card is double-claimed', async () => {
|
|
||||||
// 5 ready cards, 8 concurrent claimers. Exactly 5 win, all distinct.
|
|
||||||
for (let i = 0; i < 5; i++) {
|
|
||||||
await svc.create({ id: `card-${i}`, title: `card ${i}`, priority: i });
|
|
||||||
}
|
|
||||||
const claimers = Array.from({ length: 8 }, (_, i) =>
|
|
||||||
new BacklogService(handle.db).claim({ owner: `w-${i}` }),
|
|
||||||
);
|
|
||||||
const results = await Promise.all(claimers);
|
|
||||||
const won = results.filter((c): c is NonNullable<typeof c> => c !== null);
|
|
||||||
const wonIds = won.map((c) => c.id);
|
|
||||||
expect(won).toHaveLength(5);
|
|
||||||
expect(new Set(wonIds).size).toBe(5); // all distinct — no double-claim
|
|
||||||
});
|
|
||||||
|
|
||||||
it('N concurrent claimers on N ready cards => every claimer wins a distinct card (no starvation)', async () => {
|
|
||||||
// This is the direct benefit of locking exactly ONE ready row per claim
|
|
||||||
// (`FOR UPDATE SKIP LOCKED LIMIT 1`): with as many ready cards as
|
|
||||||
// claimers, NONE should starve. The old "lock the whole ready set"
|
|
||||||
// behaviour let one claimer lock every row, forcing the rest to null even
|
|
||||||
// though cards were free.
|
|
||||||
const N = 6;
|
|
||||||
for (let i = 0; i < N; i++) {
|
|
||||||
await svc.create({ id: `n-${i}`, title: `card ${i}`, priority: i });
|
|
||||||
}
|
|
||||||
const results = await Promise.all(
|
|
||||||
Array.from({ length: N }, (_, i) =>
|
|
||||||
new BacklogService(handle.db).claim({ owner: `w-${i}` }),
|
|
||||||
),
|
|
||||||
);
|
|
||||||
const won = results.filter((c): c is NonNullable<typeof c> => c !== null);
|
|
||||||
// No claimer starved: all N won.
|
|
||||||
expect(won).toHaveLength(N);
|
|
||||||
// Each won a distinct card.
|
|
||||||
expect(new Set(won.map((c) => c.id)).size).toBe(N);
|
|
||||||
// Every ready card was consumed.
|
|
||||||
expect(await svc.list({ status: 'ready' })).toHaveLength(0);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('sequential claims drain ready cards in priority order and never null while ready remain', async () => {
|
|
||||||
// PGlite-stable fallback assertion of the same property without relying on
|
|
||||||
// true parallelism or wall-clock timing: each claim returns the next
|
|
||||||
// highest-priority distinct card and never spuriously returns null while
|
|
||||||
// ready cards remain.
|
|
||||||
const N = 4;
|
|
||||||
for (let i = 0; i < N; i++) {
|
|
||||||
await svc.create({ id: `s-${i}`, title: `card ${i}`, priority: i });
|
|
||||||
}
|
|
||||||
const order: string[] = [];
|
|
||||||
for (let i = 0; i < N; i++) {
|
|
||||||
const claimed = await svc.claim({ owner: `w-${i}` });
|
|
||||||
expect(claimed).not.toBeNull();
|
|
||||||
order.push(claimed!.id);
|
|
||||||
}
|
|
||||||
// Highest priority first, all distinct.
|
|
||||||
expect(order).toEqual(['s-3', 's-2', 's-1', 's-0']);
|
|
||||||
expect(new Set(order).size).toBe(N);
|
|
||||||
// Now nothing ready remains => null.
|
|
||||||
expect(await svc.claim({ owner: 'late' })).toBeNull();
|
|
||||||
});
|
|
||||||
|
|
||||||
it('claim picks the highest-priority ready card', async () => {
|
|
||||||
await svc.create({ id: 'low', title: 'low', priority: 1 });
|
|
||||||
await svc.create({ id: 'high', title: 'high', priority: 9 });
|
|
||||||
const claimed = await svc.claim({ owner: 'w' });
|
|
||||||
expect(claimed!.id).toBe('high');
|
|
||||||
});
|
|
||||||
|
|
||||||
it('claim of a specific --id', async () => {
|
|
||||||
await svc.create({ id: 'a', title: 'a', priority: 9 });
|
|
||||||
await svc.create({ id: 'b', title: 'b', priority: 1 });
|
|
||||||
const claimed = await svc.claim({ owner: 'w', id: 'b' });
|
|
||||||
expect(claimed!.id).toBe('b');
|
|
||||||
});
|
|
||||||
|
|
||||||
it('claim returns null when nothing is ready', async () => {
|
|
||||||
const claimed = await svc.claim({ owner: 'w' });
|
|
||||||
expect(claimed).toBeNull();
|
|
||||||
});
|
|
||||||
});
|
|
||||||
|
|
||||||
describe('deps DAG gate', () => {
|
|
||||||
it('card with an unfinished dep is not claimable and not ready', async () => {
|
|
||||||
await svc.create({ id: 'dep', title: 'dependency' });
|
|
||||||
await svc.create({ id: 'main', title: 'depends on dep', dependsOn: ['dep'] });
|
|
||||||
|
|
||||||
// `main` should NOT be claimable while `dep` is not done — `dep` wins.
|
|
||||||
const first = await svc.claim({ owner: 'w' });
|
|
||||||
expect(first!.id).toBe('dep');
|
|
||||||
|
|
||||||
// With dep claimed (not done), main still cannot be claimed.
|
|
||||||
const second = await svc.claim({ owner: 'w' });
|
|
||||||
expect(second).toBeNull();
|
|
||||||
|
|
||||||
// ready-only list excludes main while its dep is unfinished.
|
|
||||||
const ready = await svc.list({ readyOnly: true });
|
|
||||||
expect(ready.map((c) => c.id)).not.toContain('main');
|
|
||||||
|
|
||||||
// Once dep is done, main becomes ready and claimable.
|
|
||||||
await svc.complete('dep');
|
|
||||||
const readyAfter = await svc.list({ readyOnly: true });
|
|
||||||
expect(readyAfter.map((c) => c.id)).toContain('main');
|
|
||||||
const third = await svc.claim({ owner: 'w' });
|
|
||||||
expect(third!.id).toBe('main');
|
|
||||||
});
|
|
||||||
|
|
||||||
it('link adds a depends_on edge', async () => {
|
|
||||||
await svc.create({ id: 'a', title: 'a' });
|
|
||||||
await svc.create({ id: 'b', title: 'b' });
|
|
||||||
const linked = await svc.link('a', 'b');
|
|
||||||
expect(linked.dependsOn).toEqual(['b']);
|
|
||||||
// a is now gated on b
|
|
||||||
const claimed = await svc.claim({ owner: 'w' });
|
|
||||||
expect(claimed!.id).toBe('b');
|
|
||||||
});
|
|
||||||
});
|
|
||||||
|
|
||||||
describe('reclaim TTL', () => {
|
|
||||||
it('reclaim returns expired claims to ready', async () => {
|
|
||||||
await svc.create({ id: 'c1', title: 'c1' });
|
|
||||||
const claimed = await svc.claim({ owner: 'w', ttlSeconds: 60 });
|
|
||||||
expect(claimed!.status).toBe('claimed');
|
|
||||||
|
|
||||||
// Backdate the claim so it is well past its TTL.
|
|
||||||
await handle.db.execute(sqlBackdate('c1'));
|
|
||||||
|
|
||||||
const result = await svc.reclaim();
|
|
||||||
expect(result.reclaimed).toEqual(['c1']);
|
|
||||||
const card = await svc.get('c1');
|
|
||||||
expect(card!.status).toBe('ready');
|
|
||||||
expect(card!.claimOwner).toBeNull();
|
|
||||||
expect(card!.claimedAt).toBeNull();
|
|
||||||
});
|
|
||||||
|
|
||||||
it('reclaim does not touch a fresh (unexpired) claim', async () => {
|
|
||||||
await svc.create({ id: 'c1', title: 'c1' });
|
|
||||||
await svc.claim({ owner: 'w', ttlSeconds: 3600 });
|
|
||||||
const result = await svc.reclaim();
|
|
||||||
expect(result.reclaimed).toEqual([]);
|
|
||||||
expect((await svc.get('c1'))!.status).toBe('claimed');
|
|
||||||
});
|
|
||||||
|
|
||||||
it('reclaim --id releases a specific claim regardless of expiry', async () => {
|
|
||||||
await svc.create({ id: 'c1', title: 'c1' });
|
|
||||||
await svc.claim({ owner: 'w', ttlSeconds: 3600 });
|
|
||||||
const result = await svc.reclaim({ id: 'c1' });
|
|
||||||
expect(result.reclaimed).toEqual(['c1']);
|
|
||||||
expect((await svc.get('c1'))!.status).toBe('ready');
|
|
||||||
});
|
|
||||||
});
|
|
||||||
|
|
||||||
describe('stats', () => {
|
|
||||||
it('computes counts, oldest-ready age, and expired-claim count', async () => {
|
|
||||||
await svc.create({ id: 'r1', title: 'r1' });
|
|
||||||
await svc.create({ id: 'r2', title: 'r2' });
|
|
||||||
await svc.create({ id: 'b1', title: 'b1' });
|
|
||||||
await svc.block('b1');
|
|
||||||
await svc.create({ id: 'd1', title: 'd1' });
|
|
||||||
await svc.complete('d1');
|
|
||||||
await svc.create({ id: 'cl1', title: 'cl1' });
|
|
||||||
await svc.claim({ owner: 'w', id: 'cl1', ttlSeconds: 60 });
|
|
||||||
await handle.db.execute(sqlBackdate('cl1'));
|
|
||||||
|
|
||||||
const stats = await svc.stats();
|
|
||||||
expect(stats.counts.ready).toBe(2);
|
|
||||||
expect(stats.counts.blocked).toBe(1);
|
|
||||||
expect(stats.counts.done).toBe(1);
|
|
||||||
expect(stats.counts.claimed).toBe(1);
|
|
||||||
expect(stats.total).toBe(5);
|
|
||||||
expect(stats.expiredClaimCount).toBe(1);
|
|
||||||
expect(stats.oldestReadyAgeSeconds).not.toBeNull();
|
|
||||||
expect(stats.oldestReadyAgeSeconds!).toBeGreaterThanOrEqual(0);
|
|
||||||
});
|
|
||||||
});
|
|
||||||
});
|
|
||||||
@@ -1,457 +0,0 @@
|
|||||||
/**
|
|
||||||
* Mosaic-native backlog-of-record service (card A4).
|
|
||||||
*
|
|
||||||
* This is the backlog Mosaic owns end-to-end on its OWN Postgres storage layer.
|
|
||||||
* It REPLACES the former Hermes adapter — there is NO runtime dependency on
|
|
||||||
* Hermes here or anywhere downstream.
|
|
||||||
*
|
|
||||||
* The service takes a `Db` handle, so it works identically against:
|
|
||||||
* - `createDb()` — server Postgres (DATABASE_URL / config), and
|
|
||||||
* - `createPgliteDb()` — embedded Postgres (file or in-memory).
|
|
||||||
* Same code, same semantics — PGlite gives real Postgres behaviour (including
|
|
||||||
* row locks), so the atomic-claim path is exercised by the in-memory tests.
|
|
||||||
*
|
|
||||||
* Atomic claim: `claim()` selects the highest-priority, deps-satisfied, ready
|
|
||||||
* card with `SELECT ... FOR UPDATE SKIP LOCKED` and flips it to `claimed` inside
|
|
||||||
* one transaction. Two concurrent claimers can therefore NEVER both win the same
|
|
||||||
* card — the loser's locked row is skipped and it picks the next candidate (or
|
|
||||||
* gets null).
|
|
||||||
*/
|
|
||||||
|
|
||||||
import { and, asc, desc, eq, sql } from 'drizzle-orm';
|
|
||||||
import type { Db } from './client.js';
|
|
||||||
import { backlog } from './schema.js';
|
|
||||||
|
|
||||||
export type BacklogStatus = 'ready' | 'claimed' | 'blocked' | 'done';
|
|
||||||
|
|
||||||
export interface BacklogCard {
|
|
||||||
id: string;
|
|
||||||
title: string;
|
|
||||||
body: string | null;
|
|
||||||
phase: string | null;
|
|
||||||
priority: number;
|
|
||||||
status: BacklogStatus;
|
|
||||||
dependsOn: string[];
|
|
||||||
claimOwner: string | null;
|
|
||||||
claimTtlSeconds: number | null;
|
|
||||||
claimedAt: Date | null;
|
|
||||||
attempts: number;
|
|
||||||
idempotencyKey: string | null;
|
|
||||||
acceptance: unknown;
|
|
||||||
createdAt: Date;
|
|
||||||
updatedAt: Date;
|
|
||||||
}
|
|
||||||
|
|
||||||
export interface CreateCardInput {
|
|
||||||
id: string;
|
|
||||||
title: string;
|
|
||||||
body?: string | null;
|
|
||||||
phase?: string | null;
|
|
||||||
priority?: number;
|
|
||||||
dependsOn?: string[];
|
|
||||||
acceptance?: unknown;
|
|
||||||
idempotencyKey?: string | null;
|
|
||||||
status?: BacklogStatus;
|
|
||||||
}
|
|
||||||
|
|
||||||
export interface ListFilter {
|
|
||||||
status?: BacklogStatus;
|
|
||||||
phase?: string;
|
|
||||||
/** When true, return only cards that are `ready` AND have all deps `done`. */
|
|
||||||
readyOnly?: boolean;
|
|
||||||
}
|
|
||||||
|
|
||||||
export interface ClaimOptions {
|
|
||||||
owner: string;
|
|
||||||
/** Claim time-to-live in seconds (default 900). */
|
|
||||||
ttlSeconds?: number;
|
|
||||||
/** Claim a specific card by id instead of the highest-priority ready one. */
|
|
||||||
id?: string;
|
|
||||||
}
|
|
||||||
|
|
||||||
export interface ReclaimResult {
|
|
||||||
reclaimed: string[];
|
|
||||||
}
|
|
||||||
|
|
||||||
export interface BacklogStats {
|
|
||||||
counts: Record<BacklogStatus, number>;
|
|
||||||
total: number;
|
|
||||||
oldestReadyAgeSeconds: number | null;
|
|
||||||
expiredClaimCount: number;
|
|
||||||
}
|
|
||||||
|
|
||||||
export const DEFAULT_CLAIM_TTL_SECONDS = 900;
|
|
||||||
|
|
||||||
type Row = typeof backlog.$inferSelect;
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Row shape as returned by the raw `SELECT * ... FOR UPDATE SKIP LOCKED` path.
|
|
||||||
* That path bypasses drizzle's column-name mapping, so JSON columns arrive as
|
|
||||||
* the snake_case `depends_on` (and may be a JSON string under some drivers).
|
|
||||||
*/
|
|
||||||
interface RawRow extends Row {
|
|
||||||
depends_on?: unknown;
|
|
||||||
}
|
|
||||||
|
|
||||||
function toCard(row: Row): BacklogCard {
|
|
||||||
return {
|
|
||||||
id: row.id,
|
|
||||||
title: row.title,
|
|
||||||
body: row.body,
|
|
||||||
phase: row.phase,
|
|
||||||
priority: row.priority,
|
|
||||||
status: row.status,
|
|
||||||
dependsOn: row.dependsOn ?? [],
|
|
||||||
claimOwner: row.claimOwner,
|
|
||||||
claimTtlSeconds: row.claimTtlSeconds,
|
|
||||||
claimedAt: row.claimedAt,
|
|
||||||
attempts: row.attempts,
|
|
||||||
idempotencyKey: row.idempotencyKey,
|
|
||||||
acceptance: row.acceptance,
|
|
||||||
createdAt: row.createdAt,
|
|
||||||
updatedAt: row.updatedAt,
|
|
||||||
};
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* The backlog repository/service. Construct with any `Db` handle.
|
|
||||||
*/
|
|
||||||
export class BacklogService {
|
|
||||||
constructor(private readonly db: Db) {}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Create a card. If `idempotencyKey` is provided and a card already exists
|
|
||||||
* with that key, the existing card is returned unchanged (no duplicate).
|
|
||||||
*/
|
|
||||||
async create(input: CreateCardInput): Promise<BacklogCard> {
|
|
||||||
if (input.idempotencyKey) {
|
|
||||||
const existing = await this.db
|
|
||||||
.select()
|
|
||||||
.from(backlog)
|
|
||||||
.where(eq(backlog.idempotencyKey, input.idempotencyKey))
|
|
||||||
.limit(1);
|
|
||||||
if (existing[0]) return toCard(existing[0]);
|
|
||||||
}
|
|
||||||
|
|
||||||
const inserted = await this.db
|
|
||||||
.insert(backlog)
|
|
||||||
.values({
|
|
||||||
id: input.id,
|
|
||||||
title: input.title,
|
|
||||||
body: input.body ?? null,
|
|
||||||
phase: input.phase ?? null,
|
|
||||||
priority: input.priority ?? 0,
|
|
||||||
status: input.status ?? 'ready',
|
|
||||||
dependsOn: input.dependsOn ?? [],
|
|
||||||
acceptance: input.acceptance ?? null,
|
|
||||||
idempotencyKey: input.idempotencyKey ?? null,
|
|
||||||
})
|
|
||||||
.returning();
|
|
||||||
|
|
||||||
return toCard(inserted[0]!);
|
|
||||||
}
|
|
||||||
|
|
||||||
/** Fetch a single card by id, or null. */
|
|
||||||
async get(id: string): Promise<BacklogCard | null> {
|
|
||||||
const rows = await this.db.select().from(backlog).where(eq(backlog.id, id)).limit(1);
|
|
||||||
return rows[0] ? toCard(rows[0]) : null;
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* List cards with optional filters. `readyOnly` enforces the DAG gate:
|
|
||||||
* a card is "ready" only when its own status is `ready` AND every card in
|
|
||||||
* `depends_on` exists and is `done`.
|
|
||||||
*/
|
|
||||||
async list(filter: ListFilter = {}): Promise<BacklogCard[]> {
|
|
||||||
const conditions = [];
|
|
||||||
if (filter.status) conditions.push(eq(backlog.status, filter.status));
|
|
||||||
if (filter.phase) conditions.push(eq(backlog.phase, filter.phase));
|
|
||||||
|
|
||||||
const rows = await this.db
|
|
||||||
.select()
|
|
||||||
.from(backlog)
|
|
||||||
.where(conditions.length ? and(...conditions) : undefined)
|
|
||||||
.orderBy(desc(backlog.priority), asc(backlog.createdAt));
|
|
||||||
|
|
||||||
const cards = rows.map(toCard);
|
|
||||||
if (!filter.readyOnly) return cards;
|
|
||||||
|
|
||||||
const doneIds = await this.doneIdSet();
|
|
||||||
return cards.filter(
|
|
||||||
(c) => c.status === 'ready' && c.dependsOn.every((dep) => doneIds.has(dep)),
|
|
||||||
);
|
|
||||||
}
|
|
||||||
|
|
||||||
private async doneIdSet(): Promise<Set<string>> {
|
|
||||||
const done = await this.db
|
|
||||||
.select({ id: backlog.id })
|
|
||||||
.from(backlog)
|
|
||||||
.where(eq(backlog.status, 'done'));
|
|
||||||
return new Set(done.map((d) => d.id));
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Atomically claim a card.
|
|
||||||
*
|
|
||||||
* Strategy: inside ONE transaction we lock the candidate row with
|
|
||||||
* `FOR UPDATE SKIP LOCKED LIMIT 1`. A concurrent claimer that already holds
|
|
||||||
* the lock on a row has that row skipped for us, so two claimers can never
|
|
||||||
* both win the same card — and, crucially, each claimer locks exactly ONE
|
|
||||||
* row, so concurrent claimers fan out across distinct ready cards instead of
|
|
||||||
* one claimer locking the whole ready set and starving the rest.
|
|
||||||
*
|
|
||||||
* Candidate selection (when no explicit `id`):
|
|
||||||
* - status = 'ready'
|
|
||||||
* - all deps satisfied (every id in depends_on is currently 'done')
|
|
||||||
* - ordered by priority DESC, created_at ASC
|
|
||||||
*
|
|
||||||
* Returns the claimed card, or null if nothing is claimable.
|
|
||||||
*/
|
|
||||||
async claim(opts: ClaimOptions): Promise<BacklogCard | null> {
|
|
||||||
const ttl = opts.ttlSeconds ?? DEFAULT_CLAIM_TTL_SECONDS;
|
|
||||||
|
|
||||||
return this.db.transaction(async (tx) => {
|
|
||||||
// Specific-id path: lock that one ready row (if free) and apply the
|
|
||||||
// deps-satisfied gate in JS, exactly as before.
|
|
||||||
if (opts.id) {
|
|
||||||
const doneRows = await tx
|
|
||||||
.select({ id: backlog.id })
|
|
||||||
.from(backlog)
|
|
||||||
.where(eq(backlog.status, 'done'));
|
|
||||||
const doneIds = new Set(doneRows.map((r) => r.id));
|
|
||||||
|
|
||||||
const result = await tx.execute(
|
|
||||||
sql`SELECT * FROM ${backlog}
|
|
||||||
WHERE ${backlog.id} = ${opts.id} AND ${backlog.status} = 'ready'
|
|
||||||
FOR UPDATE SKIP LOCKED`,
|
|
||||||
);
|
|
||||||
const candidate = rowsOf(result).find((row) =>
|
|
||||||
normalizeDeps(row.depends_on).every((dep) => doneIds.has(dep)),
|
|
||||||
);
|
|
||||||
if (!candidate) return null;
|
|
||||||
|
|
||||||
const updated = await tx
|
|
||||||
.update(backlog)
|
|
||||||
.set({
|
|
||||||
status: 'claimed',
|
|
||||||
claimOwner: opts.owner,
|
|
||||||
claimTtlSeconds: ttl,
|
|
||||||
claimedAt: new Date(),
|
|
||||||
attempts: sql`${backlog.attempts} + 1`,
|
|
||||||
updatedAt: new Date(),
|
|
||||||
})
|
|
||||||
.where(eq(backlog.id, candidate.id))
|
|
||||||
.returning();
|
|
||||||
|
|
||||||
return toCard(updated[0]!);
|
|
||||||
}
|
|
||||||
|
|
||||||
// No-id path: claim the single highest-priority, deps-satisfied ready
|
|
||||||
// card. We lock exactly ONE row in the inner SELECT (`FOR UPDATE SKIP
|
|
||||||
// LOCKED LIMIT 1`) so concurrent claimers grab distinct cards rather than
|
|
||||||
// one claimer locking every ready row and forcing the others to null.
|
|
||||||
//
|
|
||||||
// The deps-satisfied gate is pushed into SQL so `LIMIT 1` lands on the
|
|
||||||
// next genuinely-eligible card: a card is eligible iff none of its
|
|
||||||
// depends_on ids is absent from the set of 'done' card ids.
|
|
||||||
const updated = await tx.execute(
|
|
||||||
sql`UPDATE ${backlog}
|
|
||||||
SET status = 'claimed',
|
|
||||||
claim_owner = ${opts.owner},
|
|
||||||
claim_ttl_seconds = ${ttl},
|
|
||||||
claimed_at = now(),
|
|
||||||
attempts = ${backlog.attempts} + 1,
|
|
||||||
updated_at = now()
|
|
||||||
WHERE ${backlog.id} = (
|
|
||||||
SELECT b.id FROM ${backlog} AS b
|
|
||||||
WHERE b.status = 'ready'
|
|
||||||
AND NOT EXISTS (
|
|
||||||
SELECT 1
|
|
||||||
FROM jsonb_array_elements_text(b.depends_on) AS dep
|
|
||||||
WHERE dep NOT IN (
|
|
||||||
SELECT d.id FROM ${backlog} AS d WHERE d.status = 'done'
|
|
||||||
)
|
|
||||||
)
|
|
||||||
ORDER BY b.priority DESC, b.created_at ASC
|
|
||||||
FOR UPDATE SKIP LOCKED
|
|
||||||
LIMIT 1
|
|
||||||
)
|
|
||||||
RETURNING *`,
|
|
||||||
);
|
|
||||||
|
|
||||||
const row = rowsOf(updated)[0];
|
|
||||||
return row ? toCard(rawToRow(row)) : null;
|
|
||||||
});
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Release expired claims (claimed_at + ttl < now) back to `ready`, OR release
|
|
||||||
* a specific card by id regardless of expiry. Cleared claim fields.
|
|
||||||
* Returns the ids that were released.
|
|
||||||
*/
|
|
||||||
async reclaim(opts: { id?: string } = {}): Promise<ReclaimResult> {
|
|
||||||
if (opts.id) {
|
|
||||||
const released = await this.db
|
|
||||||
.update(backlog)
|
|
||||||
.set({
|
|
||||||
status: 'ready',
|
|
||||||
claimOwner: null,
|
|
||||||
claimTtlSeconds: null,
|
|
||||||
claimedAt: null,
|
|
||||||
updatedAt: new Date(),
|
|
||||||
})
|
|
||||||
.where(and(eq(backlog.id, opts.id), eq(backlog.status, 'claimed')))
|
|
||||||
.returning({ id: backlog.id });
|
|
||||||
return { reclaimed: released.map((r) => r.id) };
|
|
||||||
}
|
|
||||||
|
|
||||||
// Expired = status claimed AND claimed_at + (ttl seconds) < now().
|
|
||||||
const released = await this.db
|
|
||||||
.update(backlog)
|
|
||||||
.set({
|
|
||||||
status: 'ready',
|
|
||||||
claimOwner: null,
|
|
||||||
claimTtlSeconds: null,
|
|
||||||
claimedAt: null,
|
|
||||||
updatedAt: new Date(),
|
|
||||||
})
|
|
||||||
.where(
|
|
||||||
and(
|
|
||||||
eq(backlog.status, 'claimed'),
|
|
||||||
sql`${backlog.claimedAt} + make_interval(secs => ${backlog.claimTtlSeconds}) < now()`,
|
|
||||||
),
|
|
||||||
)
|
|
||||||
.returning({ id: backlog.id });
|
|
||||||
return { reclaimed: released.map((r) => r.id) };
|
|
||||||
}
|
|
||||||
|
|
||||||
/** Add a `depends_on` edge (from → depends on → to). Idempotent. */
|
|
||||||
async link(from: string, to: string): Promise<BacklogCard> {
|
|
||||||
const card = await this.get(from);
|
|
||||||
if (!card) throw new Error(`backlog card not found: ${from}`);
|
|
||||||
const target = await this.get(to);
|
|
||||||
if (!target) throw new Error(`backlog dependency not found: ${to}`);
|
|
||||||
if (from === to) throw new Error('a card cannot depend on itself');
|
|
||||||
|
|
||||||
if (card.dependsOn.includes(to)) return card;
|
|
||||||
const nextDeps = [...card.dependsOn, to];
|
|
||||||
const updated = await this.db
|
|
||||||
.update(backlog)
|
|
||||||
.set({ dependsOn: nextDeps, updatedAt: new Date() })
|
|
||||||
.where(eq(backlog.id, from))
|
|
||||||
.returning();
|
|
||||||
return toCard(updated[0]!);
|
|
||||||
}
|
|
||||||
|
|
||||||
/** Mark a card blocked. */
|
|
||||||
async block(id: string): Promise<BacklogCard | null> {
|
|
||||||
return this.setStatus(id, 'blocked');
|
|
||||||
}
|
|
||||||
|
|
||||||
/** Mark a card done (releasing any claim). */
|
|
||||||
async complete(id: string): Promise<BacklogCard | null> {
|
|
||||||
const updated = await this.db
|
|
||||||
.update(backlog)
|
|
||||||
.set({
|
|
||||||
status: 'done',
|
|
||||||
claimOwner: null,
|
|
||||||
claimTtlSeconds: null,
|
|
||||||
claimedAt: null,
|
|
||||||
updatedAt: new Date(),
|
|
||||||
})
|
|
||||||
.where(eq(backlog.id, id))
|
|
||||||
.returning();
|
|
||||||
return updated[0] ? toCard(updated[0]) : null;
|
|
||||||
}
|
|
||||||
|
|
||||||
private async setStatus(id: string, status: BacklogStatus): Promise<BacklogCard | null> {
|
|
||||||
const updated = await this.db
|
|
||||||
.update(backlog)
|
|
||||||
.set({ status, updatedAt: new Date() })
|
|
||||||
.where(eq(backlog.id, id))
|
|
||||||
.returning();
|
|
||||||
return updated[0] ? toCard(updated[0]) : null;
|
|
||||||
}
|
|
||||||
|
|
||||||
/** Counts by status, oldest-ready age (seconds), and expired-claim count. */
|
|
||||||
async stats(): Promise<BacklogStats> {
|
|
||||||
const all = await this.db.select().from(backlog);
|
|
||||||
const counts: Record<BacklogStatus, number> = {
|
|
||||||
ready: 0,
|
|
||||||
claimed: 0,
|
|
||||||
blocked: 0,
|
|
||||||
done: 0,
|
|
||||||
};
|
|
||||||
let oldestReady: Date | null = null;
|
|
||||||
let expiredClaimCount = 0;
|
|
||||||
const now = Date.now();
|
|
||||||
|
|
||||||
for (const row of all) {
|
|
||||||
counts[row.status] += 1;
|
|
||||||
if (row.status === 'ready') {
|
|
||||||
if (oldestReady === null || row.createdAt < oldestReady) oldestReady = row.createdAt;
|
|
||||||
}
|
|
||||||
if (row.status === 'claimed' && row.claimedAt && row.claimTtlSeconds != null) {
|
|
||||||
const expiry = row.claimedAt.getTime() + row.claimTtlSeconds * 1000;
|
|
||||||
if (expiry < now) expiredClaimCount += 1;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
return {
|
|
||||||
counts,
|
|
||||||
total: all.length,
|
|
||||||
oldestReadyAgeSeconds:
|
|
||||||
oldestReady === null ? null : Math.max(0, Math.floor((now - oldestReady.getTime()) / 1000)),
|
|
||||||
expiredClaimCount,
|
|
||||||
};
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
/** Extract rows from a drizzle `.execute()` result across drivers (pg / pglite). */
|
|
||||||
function rowsOf(result: unknown): RawRow[] {
|
|
||||||
if (Array.isArray(result)) return result as RawRow[];
|
|
||||||
const maybe = result as { rows?: unknown };
|
|
||||||
if (maybe && Array.isArray(maybe.rows)) return maybe.rows as RawRow[];
|
|
||||||
return [];
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Map a raw `RETURNING *` row (snake_case columns, possibly string-encoded
|
|
||||||
* timestamps/JSON depending on the driver) onto the drizzle `Row` shape that
|
|
||||||
* `toCard` consumes. Mirrors the column ↔ property mapping in `schema.ts`.
|
|
||||||
*/
|
|
||||||
function rawToRow(raw: RawRow): Row {
|
|
||||||
const r = raw as unknown as Record<string, unknown>;
|
|
||||||
const toDate = (v: unknown): Date => (v instanceof Date ? v : new Date(v as string));
|
|
||||||
return {
|
|
||||||
id: r.id as string,
|
|
||||||
title: r.title as string,
|
|
||||||
body: (r.body ?? null) as string | null,
|
|
||||||
phase: (r.phase ?? null) as string | null,
|
|
||||||
priority: Number(r.priority),
|
|
||||||
status: r.status as BacklogStatus,
|
|
||||||
dependsOn: normalizeDeps(r.depends_on),
|
|
||||||
claimOwner: (r.claim_owner ?? null) as string | null,
|
|
||||||
claimTtlSeconds: r.claim_ttl_seconds == null ? null : Number(r.claim_ttl_seconds),
|
|
||||||
claimedAt: r.claimed_at == null ? null : toDate(r.claimed_at),
|
|
||||||
attempts: Number(r.attempts),
|
|
||||||
idempotencyKey: (r.idempotency_key ?? null) as string | null,
|
|
||||||
acceptance: r.acceptance ?? null,
|
|
||||||
createdAt: toDate(r.created_at),
|
|
||||||
updatedAt: toDate(r.updated_at),
|
|
||||||
};
|
|
||||||
}
|
|
||||||
|
|
||||||
/** A raw SQL row returns snake_case `depends_on`; normalize to string[]. */
|
|
||||||
function normalizeDeps(value: unknown): string[] {
|
|
||||||
if (Array.isArray(value)) return value as string[];
|
|
||||||
if (typeof value === 'string') {
|
|
||||||
try {
|
|
||||||
const parsed = JSON.parse(value);
|
|
||||||
return Array.isArray(parsed) ? (parsed as string[]) : [];
|
|
||||||
} catch {
|
|
||||||
return [];
|
|
||||||
}
|
|
||||||
}
|
|
||||||
return [];
|
|
||||||
}
|
|
||||||
@@ -3,17 +3,6 @@ export { createPgliteDb } from './client-pglite.js';
|
|||||||
export { runMigrations, runPgliteMigrations } from './migrate.js';
|
export { runMigrations, runPgliteMigrations } from './migrate.js';
|
||||||
export * from './schema.js';
|
export * from './schema.js';
|
||||||
export * from './federation.js';
|
export * from './federation.js';
|
||||||
export {
|
|
||||||
BacklogService,
|
|
||||||
DEFAULT_CLAIM_TTL_SECONDS,
|
|
||||||
type BacklogCard,
|
|
||||||
type BacklogStatus,
|
|
||||||
type BacklogStats,
|
|
||||||
type ClaimOptions,
|
|
||||||
type CreateCardInput,
|
|
||||||
type ListFilter,
|
|
||||||
type ReclaimResult,
|
|
||||||
} from './backlog.js';
|
|
||||||
export {
|
export {
|
||||||
eq,
|
eq,
|
||||||
and,
|
and,
|
||||||
|
|||||||
@@ -587,62 +587,6 @@ export const summarizationJobs = pgTable(
|
|||||||
(t) => [index('summarization_jobs_status_idx').on(t.status)],
|
(t) => [index('summarization_jobs_status_idx').on(t.status)],
|
||||||
);
|
);
|
||||||
|
|
||||||
// ─── Fleet Backlog ────────────────────────────────────────────────────────────
|
|
||||||
// Mosaic-native backlog-of-record (card A4). This REPLACES the former Hermes
|
|
||||||
// adapter — there is NO runtime dependency on Hermes. Cards form a dependency
|
|
||||||
// DAG (`depends_on`), are claimed atomically by fleet workers via
|
|
||||||
// `SELECT ... FOR UPDATE SKIP LOCKED`, and auto-expire via a TTL so a crashed
|
|
||||||
// claimer's card returns to the pool.
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Lifecycle status of a backlog card.
|
|
||||||
* - ready: eligible to be claimed (once its deps are all `done`).
|
|
||||||
* - claimed: a worker holds it (claim_owner + claimed_at set); may expire via TTL.
|
|
||||||
* - blocked: explicitly parked; never auto-claimed.
|
|
||||||
* - done: completed; satisfies dependents.
|
|
||||||
*/
|
|
||||||
export const backlogStatusEnum = pgEnum('backlog_status', ['ready', 'claimed', 'blocked', 'done']);
|
|
||||||
|
|
||||||
export const backlog = pgTable(
|
|
||||||
'backlog',
|
|
||||||
{
|
|
||||||
/** Stable, caller-supplied card id (e.g. "A4", "fleet-001"). PK. */
|
|
||||||
id: text('id').primaryKey(),
|
|
||||||
title: text('title').notNull(),
|
|
||||||
body: text('body'),
|
|
||||||
/** Board/phase grouping (e.g. "M1", "fleet"). Free-form. */
|
|
||||||
phase: text('phase'),
|
|
||||||
/** Higher number = higher priority; claim picks the max-priority ready card. */
|
|
||||||
priority: integer('priority').notNull().default(0),
|
|
||||||
status: backlogStatusEnum('status').notNull().default('ready'),
|
|
||||||
/** DAG edges: ids of cards this one depends on. "ready" requires all done. */
|
|
||||||
dependsOn: jsonb('depends_on').notNull().$type<string[]>().default([]),
|
|
||||||
/** Owner token of the current claim (worker/agent id). NULL when unclaimed. */
|
|
||||||
claimOwner: text('claim_owner'),
|
|
||||||
/** TTL of the active claim in seconds. NULL when unclaimed. */
|
|
||||||
claimTtlSeconds: integer('claim_ttl_seconds'),
|
|
||||||
/** When the active claim was taken. NULL when unclaimed. claimed_at + ttl = expiry. */
|
|
||||||
claimedAt: timestamp('claimed_at', { withTimezone: true }),
|
|
||||||
/** Count of times this card has been claimed (incremented on each claim). */
|
|
||||||
attempts: integer('attempts').notNull().default(0),
|
|
||||||
/** Optional dedup key for `create`; a repeat key returns the existing card. */
|
|
||||||
idempotencyKey: text('idempotency_key'),
|
|
||||||
/** Acceptance criteria — free-form JSON (array of strings or object). */
|
|
||||||
acceptance: jsonb('acceptance'),
|
|
||||||
createdAt: timestamp('created_at', { withTimezone: true }).notNull().defaultNow(),
|
|
||||||
updatedAt: timestamp('updated_at', { withTimezone: true }).notNull().defaultNow(),
|
|
||||||
},
|
|
||||||
(t) => [
|
|
||||||
// Hot path: claim scans ready cards ordered by priority then age.
|
|
||||||
index('backlog_status_priority_idx').on(t.status, t.priority),
|
|
||||||
// reclaim sweeps claimed cards by claimed_at to find expired ones.
|
|
||||||
index('backlog_status_claimed_at_idx').on(t.status, t.claimedAt),
|
|
||||||
// Idempotent create dedups on this key (NULLs are distinct in Postgres, so
|
|
||||||
// many unkeyed cards coexist; a repeated non-null key collides).
|
|
||||||
uniqueIndex('backlog_idempotency_key_idx').on(t.idempotencyKey),
|
|
||||||
],
|
|
||||||
);
|
|
||||||
|
|
||||||
// ─── Federation ──────────────────────────────────────────────────────────────
|
// ─── Federation ──────────────────────────────────────────────────────────────
|
||||||
// Enums declared before tables that reference them.
|
// Enums declared before tables that reference them.
|
||||||
// All federation definitions live in this file (avoids CJS/ESM cross-import
|
// All federation definitions live in this file (avoids CJS/ESM cross-import
|
||||||
|
|||||||
@@ -4,22 +4,5 @@ export default defineConfig({
|
|||||||
test: {
|
test: {
|
||||||
globals: true,
|
globals: true,
|
||||||
environment: 'node',
|
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 },
|
|
||||||
},
|
|
||||||
},
|
},
|
||||||
});
|
});
|
||||||
|
|||||||
@@ -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).
|
|
||||||
@@ -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).
|
|
||||||
@@ -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.
|
|
||||||
@@ -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).
|
|
||||||
@@ -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.
|
|
||||||
@@ -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`.
|
|
||||||
@@ -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).
|
|
||||||
@@ -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).
|
|
||||||
@@ -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).
|
|
||||||
@@ -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.
|
|
||||||
@@ -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.
|
|
||||||
@@ -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).
|
|
||||||
@@ -25,17 +25,13 @@ INSTALL_MODE="${MOSAIC_INSTALL_MODE:-prompt}"
|
|||||||
# User-created content in these paths survives rsync --delete.
|
# User-created content in these paths survives rsync --delete.
|
||||||
#
|
#
|
||||||
# fleet/* — the framework SEEDS only fleet/examples, fleet/roles, and
|
# fleet/* — the framework SEEDS only fleet/examples, fleet/roles, and
|
||||||
# fleet/roster.schema.json (synced normally — every fleet/roles/*.md role contract
|
# fleet/roster.schema.json (synced normally). The user's own fleet files MUST
|
||||||
# lands automatically via this sync, so no per-file entry is needed). The user's
|
|
||||||
# own fleet files MUST
|
|
||||||
# survive `mosaic update` (which runs this sync automatically): the active
|
# survive `mosaic update` (which runs this sync automatically): the active
|
||||||
# roster (`fleet/roster.yaml` + any other `fleet/*.yaml`), per-agent env
|
# roster (`fleet/roster.yaml` + any other `fleet/*.yaml`), per-agent env
|
||||||
# (`fleet/agents/`), heartbeat run dir (`fleet/run/`), and the Mosaic-native
|
# (`fleet/agents/`), and heartbeat run dir (`fleet/run/`). Without these, an
|
||||||
# backlog-of-record store (`fleet/backlog/` — embedded PGlite data dir; see
|
# update wipes the operator's fleet. Glob entries are honored by both the rsync
|
||||||
# packages/mosaic/src/commands/fleet-backlog.ts). Without these, an update
|
# path (`--exclude`) and the glob-aware cp fallback below.
|
||||||
# wipes the operator's fleet AND their backlog. Glob entries are honored by
|
PRESERVE_PATHS=("CONSTITUTION.md" "AGENTS.md" "SOUL.md" "USER.md" "TOOLS.md" "STANDARDS.md" "memory" "sources" "credentials" "fleet/*.yaml" "fleet/agents" "fleet/run")
|
||||||
# both the rsync path (`--exclude`) and the glob-aware cp fallback below.
|
|
||||||
PRESERVE_PATHS=("CONSTITUTION.md" "AGENTS.md" "SOUL.md" "USER.md" "TOOLS.md" "STANDARDS.md" "memory" "sources" "credentials" "fleet/*.yaml" "fleet/agents" "fleet/run" "fleet/backlog")
|
|
||||||
|
|
||||||
# Framework-owned contract files: re-copied from defaults/ on every upgrade (the
|
# Framework-owned contract files: re-copied from defaults/ on every upgrade (the
|
||||||
# user must not edit them; a divergent copy is backed up once before overwrite).
|
# user must not edit them; a divergent copy is backed up once before overwrite).
|
||||||
|
|||||||
@@ -122,85 +122,6 @@ fi
|
|||||||
|
|
||||||
mkdir -p "$MOSAIC_AGENT_WORKDIR"
|
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 $AGENT_NAME" >&2
|
|
||||||
;;
|
|
||||||
esac
|
|
||||||
|
|
||||||
# ── Launch the tmux session (no exec — we continue to wire the heartbeat) ────
|
# ── Launch the tmux session (no exec — we continue to wire the heartbeat) ────
|
||||||
_tmux new-session -d -s "$AGENT_NAME" -c "$MOSAIC_AGENT_WORKDIR" \
|
_tmux new-session -d -s "$AGENT_NAME" -c "$MOSAIC_AGENT_WORKDIR" \
|
||||||
bash -c "$PANE_SHELL_SNIPPET"
|
bash -c "$PANE_SHELL_SNIPPET"
|
||||||
|
|||||||
@@ -128,8 +128,8 @@ PY
|
|||||||
merge_gitea_with_api() {
|
merge_gitea_with_api() {
|
||||||
local host="$1" api_url token basic_auth body_file raw_code payload
|
local host="$1" api_url token basic_auth body_file raw_code payload
|
||||||
api_url="https://${host}/api/v1/repos/${OWNER}/${REPO}/pulls/${PR_NUMBER}/merge"
|
api_url="https://${host}/api/v1/repos/${OWNER}/${REPO}/pulls/${PR_NUMBER}/merge"
|
||||||
mkdir -p "${AGENT_WORK_ROOT:-${HOME:-/tmp}/mosaic/agent-work}"
|
mkdir -p "${AGENT_WORK_ROOT:-/home/hermes/agent-work}"
|
||||||
body_file=$(mktemp "${AGENT_WORK_ROOT:-${HOME:-/tmp}/mosaic/agent-work}/pr-merge-api-response.XXXXXX")
|
body_file=$(mktemp "${AGENT_WORK_ROOT:-/home/hermes/agent-work}/pr-merge-api-response.XXXXXX")
|
||||||
payload='{"Do":"squash"}'
|
payload='{"Do":"squash"}'
|
||||||
|
|
||||||
token=$(get_gitea_token "$host" || true)
|
token=$(get_gitea_token "$host" || true)
|
||||||
@@ -214,8 +214,8 @@ case "$PLATFORM" in
|
|||||||
TEA_LOGIN="$(get_gitea_login_for_host "$HOST" || true)"
|
TEA_LOGIN="$(get_gitea_login_for_host "$HOST" || true)"
|
||||||
|
|
||||||
if [[ -n "$TEA_LOGIN" ]]; then
|
if [[ -n "$TEA_LOGIN" ]]; then
|
||||||
mkdir -p "${AGENT_WORK_ROOT:-${HOME:-/tmp}/mosaic/agent-work}"
|
mkdir -p "${AGENT_WORK_ROOT:-/home/hermes/agent-work}"
|
||||||
TEA_ERROR_FILE=$(mktemp "${AGENT_WORK_ROOT:-${HOME:-/tmp}/mosaic/agent-work}/pr-merge-tea-error.XXXXXX")
|
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> "$TEA_ERROR_FILE"; then
|
if tea pr merge "$PR_NUMBER" --style squash --repo "$OWNER/$REPO" --login "$TEA_LOGIN" 2> "$TEA_ERROR_FILE"; then
|
||||||
rm -f "$TEA_ERROR_FILE"
|
rm -f "$TEA_ERROR_FILE"
|
||||||
elif is_known_tea_empty_identity_failure "$TEA_ERROR_FILE"; then
|
elif is_known_tea_empty_identity_failure "$TEA_ERROR_FILE"; then
|
||||||
|
|||||||
@@ -4,7 +4,7 @@
|
|||||||
set -euo pipefail
|
set -euo pipefail
|
||||||
|
|
||||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
SCRIPT_DIR="$(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-$$"
|
SANDBOX="$WORK_ROOT/pr-merge-empty-uid-test-$$"
|
||||||
MOCK_BIN="$SANDBOX/bin"
|
MOCK_BIN="$SANDBOX/bin"
|
||||||
REPO_DIR="$SANDBOX/repo"
|
REPO_DIR="$SANDBOX/repo"
|
||||||
|
|||||||
@@ -12,10 +12,6 @@
|
|||||||
# ambiguity about lanes or origin. Recipients replying should FLIP the
|
# ambiguity about lanes or origin. Recipients replying should FLIP the
|
||||||
# preamble: [<dst> -> <src>] ... (this tool sends; it does not auto-reply).
|
# preamble: [<dst> -> <src>] ... (this tool sends; it does not auto-reply).
|
||||||
#
|
#
|
||||||
# Optionally tags the message with a TRIAGE CLASS (see -C / --class) so a
|
|
||||||
# comms daemon can route it (deliver-to-agent vs log-and-drop) from an exact
|
|
||||||
# field instead of re-deriving intent from the body.
|
|
||||||
#
|
|
||||||
# WHY A WRAPPER
|
# WHY A WRAPPER
|
||||||
# Reliable submission into an interactive REPL (Claude Code / Codex) is fiddly:
|
# Reliable submission into an interactive REPL (Claude Code / Codex) is fiddly:
|
||||||
# a trailing Enter is often swallowed and the message sits as an unsubmitted
|
# a trailing Enter is often swallowed and the message sits as an unsubmitted
|
||||||
@@ -30,7 +26,6 @@
|
|||||||
# agent-send.sh [-L socket] -s <dst_session> -m "message" # local target
|
# agent-send.sh [-L socket] -s <dst_session> -m "message" # local target
|
||||||
# agent-send.sh [-L socket] -H user@host -s <dst_session> -m "message" # remote target
|
# agent-send.sh [-L socket] -H user@host -s <dst_session> -m "message" # remote target
|
||||||
# agent-send.sh [-L socket] -H user@host -n <dst_hostname> -s <sess> -f msg.txt
|
# agent-send.sh [-L socket] -H user@host -n <dst_hostname> -s <sess> -f msg.txt
|
||||||
# agent-send.sh -s mos-claude --class terminal-log -m "ACK — received"
|
|
||||||
# echo "msg" | agent-send.sh [-L socket] -H user@host -s <dst_session>
|
# echo "msg" | agent-send.sh [-L socket] -H user@host -s <dst_session>
|
||||||
#
|
#
|
||||||
# OPTIONS
|
# OPTIONS
|
||||||
@@ -41,61 +36,27 @@
|
|||||||
# Default: local hostname, or (remote) resolved via one ssh.
|
# Default: local hostname, or (remote) resolved via one ssh.
|
||||||
# -m MESSAGE message text (single- or multi-line)
|
# -m MESSAGE message text (single- or multi-line)
|
||||||
# -f FILE read message from FILE instead of -m
|
# -f FILE read message from FILE instead of -m
|
||||||
# -C CLASS triage class for a comms daemon. One of:
|
|
||||||
# terminal-log log-only; never needs the agent's attention
|
|
||||||
# actionable carries a decision/blocker/gate — deliver
|
|
||||||
# human from a human operator — deliver
|
|
||||||
# reaction an emoji/ack reaction
|
|
||||||
# Long form: --class CLASS (or --class=CLASS). When SET, the
|
|
||||||
# preamble carries a ` class=<CLASS>` token INSIDE the bracket:
|
|
||||||
# [<src> -> <dst> class=terminal-log] <message>
|
|
||||||
# When OMITTED, NO token is emitted and the preamble is
|
|
||||||
# byte-for-byte identical to the classic format. Consumers MUST
|
|
||||||
# treat an absent class as 'actionable' (fail-safe: agent sees it).
|
|
||||||
# -S SRC_LABEL override source label "<host>:<session>" (default: auto)
|
# -S SRC_LABEL override source label "<host>:<session>" (default: auto)
|
||||||
# -r N Enter-flush attempts passed through (default 2)
|
# -r N Enter-flush attempts passed through (default 2)
|
||||||
# -v verbose: print pane tail after delivery
|
# -v verbose: print pane tail after delivery
|
||||||
# -h help
|
# -h help
|
||||||
#
|
#
|
||||||
# PREAMBLE GRAMMAR (for consumers / daemons mirroring this producer)
|
|
||||||
# ^\[(\S+) -> (\S+?)(?: class=(terminal-log|actionable|human|reaction))?\] (.*)$
|
|
||||||
# group 1 = src label group 2 = dst host:session
|
|
||||||
# group 3 = class (absent => actionable) group 4 = message body
|
|
||||||
#
|
|
||||||
# EXIT CODES (passed through from send-message.sh)
|
# EXIT CODES (passed through from send-message.sh)
|
||||||
# 0 delivered/queued · 1 target not found · 2 still draft · 3 usage error
|
# 0 delivered/queued · 1 target not found · 2 still draft · 3 usage error
|
||||||
set -uo pipefail
|
set -uo pipefail
|
||||||
|
|
||||||
SELF_DIR=$(cd -- "$(dirname -- "$0")" && pwd)
|
SELF_DIR=$(cd -- "$(dirname -- "$0")" && pwd)
|
||||||
# Sender is overridable via env purely for testing (inject a capture stub). The
|
SENDER="$SELF_DIR/send-message.sh"
|
||||||
# default is the canonical send-message.sh beside this script; production callers
|
|
||||||
# never set AGENT_SEND_SENDER, so behavior is unchanged.
|
|
||||||
SENDER="${AGENT_SEND_SENDER:-$SELF_DIR/send-message.sh}"
|
|
||||||
|
|
||||||
# Translate the long option --class[=value] into "-C value" so getopts (which is
|
|
||||||
# short-option-only) can parse it. Every other argument passes through untouched,
|
|
||||||
# so callers that never use --class hit the exact original getopts path.
|
|
||||||
args=()
|
|
||||||
while [ $# -gt 0 ]; do
|
|
||||||
case "$1" in
|
|
||||||
--class) [ $# -ge 2 ] || { echo "ERROR: --class requires a value" >&2; exit 3; }
|
|
||||||
args+=(-C "$2"); shift 2 ;;
|
|
||||||
--class=*) args+=(-C "${1#*=}"); shift ;;
|
|
||||||
*) args+=("$1"); shift ;;
|
|
||||||
esac
|
|
||||||
done
|
|
||||||
set -- ${args[@]+"${args[@]}"}
|
|
||||||
|
|
||||||
DST_SESSION=""; SSH_TARGET=""; DST_HOST=""; MSG=""; FILE=""; SOCKET_NAME=""
|
DST_SESSION=""; SSH_TARGET=""; DST_HOST=""; MSG=""; FILE=""; SOCKET_NAME=""
|
||||||
SRC_LABEL=""; RETRIES=2; VERBOSE=0; CLASS=""
|
SRC_LABEL=""; RETRIES=2; VERBOSE=0
|
||||||
usage() { sed -n '2,/^set -uo pipefail/{/^set -uo pipefail/d;p}' "$0"; exit "${1:-3}"; }
|
usage() { sed -n '2,44p' "$0"; exit "${1:-3}"; }
|
||||||
|
|
||||||
while getopts "L:s:H:n:m:f:S:r:C:vh" o; do
|
while getopts "L:s:H:n:m:f:S:r:vh" o; do
|
||||||
case "$o" in
|
case "$o" in
|
||||||
L) SOCKET_NAME=$OPTARG ;;
|
L) SOCKET_NAME=$OPTARG ;;
|
||||||
s) DST_SESSION=$OPTARG ;; H) SSH_TARGET=$OPTARG ;; n) DST_HOST=$OPTARG ;;
|
s) DST_SESSION=$OPTARG ;; H) SSH_TARGET=$OPTARG ;; n) DST_HOST=$OPTARG ;;
|
||||||
m) MSG=$OPTARG ;; f) FILE=$OPTARG ;; S) SRC_LABEL=$OPTARG ;;
|
m) MSG=$OPTARG ;; f) FILE=$OPTARG ;; S) SRC_LABEL=$OPTARG ;;
|
||||||
C) CLASS=$OPTARG ;;
|
|
||||||
r) RETRIES=$OPTARG ;; v) VERBOSE=1 ;; h) usage 0 ;; *) usage 3 ;;
|
r) RETRIES=$OPTARG ;; v) VERBOSE=1 ;; h) usage 0 ;; *) usage 3 ;;
|
||||||
esac
|
esac
|
||||||
done
|
done
|
||||||
@@ -103,17 +64,6 @@ done
|
|||||||
[ -n "$DST_SESSION" ] || { echo "ERROR: -s DST_SESSION is required" >&2; usage 3; }
|
[ -n "$DST_SESSION" ] || { echo "ERROR: -s DST_SESSION is required" >&2; usage 3; }
|
||||||
[ -x "$SENDER" ] || { echo "ERROR: send-message.sh not found beside this script" >&2; exit 3; }
|
[ -x "$SENDER" ] || { echo "ERROR: send-message.sh not found beside this script" >&2; exit 3; }
|
||||||
|
|
||||||
# Validate the triage class only when one was given. An absent class emits NO
|
|
||||||
# token (preamble byte-identical to the classic format); the consumer defaults
|
|
||||||
# absent => actionable.
|
|
||||||
CLASS_TOKEN=""
|
|
||||||
if [ -n "$CLASS" ]; then
|
|
||||||
case "$CLASS" in
|
|
||||||
terminal-log|actionable|human|reaction) CLASS_TOKEN=" class=${CLASS}" ;;
|
|
||||||
*) echo "ERROR: invalid --class '$CLASS' (allowed: terminal-log, actionable, human, reaction)" >&2; exit 3 ;;
|
|
||||||
esac
|
|
||||||
fi
|
|
||||||
|
|
||||||
# Message body from -f / -m / stdin.
|
# Message body from -f / -m / stdin.
|
||||||
if [ -n "$FILE" ]; then [ -r "$FILE" ] || { echo "ERROR: cannot read $FILE" >&2; exit 3; }; MSG=$(cat -- "$FILE")
|
if [ -n "$FILE" ]; then [ -r "$FILE" ] || { echo "ERROR: cannot read $FILE" >&2; exit 3; }; MSG=$(cat -- "$FILE")
|
||||||
elif [ -z "$MSG" ] && [ ! -t 0 ]; then MSG=$(cat)
|
elif [ -z "$MSG" ] && [ ! -t 0 ]; then MSG=$(cat)
|
||||||
@@ -140,7 +90,7 @@ if [ -z "$DST_HOST" ]; then
|
|||||||
fi
|
fi
|
||||||
fi
|
fi
|
||||||
|
|
||||||
PREAMBLE="[${SRC_LABEL} -> ${DST_HOST}:${DST_SESSION}${CLASS_TOKEN}]"
|
PREAMBLE="[${SRC_LABEL} -> ${DST_HOST}:${DST_SESSION}]"
|
||||||
FULL="${PREAMBLE} ${MSG}"
|
FULL="${PREAMBLE} ${MSG}"
|
||||||
B64=$(printf '%s' "$FULL" | base64 -w0)
|
B64=$(printf '%s' "$FULL" | base64 -w0)
|
||||||
|
|
||||||
|
|||||||
@@ -1,97 +0,0 @@
|
|||||||
#!/usr/bin/env bash
|
|
||||||
# agent-send.test.sh — regression + grammar lock for agent-send.sh --class.
|
|
||||||
#
|
|
||||||
# Strategy: inject a capture stub via AGENT_SEND_SENDER that decodes the -b
|
|
||||||
# base64 payload and prints the FULL message (preamble + body) so we can assert
|
|
||||||
# the exact bytes on the wire. Local path only (no ssh), -n pins the dst host so
|
|
||||||
# the preamble is deterministic across machines.
|
|
||||||
#
|
|
||||||
# Guarantees locked here:
|
|
||||||
# 1. REGRESSION BAR — no --class => preamble byte-for-byte identical to classic.
|
|
||||||
# 2. --class <c> => ` class=<c>` token emitted inside the bracket.
|
|
||||||
# 3. --class=<c> (equals form) parses identically to the space form.
|
|
||||||
# 4. -C <c> short form parses identically.
|
|
||||||
# 5. invalid class => exit 3, nothing sent.
|
|
||||||
# 6. --class with no value => exit 3.
|
|
||||||
# 7. the documented consumer regex parses producer output for every class.
|
|
||||||
set -uo pipefail
|
|
||||||
|
|
||||||
HERE=$(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 ]
|
|
||||||
@@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"name": "@mosaicstack/mosaic",
|
"name": "@mosaicstack/mosaic",
|
||||||
"version": "0.0.45",
|
"version": "0.0.40",
|
||||||
"repository": {
|
"repository": {
|
||||||
"type": "git",
|
"type": "git",
|
||||||
"url": "https://git.mosaicstack.dev/mosaicstack/stack.git",
|
"url": "https://git.mosaicstack.dev/mosaicstack/stack.git",
|
||||||
@@ -29,7 +29,6 @@
|
|||||||
"dependencies": {
|
"dependencies": {
|
||||||
"@mosaicstack/brain": "workspace:*",
|
"@mosaicstack/brain": "workspace:*",
|
||||||
"@mosaicstack/config": "workspace:*",
|
"@mosaicstack/config": "workspace:*",
|
||||||
"@mosaicstack/db": "workspace:*",
|
|
||||||
"@mosaicstack/forge": "workspace:*",
|
"@mosaicstack/forge": "workspace:*",
|
||||||
"@mosaicstack/log": "workspace:*",
|
"@mosaicstack/log": "workspace:*",
|
||||||
"@mosaicstack/macp": "workspace:*",
|
"@mosaicstack/macp": "workspace:*",
|
||||||
|
|||||||
@@ -30,7 +30,6 @@ import {
|
|||||||
refreshActiveFleetUnits,
|
refreshActiveFleetUnits,
|
||||||
readRosterAgentNames,
|
readRosterAgentNames,
|
||||||
buildRelaunchCommands,
|
buildRelaunchCommands,
|
||||||
checkFrameworkDrift,
|
|
||||||
FRAMEWORK_RESEED_PACKAGE,
|
FRAMEWORK_RESEED_PACKAGE,
|
||||||
} from './runtime/update-checker.js';
|
} from './runtime/update-checker.js';
|
||||||
import { runWizard } from './wizard.js';
|
import { runWizard } from './wizard.js';
|
||||||
@@ -419,48 +418,6 @@ program
|
|||||||
// checkForAllUpdates imported statically above
|
// checkForAllUpdates imported statically above
|
||||||
const { execSync } = await import('node:child_process');
|
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(
|
|
||||||
`\nℹ ${agents.length} fleet agent(s) are still running the previous runtime. ` +
|
|
||||||
'Restart them to activate the update:\n mosaic update --relaunch ' +
|
|
||||||
'(or: mosaic fleet restart <agent>)',
|
|
||||||
);
|
|
||||||
}
|
|
||||||
};
|
|
||||||
|
|
||||||
console.log('Checking for updates…');
|
console.log('Checking for updates…');
|
||||||
const results = checkForAllUpdates({ skipCache: true });
|
const results = checkForAllUpdates({ skipCache: true });
|
||||||
|
|
||||||
@@ -475,18 +432,6 @@ program
|
|||||||
process.exit(1);
|
process.exit(1);
|
||||||
}
|
}
|
||||||
console.log('\n✔ All packages up to date.');
|
console.log('\n✔ All packages up to date.');
|
||||||
// #642: the CLI may have been upgraded outside `mosaic update` (e.g. a
|
|
||||||
// direct `npm i -g`), leaving the framework files stale even though no
|
|
||||||
// package is reported outdated. Detect that via the framework version and
|
|
||||||
// re-seed so shipped launcher/runtime fixes still activate.
|
|
||||||
const drift = checkFrameworkDrift();
|
|
||||||
if (drift.drifted && opts.reseed !== false) {
|
|
||||||
reseedFramework(
|
|
||||||
`\nFramework drift detected (on-disk v${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;
|
return;
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -511,17 +456,52 @@ program
|
|||||||
// F3-m3 / R13: the CLI is updated, but the framework files in
|
// F3-m3 / R13: the CLI is updated, but the framework files in
|
||||||
// ~/.config/mosaic/ are still the previous version. Re-seed them from the
|
// ~/.config/mosaic/ are still the previous version. Re-seed them from the
|
||||||
// freshly-installed package so shipped launcher/runtime changes ACTIVATE.
|
// freshly-installed package so shipped launcher/runtime changes ACTIVATE.
|
||||||
// Re-seed when the framework-bearing package itself updated OR the on-disk
|
// Only when the framework-bearing package itself updated.
|
||||||
// framework is older than the freshly-installed one (#642 — e.g. only
|
|
||||||
// sibling packages were outdated but the CLI was already ahead).
|
|
||||||
const mosaicUpdated = outdated.some(
|
const mosaicUpdated = outdated.some(
|
||||||
(r: { package: string }) => r.package === FRAMEWORK_RESEED_PACKAGE,
|
(r: { package: string }) => r.package === FRAMEWORK_RESEED_PACKAGE,
|
||||||
);
|
);
|
||||||
const drift = checkFrameworkDrift();
|
if (mosaicUpdated && opts.reseed !== false) {
|
||||||
if ((mosaicUpdated || drift.drifted) && opts.reseed !== false) {
|
console.log(
|
||||||
reseedFramework(
|
|
||||||
'\nRe-seeding framework files into ~/.config/mosaic (data-safe; keeps your edits)…',
|
'\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(
|
||||||
|
`\nℹ ${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)',
|
||||||
|
);
|
||||||
|
}
|
||||||
}
|
}
|
||||||
});
|
});
|
||||||
|
|
||||||
|
|||||||
@@ -1,285 +0,0 @@
|
|||||||
/**
|
|
||||||
* `mosaic fleet backlog <sub> --json` — Mosaic-native backlog of record.
|
|
||||||
*
|
|
||||||
* Mosaic OWNS this backlog end-to-end on its existing Postgres storage layer
|
|
||||||
* (`@mosaicstack/db`). It REPLACES the former Hermes adapter — there is NO
|
|
||||||
* runtime dependency on Hermes.
|
|
||||||
*
|
|
||||||
* Storage tier (the existing storage-layer convention, no new engine):
|
|
||||||
* - default: embedded PGlite at <mosaicHome>/fleet/backlog (real Postgres
|
|
||||||
* semantics, persisted on disk so the operator's backlog survives reboots
|
|
||||||
* and `mosaic update` — see install.sh PRESERVE_PATHS).
|
|
||||||
* - DATABASE_URL set: full server Postgres — same code, no change.
|
|
||||||
*
|
|
||||||
* Migrations run on first use so the `backlog` table always exists.
|
|
||||||
*/
|
|
||||||
|
|
||||||
import { mkdir } from 'node:fs/promises';
|
|
||||||
import { homedir } from 'node:os';
|
|
||||||
import { join } from 'node:path';
|
|
||||||
import type { Command } from 'commander';
|
|
||||||
import {
|
|
||||||
BacklogService,
|
|
||||||
DEFAULT_CLAIM_TTL_SECONDS,
|
|
||||||
type BacklogCard,
|
|
||||||
type DbHandle,
|
|
||||||
} from '@mosaicstack/db';
|
|
||||||
|
|
||||||
function defaultMosaicHome(): string {
|
|
||||||
return process.env['MOSAIC_HOME'] ?? join(homedir(), '.config', 'mosaic');
|
|
||||||
}
|
|
||||||
|
|
||||||
/** Resolve where the embedded PGlite backlog store lives (default tier). */
|
|
||||||
export function defaultBacklogDataDir(mosaicHome = defaultMosaicHome()): string {
|
|
||||||
return join(mosaicHome, 'fleet', 'backlog');
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Open a db handle for the backlog and ensure the schema exists.
|
|
||||||
*
|
|
||||||
* Tier detection mirrors the storage layer: DATABASE_URL => server Postgres
|
|
||||||
* (migrations applied via runMigrations); otherwise embedded PGlite at the
|
|
||||||
* fleet/backlog data dir (migrations applied via runPgliteMigrations).
|
|
||||||
*/
|
|
||||||
async function openBacklogDb(mosaicHome: string): Promise<DbHandle> {
|
|
||||||
const { createDb, createPgliteDb, runMigrations, runPgliteMigrations } =
|
|
||||||
await import('@mosaicstack/db');
|
|
||||||
const url = process.env['DATABASE_URL'];
|
|
||||||
if (url) {
|
|
||||||
await runMigrations(url);
|
|
||||||
return createDb(url);
|
|
||||||
}
|
|
||||||
const dataDir = process.env['PGLITE_DATA_DIR'] ?? defaultBacklogDataDir(mosaicHome);
|
|
||||||
// PGlite writes a file-backed store to dataDir but does not create missing
|
|
||||||
// parent directories (e.g. <mosaicHome>/fleet). Create them first. Skip for
|
|
||||||
// the in-memory pseudo-paths so a memory:// store never touches the fs.
|
|
||||||
if (!dataDir.startsWith('memory://') && dataDir !== ':memory:') {
|
|
||||||
await mkdir(dataDir, { recursive: true });
|
|
||||||
}
|
|
||||||
const handle = createPgliteDb(dataDir);
|
|
||||||
await runPgliteMigrations(handle);
|
|
||||||
return handle;
|
|
||||||
}
|
|
||||||
|
|
||||||
function parseDependsOn(value?: string): string[] {
|
|
||||||
if (!value) return [];
|
|
||||||
return value
|
|
||||||
.split(',')
|
|
||||||
.map((s) => s.trim())
|
|
||||||
.filter((s) => s.length > 0);
|
|
||||||
}
|
|
||||||
|
|
||||||
function parseAcceptance(value?: string): unknown {
|
|
||||||
if (!value) return null;
|
|
||||||
try {
|
|
||||||
return JSON.parse(value);
|
|
||||||
} catch {
|
|
||||||
// Fall back to a list of newline/semicolon-separated criteria.
|
|
||||||
return value
|
|
||||||
.split(/[\n;]/)
|
|
||||||
.map((s) => s.trim())
|
|
||||||
.filter((s) => s.length > 0);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
function printCard(card: BacklogCard | null, json?: boolean): void {
|
|
||||||
if (json) {
|
|
||||||
console.log(JSON.stringify(card));
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
if (!card) {
|
|
||||||
console.log('(none)');
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
const deps = card.dependsOn.length ? card.dependsOn.join(',') : '-';
|
|
||||||
console.log(
|
|
||||||
`${card.id}\t[${card.status}]\tp=${card.priority}\tphase=${card.phase ?? '-'}\tdeps=${deps}\t${card.title}`,
|
|
||||||
);
|
|
||||||
}
|
|
||||||
|
|
||||||
function printCards(cards: BacklogCard[], json?: boolean): void {
|
|
||||||
if (json) {
|
|
||||||
console.log(JSON.stringify(cards));
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
if (cards.length === 0) {
|
|
||||||
console.log('(no cards)');
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
for (const card of cards) printCard(card, false);
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Register `backlog` under an existing `fleet` command.
|
|
||||||
* `mosaicHomeFor` resolves the active --mosaic-home (parent flag) at call time.
|
|
||||||
*/
|
|
||||||
export function registerFleetBacklogCommand(
|
|
||||||
fleetCmd: Command,
|
|
||||||
mosaicHomeFor: () => string,
|
|
||||||
): Command {
|
|
||||||
const backlogCmd = fleetCmd
|
|
||||||
.command('backlog')
|
|
||||||
.description('Mosaic-native backlog of record (atomic claim + TTL, deps DAG)');
|
|
||||||
|
|
||||||
const withSvc = async <T>(fn: (svc: BacklogService) => Promise<T>): Promise<T> => {
|
|
||||||
const handle = await openBacklogDb(mosaicHomeFor());
|
|
||||||
try {
|
|
||||||
return await fn(new BacklogService(handle.db));
|
|
||||||
} finally {
|
|
||||||
await handle.close();
|
|
||||||
}
|
|
||||||
};
|
|
||||||
|
|
||||||
backlogCmd
|
|
||||||
.command('create')
|
|
||||||
.description('Create a backlog card (idempotency_key dedups)')
|
|
||||||
.requiredOption('--id <id>', 'Stable card id')
|
|
||||||
.requiredOption('--title <title>', 'Card title')
|
|
||||||
.option('--body <body>', 'Card body / description')
|
|
||||||
.option('--phase <phase>', 'Board/phase grouping')
|
|
||||||
.option('--priority <n>', 'Priority (higher = sooner)', (v) => parseInt(v, 10), 0)
|
|
||||||
.option('--depends-on <ids>', 'Comma-separated dependency card ids')
|
|
||||||
.option('--acceptance <json>', 'Acceptance criteria (JSON or ;/newline list)')
|
|
||||||
.option('--idempotency-key <key>', 'Dedup key; repeat returns the existing card')
|
|
||||||
.option('--json', 'Print JSON')
|
|
||||||
.action(
|
|
||||||
async (opts: {
|
|
||||||
id: string;
|
|
||||||
title: string;
|
|
||||||
body?: string;
|
|
||||||
phase?: string;
|
|
||||||
priority: number;
|
|
||||||
dependsOn?: string;
|
|
||||||
acceptance?: string;
|
|
||||||
idempotencyKey?: string;
|
|
||||||
json?: boolean;
|
|
||||||
}) => {
|
|
||||||
const card = await withSvc((svc) =>
|
|
||||||
svc.create({
|
|
||||||
id: opts.id,
|
|
||||||
title: opts.title,
|
|
||||||
body: opts.body ?? null,
|
|
||||||
phase: opts.phase ?? null,
|
|
||||||
priority: opts.priority,
|
|
||||||
dependsOn: parseDependsOn(opts.dependsOn),
|
|
||||||
acceptance: parseAcceptance(opts.acceptance),
|
|
||||||
idempotencyKey: opts.idempotencyKey ?? null,
|
|
||||||
}),
|
|
||||||
);
|
|
||||||
printCard(card, opts.json);
|
|
||||||
},
|
|
||||||
);
|
|
||||||
|
|
||||||
backlogCmd
|
|
||||||
.command('list')
|
|
||||||
.description('List cards (filters: --status, --phase, --ready-only)')
|
|
||||||
.option('--status <status>', 'Filter by status: ready|claimed|blocked|done')
|
|
||||||
.option('--phase <phase>', 'Filter by phase')
|
|
||||||
.option('--ready-only', 'Only cards that are ready AND have all deps done')
|
|
||||||
.option('--json', 'Print JSON')
|
|
||||||
.action(
|
|
||||||
async (opts: {
|
|
||||||
status?: BacklogCard['status'];
|
|
||||||
phase?: string;
|
|
||||||
readyOnly?: boolean;
|
|
||||||
json?: boolean;
|
|
||||||
}) => {
|
|
||||||
const cards = await withSvc((svc) =>
|
|
||||||
svc.list({
|
|
||||||
...(opts.status ? { status: opts.status } : {}),
|
|
||||||
...(opts.phase ? { phase: opts.phase } : {}),
|
|
||||||
...(opts.readyOnly ? { readyOnly: true } : {}),
|
|
||||||
}),
|
|
||||||
);
|
|
||||||
printCards(cards, opts.json);
|
|
||||||
},
|
|
||||||
);
|
|
||||||
|
|
||||||
backlogCmd
|
|
||||||
.command('claim')
|
|
||||||
.description('Atomically claim the highest-priority ready card (FOR UPDATE SKIP LOCKED)')
|
|
||||||
.requiredOption('--owner <owner>', 'Claim owner (worker/agent id)')
|
|
||||||
.option(
|
|
||||||
'--ttl <sec>',
|
|
||||||
'Claim TTL in seconds',
|
|
||||||
(v) => parseInt(v, 10),
|
|
||||||
DEFAULT_CLAIM_TTL_SECONDS,
|
|
||||||
)
|
|
||||||
.option('--id <id>', 'Claim a specific card by id')
|
|
||||||
.option('--json', 'Print JSON')
|
|
||||||
.action(async (opts: { owner: string; ttl: number; id?: string; json?: boolean }) => {
|
|
||||||
const card = await withSvc((svc) =>
|
|
||||||
svc.claim({ owner: opts.owner, ttlSeconds: opts.ttl, ...(opts.id ? { id: opts.id } : {}) }),
|
|
||||||
);
|
|
||||||
printCard(card, opts.json);
|
|
||||||
if (!card && !opts.json) process.exitCode = 0;
|
|
||||||
});
|
|
||||||
|
|
||||||
backlogCmd
|
|
||||||
.command('reclaim')
|
|
||||||
.description('Release expired claims back to ready (or a specific --id)')
|
|
||||||
.option('--id <id>', 'Release a specific card regardless of expiry')
|
|
||||||
.option('--json', 'Print JSON')
|
|
||||||
.action(async (opts: { id?: string; json?: boolean }) => {
|
|
||||||
const result = await withSvc((svc) => svc.reclaim(opts.id ? { id: opts.id } : {}));
|
|
||||||
if (opts.json) {
|
|
||||||
console.log(JSON.stringify(result));
|
|
||||||
} else if (result.reclaimed.length === 0) {
|
|
||||||
console.log('(nothing to reclaim)');
|
|
||||||
} else {
|
|
||||||
console.log(`reclaimed: ${result.reclaimed.join(', ')}`);
|
|
||||||
}
|
|
||||||
});
|
|
||||||
|
|
||||||
backlogCmd
|
|
||||||
.command('link')
|
|
||||||
.description('Add a depends_on edge (--from depends on --to)')
|
|
||||||
.requiredOption('--from <id>', 'Card that gains the dependency')
|
|
||||||
.requiredOption('--to <id>', 'Card it now depends on')
|
|
||||||
.option('--json', 'Print JSON')
|
|
||||||
.action(async (opts: { from: string; to: string; json?: boolean }) => {
|
|
||||||
const card = await withSvc((svc) => svc.link(opts.from, opts.to));
|
|
||||||
printCard(card, opts.json);
|
|
||||||
});
|
|
||||||
|
|
||||||
backlogCmd
|
|
||||||
.command('stats')
|
|
||||||
.description('Counts by status, oldest-ready age, expired-claim count')
|
|
||||||
.option('--json', 'Print JSON')
|
|
||||||
.action(async (opts: { json?: boolean }) => {
|
|
||||||
const stats = await withSvc((svc) => svc.stats());
|
|
||||||
if (opts.json) {
|
|
||||||
console.log(JSON.stringify(stats));
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
console.log(`total: ${stats.total}`);
|
|
||||||
console.log(
|
|
||||||
`ready=${stats.counts.ready} claimed=${stats.counts.claimed} ` +
|
|
||||||
`blocked=${stats.counts.blocked} done=${stats.counts.done}`,
|
|
||||||
);
|
|
||||||
console.log(`oldest-ready-age: ${stats.oldestReadyAgeSeconds ?? '-'}s`);
|
|
||||||
console.log(`expired-claims: ${stats.expiredClaimCount}`);
|
|
||||||
});
|
|
||||||
|
|
||||||
backlogCmd
|
|
||||||
.command('block')
|
|
||||||
.description('Mark a card blocked')
|
|
||||||
.requiredOption('--id <id>', 'Card id')
|
|
||||||
.option('--json', 'Print JSON')
|
|
||||||
.action(async (opts: { id: string; json?: boolean }) => {
|
|
||||||
const card = await withSvc((svc) => svc.block(opts.id));
|
|
||||||
printCard(card, opts.json);
|
|
||||||
});
|
|
||||||
|
|
||||||
backlogCmd
|
|
||||||
.command('complete')
|
|
||||||
.description('Mark a card done')
|
|
||||||
.requiredOption('--id <id>', 'Card id')
|
|
||||||
.option('--json', 'Print JSON')
|
|
||||||
.action(async (opts: { id: string; json?: boolean }) => {
|
|
||||||
const card = await withSvc((svc) => svc.complete(opts.id));
|
|
||||||
printCard(card, opts.json);
|
|
||||||
});
|
|
||||||
|
|
||||||
return backlogCmd;
|
|
||||||
}
|
|
||||||
@@ -1,200 +0,0 @@
|
|||||||
import { readFile } from 'node:fs/promises';
|
|
||||||
import { dirname, join, resolve } from 'node:path';
|
|
||||||
import { fileURLToPath } from 'node:url';
|
|
||||||
import { describe, expect, it, vi } from 'vitest';
|
|
||||||
import {
|
|
||||||
parseNorthStar,
|
|
||||||
renderNorthStarMarkdown,
|
|
||||||
resolveNorthStarPaths,
|
|
||||||
type NorthStar,
|
|
||||||
} from './fleet.js';
|
|
||||||
|
|
||||||
// Repo root resolved from this spec file: packages/mosaic/src/commands → up 4.
|
|
||||||
const repoRoot = resolve(dirname(fileURLToPath(import.meta.url)), '..', '..', '..', '..');
|
|
||||||
const yamlPath = join(repoRoot, 'docs', 'fleet', 'NORTH_STAR.yaml');
|
|
||||||
|
|
||||||
async function loadYamlText(): Promise<string> {
|
|
||||||
return readFile(yamlPath, 'utf8');
|
|
||||||
}
|
|
||||||
|
|
||||||
async function loadParsed(): Promise<NorthStar> {
|
|
||||||
return parseNorthStar(await loadYamlText());
|
|
||||||
}
|
|
||||||
|
|
||||||
describe('NORTH_STAR.yaml', () => {
|
|
||||||
it('parses to a typed object with the required top-level keys', async () => {
|
|
||||||
const ns = await loadParsed();
|
|
||||||
expect(ns.version).toBeTypeOf('number');
|
|
||||||
expect(ns.mission).toContain('self-driving Mosaic system');
|
|
||||||
expect(ns.mission).toContain('Mosaic is general-purpose');
|
|
||||||
expect(ns.substrate.note).toBeTruthy();
|
|
||||||
expect(ns.standing_objectives.length).toBeGreaterThan(0);
|
|
||||||
expect(ns.success_criteria.length).toBeGreaterThan(0);
|
|
||||||
expect(ns.workstreams.length).toBeGreaterThan(0);
|
|
||||||
expect(ns.goals.length).toBeGreaterThan(0);
|
|
||||||
expect(ns.assumptions.length).toBeGreaterThan(0);
|
|
||||||
expect(ns.spend.advisory).toBe(true);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('names the native Postgres storage layer and declares no Hermes runtime dependency', async () => {
|
|
||||||
const rawText = await loadYamlText();
|
|
||||||
const lower = rawText.toLowerCase();
|
|
||||||
expect(rawText).toContain('@mosaicstack/db');
|
|
||||||
expect(lower).toContain('postgres');
|
|
||||||
expect(lower).toContain('pglite');
|
|
||||||
// The doctrine explicitly disowns Hermes ("NOT Hermes"); the only mentions
|
|
||||||
// are negations. Assert there is no Hermes RUNTIME dependency: no hermes
|
|
||||||
// CLI/kanban invocation and no ~/.hermes storage reference.
|
|
||||||
expect(lower).not.toContain('hermes kanban');
|
|
||||||
expect(lower).not.toContain('~/.hermes');
|
|
||||||
expect(lower).not.toContain('hermes mcp');
|
|
||||||
});
|
|
||||||
|
|
||||||
it('declares all NS-1..NS-8 standing objectives', async () => {
|
|
||||||
const ns = await loadParsed();
|
|
||||||
const ids = ns.standing_objectives.map((o) => o.id);
|
|
||||||
for (let n = 1; n <= 8; n += 1) {
|
|
||||||
expect(ids).toContain(`NS-${n}`);
|
|
||||||
}
|
|
||||||
});
|
|
||||||
|
|
||||||
it('declares all AC-NS-1..AC-NS-5 success criteria', async () => {
|
|
||||||
const ns = await loadParsed();
|
|
||||||
const ids = ns.success_criteria.map((c) => c.id);
|
|
||||||
for (let n = 1; n <= 5; n += 1) {
|
|
||||||
expect(ids).toContain(`AC-NS-${n}`);
|
|
||||||
}
|
|
||||||
});
|
|
||||||
|
|
||||||
it('seeds the expected backlog goal ids', async () => {
|
|
||||||
const ns = await loadParsed();
|
|
||||||
const ids = ns.goals.map((g) => g.id);
|
|
||||||
expect(ids).toEqual(
|
|
||||||
expect.arrayContaining(['A1', 'A2', 'A3a', 'A3b', 'A4', 'B1', 'B2', 'B3a', 'B3b', 'G1']),
|
|
||||||
);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('has a coherent depends_on DAG (every dependency references a known goal)', async () => {
|
|
||||||
const ns = await loadParsed();
|
|
||||||
const ids = new Set(ns.goals.map((g) => g.id));
|
|
||||||
for (const goal of ns.goals) {
|
|
||||||
for (const dep of goal.depends_on) {
|
|
||||||
expect(ids.has(dep)).toBe(true);
|
|
||||||
}
|
|
||||||
// No goal may depend on itself.
|
|
||||||
expect(goal.depends_on).not.toContain(goal.id);
|
|
||||||
}
|
|
||||||
// A1 is the root: no dependencies.
|
|
||||||
const a1 = ns.goals.find((g) => g.id === 'A1');
|
|
||||||
expect(a1?.depends_on).toEqual([]);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('marks spend as advisory with a degrade-to-TTL note', async () => {
|
|
||||||
const ns = await loadParsed();
|
|
||||||
expect(ns.spend.advisory).toBe(true);
|
|
||||||
expect(ns.spend.note.toLowerCase()).toContain('ttl');
|
|
||||||
});
|
|
||||||
});
|
|
||||||
|
|
||||||
describe('renderNorthStarMarkdown', () => {
|
|
||||||
it('is a pure deterministic projection (round-trip stable)', async () => {
|
|
||||||
const ns = await loadParsed();
|
|
||||||
const first = renderNorthStarMarkdown(ns);
|
|
||||||
const second = renderNorthStarMarkdown(ns);
|
|
||||||
expect(first).toBe(second);
|
|
||||||
// Re-parsing the same YAML and re-rendering yields identical bytes.
|
|
||||||
const reparsed = parseNorthStar(await loadYamlText());
|
|
||||||
expect(renderNorthStarMarkdown(reparsed)).toBe(first);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('matches the committed NORTH_STAR.md projection (regenerate if this fails)', async () => {
|
|
||||||
const ns = await loadParsed();
|
|
||||||
const rendered = `${renderNorthStarMarkdown(ns)}\n`;
|
|
||||||
const committed = await readFile(join(repoRoot, 'docs', 'fleet', 'NORTH_STAR.md'), 'utf8');
|
|
||||||
expect(rendered).toBe(committed);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('projects mission, objectives, criteria, goals, assumptions, and spend', async () => {
|
|
||||||
const ns = await loadParsed();
|
|
||||||
const md = renderNorthStarMarkdown(ns);
|
|
||||||
expect(md).toContain('# Mosaic Fleet — NORTH STAR');
|
|
||||||
expect(md).toContain('## Mission');
|
|
||||||
expect(md).toContain('## Standing objectives');
|
|
||||||
expect(md).toContain('**NS-1**');
|
|
||||||
expect(md).toContain('**AC-NS-5**');
|
|
||||||
expect(md).toContain('## Goals (backlog projection)');
|
|
||||||
// Tables are column-padded (prettier-style); match the row id, not exact spacing.
|
|
||||||
expect(md).toMatch(/\| A1\s+\|/);
|
|
||||||
expect(md).toContain('## Assumptions (vetoable)');
|
|
||||||
expect(md).toContain('**advisory:** true');
|
|
||||||
// The banner disowns Hermes; the projection carries no Hermes runtime hook.
|
|
||||||
expect(md.toLowerCase()).not.toContain('hermes kanban');
|
|
||||||
expect(md.toLowerCase()).not.toContain('~/.hermes');
|
|
||||||
});
|
|
||||||
|
|
||||||
it('does no network or CLI work (pure functions; only the writer touches IO)', () => {
|
|
||||||
// parseNorthStar + renderNorthStarMarkdown take strings and return strings.
|
|
||||||
// Guard against accidental IO by asserting fetch/spawn are never invoked.
|
|
||||||
const fetchSpy = vi.spyOn(globalThis, 'fetch' as never).mockImplementation((() => {
|
|
||||||
throw new Error('network access is forbidden in the NORTH_STAR generator');
|
|
||||||
}) as never);
|
|
||||||
try {
|
|
||||||
const yaml = [
|
|
||||||
'version: 1',
|
|
||||||
'mission: m',
|
|
||||||
'substrate:',
|
|
||||||
' note: n',
|
|
||||||
'standing_objectives:',
|
|
||||||
' - { id: NS-1, text: t }',
|
|
||||||
'success_criteria:',
|
|
||||||
' - { id: AC-NS-1, text: t }',
|
|
||||||
'workstreams:',
|
|
||||||
' - { id: A, title: t }',
|
|
||||||
'goals:',
|
|
||||||
' - { id: A1, title: t, phase: 1, priority: must-have, depends_on: [] }',
|
|
||||||
'assumptions:',
|
|
||||||
' - { id: ASM-1, vetoable: true, text: t }',
|
|
||||||
'spend:',
|
|
||||||
' advisory: true',
|
|
||||||
' note: TTL',
|
|
||||||
'',
|
|
||||||
].join('\n');
|
|
||||||
const ns = parseNorthStar(yaml);
|
|
||||||
const md = renderNorthStarMarkdown(ns);
|
|
||||||
expect(md).toContain('# Mosaic Fleet — NORTH STAR');
|
|
||||||
expect(fetchSpy).not.toHaveBeenCalled();
|
|
||||||
} finally {
|
|
||||||
fetchSpy.mockRestore();
|
|
||||||
}
|
|
||||||
});
|
|
||||||
});
|
|
||||||
|
|
||||||
describe('parseNorthStar validation', () => {
|
|
||||||
it('throws on a missing required key', () => {
|
|
||||||
expect(() => parseNorthStar('version: 1\n')).toThrow();
|
|
||||||
});
|
|
||||||
|
|
||||||
it('throws when spend.advisory is not a boolean', () => {
|
|
||||||
const yaml = [
|
|
||||||
'version: 1',
|
|
||||||
'mission: m',
|
|
||||||
'substrate: { note: n }',
|
|
||||||
'standing_objectives: [{ id: NS-1, text: t }]',
|
|
||||||
'success_criteria: [{ id: AC-NS-1, text: t }]',
|
|
||||||
'workstreams: [{ id: A, title: t }]',
|
|
||||||
'goals: [{ id: A1, title: t, phase: 1, priority: must-have, depends_on: [] }]',
|
|
||||||
'assumptions: [{ id: ASM-1, vetoable: true, text: t }]',
|
|
||||||
'spend: { advisory: maybe, note: TTL }',
|
|
||||||
'',
|
|
||||||
].join('\n');
|
|
||||||
expect(() => parseNorthStar(yaml)).toThrow(/spend\.advisory/);
|
|
||||||
});
|
|
||||||
});
|
|
||||||
|
|
||||||
describe('resolveNorthStarPaths', () => {
|
|
||||||
it('resolves YAML + Markdown under docs/fleet from a given repo root', () => {
|
|
||||||
const paths = resolveNorthStarPaths('/repo');
|
|
||||||
expect(paths.yamlPath).toBe('/repo/docs/fleet/NORTH_STAR.yaml');
|
|
||||||
expect(paths.markdownPath).toBe('/repo/docs/fleet/NORTH_STAR.md');
|
|
||||||
});
|
|
||||||
});
|
|
||||||
@@ -19,20 +19,17 @@ import {
|
|||||||
buildSystemdShowCommand,
|
buildSystemdShowCommand,
|
||||||
buildTmuxListPanesCommand,
|
buildTmuxListPanesCommand,
|
||||||
buildTmuxListSessionsCommand,
|
buildTmuxListSessionsCommand,
|
||||||
classifyReadiness,
|
|
||||||
classifySendResult,
|
classifySendResult,
|
||||||
countOrchestrators,
|
countOrchestrators,
|
||||||
countEnhancers,
|
countEnhancers,
|
||||||
detectDrift,
|
detectDrift,
|
||||||
enableFleetUnits,
|
enableFleetUnits,
|
||||||
FLEET_PROFILES,
|
FLEET_PROFILES,
|
||||||
HEARTBEAT_IDLE_THRESHOLD_SECONDS,
|
|
||||||
generateAgentEnv,
|
generateAgentEnv,
|
||||||
getDefaultOperatorSourceLabel,
|
getDefaultOperatorSourceLabel,
|
||||||
getDefaultTenantAndHost,
|
getDefaultTenantAndHost,
|
||||||
getRosterAgent,
|
getRosterAgent,
|
||||||
heartbeatPath,
|
heartbeatPath,
|
||||||
idleThresholdSeconds,
|
|
||||||
isSendAccepted,
|
isSendAccepted,
|
||||||
loadFleetRoster,
|
loadFleetRoster,
|
||||||
mergeAgentEnv,
|
mergeAgentEnv,
|
||||||
@@ -78,7 +75,6 @@ describe('registerFleetCommand', () => {
|
|||||||
expect(fleet).toBeDefined();
|
expect(fleet).toBeDefined();
|
||||||
expect(fleet!.commands.map((command) => command.name()).sort()).toEqual([
|
expect(fleet!.commands.map((command) => command.name()).sort()).toEqual([
|
||||||
'add',
|
'add',
|
||||||
'backlog',
|
|
||||||
'init',
|
'init',
|
||||||
'install',
|
'install',
|
||||||
'install-systemd',
|
'install-systemd',
|
||||||
@@ -92,24 +88,6 @@ describe('registerFleetCommand', () => {
|
|||||||
]);
|
]);
|
||||||
});
|
});
|
||||||
|
|
||||||
it('registers the backlog subcommand with its operations', () => {
|
|
||||||
const program = buildProgram();
|
|
||||||
const fleet = program.commands.find((command) => command.name() === 'fleet');
|
|
||||||
const backlog = fleet!.commands.find((command) => command.name() === 'backlog');
|
|
||||||
|
|
||||||
expect(backlog).toBeDefined();
|
|
||||||
expect(backlog!.commands.map((command) => command.name()).sort()).toEqual([
|
|
||||||
'block',
|
|
||||||
'claim',
|
|
||||||
'complete',
|
|
||||||
'create',
|
|
||||||
'link',
|
|
||||||
'list',
|
|
||||||
'reclaim',
|
|
||||||
'stats',
|
|
||||||
]);
|
|
||||||
});
|
|
||||||
|
|
||||||
it('adds fleet-backed agent subcommands without removing existing options', () => {
|
it('adds fleet-backed agent subcommands without removing existing options', () => {
|
||||||
const program = buildProgram();
|
const program = buildProgram();
|
||||||
const agent = program.commands.find((command) => command.name() === 'agent');
|
const agent = program.commands.find((command) => command.name() === 'agent');
|
||||||
@@ -117,7 +95,6 @@ describe('registerFleetCommand', () => {
|
|||||||
expect(agent).toBeDefined();
|
expect(agent).toBeDefined();
|
||||||
expect(agent!.options.map((option) => option.long)).toContain('--list');
|
expect(agent!.options.map((option) => option.long)).toContain('--list');
|
||||||
expect(agent!.commands.map((command) => command.name()).sort()).toEqual([
|
expect(agent!.commands.map((command) => command.name()).sort()).toEqual([
|
||||||
'comms-block',
|
|
||||||
'reset',
|
'reset',
|
||||||
'roster',
|
'roster',
|
||||||
'send',
|
'send',
|
||||||
@@ -872,7 +849,7 @@ describe('fleet ps — command construction', () => {
|
|||||||
'-t',
|
'-t',
|
||||||
'=canary-pi:0.0',
|
'=canary-pi:0.0',
|
||||||
'-F',
|
'-F',
|
||||||
'#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity} #{window_activity} #{session_activity}',
|
'#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity}',
|
||||||
]);
|
]);
|
||||||
});
|
});
|
||||||
|
|
||||||
@@ -955,125 +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', () => {
|
describe('fleet ps — systemd show parsing', () => {
|
||||||
it('parses ActiveState, SubState, UnitFileState from systemctl show output', () => {
|
it('parses ActiveState, SubState, UnitFileState from systemctl show output', () => {
|
||||||
const output = 'ActiveState=active\nSubState=running\nUnitFileState=enabled\n';
|
const output = 'ActiveState=active\nSubState=running\nUnitFileState=enabled\n';
|
||||||
@@ -1094,11 +952,9 @@ describe('fleet ps — systemd show parsing', () => {
|
|||||||
describe('fleet ps — tmux list-panes parsing', () => {
|
describe('fleet ps — tmux list-panes parsing', () => {
|
||||||
const NOW_MS = 1_700_000_000_000;
|
const NOW_MS = 1_700_000_000_000;
|
||||||
|
|
||||||
it('uses pane_activity when present', () => {
|
it('parses alive pane with pid, command, and idle time', () => {
|
||||||
const paneActivityEpoch = Math.floor((NOW_MS - 30_000) / 1000); // 30s ago
|
const activityEpoch = Math.floor((NOW_MS - 30_000) / 1000); // 30s ago
|
||||||
const windowActivityEpoch = Math.floor((NOW_MS - 60_000) / 1000); // 60s ago
|
const output = `12345 claude 0 ${activityEpoch}\n`;
|
||||||
const sessionActivityEpoch = Math.floor((NOW_MS - 90_000) / 1000); // 90s ago
|
|
||||||
const output = `12345 claude 0 ${paneActivityEpoch} ${windowActivityEpoch} ${sessionActivityEpoch}\n`;
|
|
||||||
const result = parseTmuxListPanes(output, NOW_MS);
|
const result = parseTmuxListPanes(output, NOW_MS);
|
||||||
expect(result.pid).toBe(12345);
|
expect(result.pid).toBe(12345);
|
||||||
expect(result.command).toBe('claude');
|
expect(result.command).toBe('claude');
|
||||||
@@ -1106,45 +962,8 @@ describe('fleet ps — tmux list-panes parsing', () => {
|
|||||||
expect(result.idleSeconds).toBe(30);
|
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', () => {
|
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);
|
const result = parseTmuxListPanes(output, NOW_MS);
|
||||||
expect(result.dead).toBe(true);
|
expect(result.dead).toBe(true);
|
||||||
});
|
});
|
||||||
@@ -1504,9 +1323,8 @@ describe('fleet ps — JSON output shape (FR-6)', () => {
|
|||||||
// boot-enable warning: active + disabled
|
// boot-enable warning: active + disabled
|
||||||
expect(row.bootEnableWarning).toBe(true);
|
expect(row.bootEnableWarning).toBe(true);
|
||||||
|
|
||||||
// heartbeat missing → unknown readiness preserves existing display semantics
|
// heartbeat missing → unknown
|
||||||
expect(row.heartbeat.health).toBe('unknown');
|
expect(row.heartbeat.health).toBe('unknown');
|
||||||
expect(row.readiness).toBe('unknown');
|
|
||||||
|
|
||||||
expect(row.name).toBe('canary-pi');
|
expect(row.name).toBe('canary-pi');
|
||||||
expect(row.runtime).toBe('pi');
|
expect(row.runtime).toBe('pi');
|
||||||
@@ -1568,88 +1386,6 @@ 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', () => {
|
describe('buildTmuxListSessionsCommand', () => {
|
||||||
it('builds exact list-sessions command with session_name format', () => {
|
it('builds exact list-sessions command with session_name format', () => {
|
||||||
expect(buildTmuxListSessionsCommand('mosaic-fleet')).toEqual([
|
expect(buildTmuxListSessionsCommand('mosaic-fleet')).toEqual([
|
||||||
@@ -1777,7 +1513,6 @@ describe('fleet ps — unmanaged socket sessions', () => {
|
|||||||
|
|
||||||
// driftFlag must be false for unmanaged (no roster runtime to compare)
|
// driftFlag must be false for unmanaged (no roster runtime to compare)
|
||||||
expect(unmanagedRow.driftFlag).toBe(false);
|
expect(unmanagedRow.driftFlag).toBe(false);
|
||||||
expect(unmanagedRow.readiness).toBe('unknown');
|
|
||||||
});
|
});
|
||||||
|
|
||||||
it('shows UNMANAGED flag in table output for unmanaged sessions', async () => {
|
it('shows UNMANAGED flag in table output for unmanaged sessions', async () => {
|
||||||
|
|||||||
@@ -7,8 +7,6 @@ import { spawn } from 'node:child_process';
|
|||||||
import * as readline from 'node:readline';
|
import * as readline from 'node:readline';
|
||||||
import type { Command } from 'commander';
|
import type { Command } from 'commander';
|
||||||
import YAML from 'yaml';
|
import YAML from 'yaml';
|
||||||
import { resolveCommsBlock } from '../fleet/comms-onboarding.js';
|
|
||||||
import { registerFleetBacklogCommand } from './fleet-backlog.js';
|
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* A function that spawns a command with inherited stdio (TTY passthrough).
|
* A function that spawns a command with inherited stdio (TTY passthrough).
|
||||||
@@ -198,292 +196,6 @@ export function getRosterAgent(roster: FleetRoster, name: string): FleetAgent {
|
|||||||
return agent;
|
return agent;
|
||||||
}
|
}
|
||||||
|
|
||||||
// ---------------------------------------------------------------------------
|
|
||||||
// NORTH_STAR — machine-readable fleet planning source + Markdown projection
|
|
||||||
//
|
|
||||||
// docs/fleet/NORTH_STAR.yaml is the single source of truth. The Markdown file
|
|
||||||
// (docs/fleet/NORTH_STAR.md) is a deterministic, pure projection of the YAML —
|
|
||||||
// no network, no CLI, no clock. Edit the YAML, regenerate the .md.
|
|
||||||
// ---------------------------------------------------------------------------
|
|
||||||
|
|
||||||
export interface NorthStarIdText {
|
|
||||||
id: string;
|
|
||||||
text: string;
|
|
||||||
}
|
|
||||||
|
|
||||||
export interface NorthStarWorkstream {
|
|
||||||
id: string;
|
|
||||||
title: string;
|
|
||||||
}
|
|
||||||
|
|
||||||
export interface NorthStarGoal {
|
|
||||||
id: string;
|
|
||||||
title: string;
|
|
||||||
phase: number;
|
|
||||||
priority: string;
|
|
||||||
depends_on: string[];
|
|
||||||
}
|
|
||||||
|
|
||||||
export interface NorthStarAssumption {
|
|
||||||
id: string;
|
|
||||||
vetoable: boolean;
|
|
||||||
text: string;
|
|
||||||
}
|
|
||||||
|
|
||||||
export interface NorthStarSpend {
|
|
||||||
advisory: boolean;
|
|
||||||
note: string;
|
|
||||||
}
|
|
||||||
|
|
||||||
export interface NorthStar {
|
|
||||||
version: number;
|
|
||||||
mission: string;
|
|
||||||
substrate: { note: string };
|
|
||||||
standing_objectives: NorthStarIdText[];
|
|
||||||
success_criteria: NorthStarIdText[];
|
|
||||||
workstreams: NorthStarWorkstream[];
|
|
||||||
goals: NorthStarGoal[];
|
|
||||||
assumptions: NorthStarAssumption[];
|
|
||||||
spend: NorthStarSpend;
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Parse + validate the NORTH_STAR YAML text into a typed NorthStar object.
|
|
||||||
* Pure: no IO, no network. Throws a descriptive error when a required key is
|
|
||||||
* missing or malformed so the generator/tests fail loudly rather than emit a
|
|
||||||
* partial projection.
|
|
||||||
*/
|
|
||||||
export function parseNorthStar(rawText: string): NorthStar {
|
|
||||||
const parsed = YAML.parse(rawText) as Record<string, unknown> | null;
|
|
||||||
if (!parsed || typeof parsed !== 'object') {
|
|
||||||
throw new Error('NORTH_STAR.yaml did not parse to a mapping.');
|
|
||||||
}
|
|
||||||
|
|
||||||
const requireString = (value: unknown, key: string): string => {
|
|
||||||
if (typeof value !== 'string' || value.trim() === '') {
|
|
||||||
throw new Error(`NORTH_STAR.yaml: "${key}" must be a non-empty string.`);
|
|
||||||
}
|
|
||||||
return value.trim();
|
|
||||||
};
|
|
||||||
|
|
||||||
const requireArray = (value: unknown, key: string): unknown[] => {
|
|
||||||
if (!Array.isArray(value) || value.length === 0) {
|
|
||||||
throw new Error(`NORTH_STAR.yaml: "${key}" must be a non-empty array.`);
|
|
||||||
}
|
|
||||||
return value;
|
|
||||||
};
|
|
||||||
|
|
||||||
const idText = (value: unknown, key: string, index: number): NorthStarIdText => {
|
|
||||||
const row = value as Record<string, unknown>;
|
|
||||||
return {
|
|
||||||
id: requireString(row?.id, `${key}[${index}].id`),
|
|
||||||
text: requireString(row?.text, `${key}[${index}].text`),
|
|
||||||
};
|
|
||||||
};
|
|
||||||
|
|
||||||
const version = parsed.version;
|
|
||||||
if (typeof version !== 'number') {
|
|
||||||
throw new Error('NORTH_STAR.yaml: "version" must be a number.');
|
|
||||||
}
|
|
||||||
|
|
||||||
const substrate = parsed.substrate as Record<string, unknown> | undefined;
|
|
||||||
|
|
||||||
const spendRaw = parsed.spend as Record<string, unknown> | undefined;
|
|
||||||
if (!spendRaw || typeof spendRaw.advisory !== 'boolean') {
|
|
||||||
throw new Error('NORTH_STAR.yaml: "spend.advisory" must be a boolean.');
|
|
||||||
}
|
|
||||||
|
|
||||||
return {
|
|
||||||
version,
|
|
||||||
mission: requireString(parsed.mission, 'mission'),
|
|
||||||
substrate: { note: requireString(substrate?.note, 'substrate.note') },
|
|
||||||
standing_objectives: requireArray(parsed.standing_objectives, 'standing_objectives').map(
|
|
||||||
(row, i) => idText(row, 'standing_objectives', i),
|
|
||||||
),
|
|
||||||
success_criteria: requireArray(parsed.success_criteria, 'success_criteria').map((row, i) =>
|
|
||||||
idText(row, 'success_criteria', i),
|
|
||||||
),
|
|
||||||
workstreams: requireArray(parsed.workstreams, 'workstreams').map((row, i) => {
|
|
||||||
const ws = row as Record<string, unknown>;
|
|
||||||
return {
|
|
||||||
id: requireString(ws?.id, `workstreams[${i}].id`),
|
|
||||||
title: requireString(ws?.title, `workstreams[${i}].title`),
|
|
||||||
};
|
|
||||||
}),
|
|
||||||
goals: requireArray(parsed.goals, 'goals').map((row, i) => {
|
|
||||||
const goal = row as Record<string, unknown>;
|
|
||||||
const dependsRaw = goal?.depends_on ?? [];
|
|
||||||
if (!Array.isArray(dependsRaw)) {
|
|
||||||
throw new Error(`NORTH_STAR.yaml: goals[${i}].depends_on must be an array.`);
|
|
||||||
}
|
|
||||||
const phase = goal?.phase;
|
|
||||||
if (typeof phase !== 'number') {
|
|
||||||
throw new Error(`NORTH_STAR.yaml: goals[${i}].phase must be a number.`);
|
|
||||||
}
|
|
||||||
return {
|
|
||||||
id: requireString(goal?.id, `goals[${i}].id`),
|
|
||||||
title: requireString(goal?.title, `goals[${i}].title`),
|
|
||||||
phase,
|
|
||||||
priority: requireString(goal?.priority, `goals[${i}].priority`),
|
|
||||||
depends_on: dependsRaw.map((dep, j) => requireString(dep, `goals[${i}].depends_on[${j}]`)),
|
|
||||||
};
|
|
||||||
}),
|
|
||||||
assumptions: requireArray(parsed.assumptions, 'assumptions').map((row, i) => {
|
|
||||||
const asm = row as Record<string, unknown>;
|
|
||||||
if (typeof asm?.vetoable !== 'boolean') {
|
|
||||||
throw new Error(`NORTH_STAR.yaml: assumptions[${i}].vetoable must be a boolean.`);
|
|
||||||
}
|
|
||||||
return {
|
|
||||||
id: requireString(asm?.id, `assumptions[${i}].id`),
|
|
||||||
vetoable: asm.vetoable,
|
|
||||||
text: requireString(asm?.text, `assumptions[${i}].text`),
|
|
||||||
};
|
|
||||||
}),
|
|
||||||
spend: {
|
|
||||||
advisory: spendRaw.advisory,
|
|
||||||
note: requireString(spendRaw?.note, 'spend.note'),
|
|
||||||
},
|
|
||||||
};
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Render a GitHub-Flavored-Markdown table with prettier-compatible column
|
|
||||||
* alignment: each column is padded to the widest cell (minimum 3 for the
|
|
||||||
* `---` divider) so the generated bytes survive `prettier --check` unchanged.
|
|
||||||
* Pure; the row strings use the same single-code-unit dash/arrow glyphs that
|
|
||||||
* prettier's string-width counts as width 1.
|
|
||||||
*/
|
|
||||||
function renderMarkdownTable(headers: string[], rows: string[][]): string[] {
|
|
||||||
const widths = headers.map((header, col) =>
|
|
||||||
Math.max(3, header.length, ...rows.map((row) => row[col]?.length ?? 0)),
|
|
||||||
);
|
|
||||||
const pad = (cell: string, col: number): string => cell.padEnd(widths[col] ?? 0, ' ');
|
|
||||||
const formatRow = (cells: string[]): string =>
|
|
||||||
`| ${cells.map((cell, col) => pad(cell, col)).join(' | ')} |`;
|
|
||||||
const divider = `| ${widths.map((w) => '-'.repeat(w)).join(' | ')} |`;
|
|
||||||
return [formatRow(headers), divider, ...rows.map(formatRow)];
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Deterministically project a parsed NorthStar into the Markdown doctrine doc.
|
|
||||||
* Pure function of its input — same input always yields byte-identical output,
|
|
||||||
* so the round-trip (YAML → render → write) is stable across runs. No clock, no
|
|
||||||
* network, no CLI. Layout follows the repo's existing doctrine-doc convention
|
|
||||||
* (heading, blockquote banner, then sections + tables, e.g. north-star.md /
|
|
||||||
* mission-control/BOARD.md).
|
|
||||||
*/
|
|
||||||
export function renderNorthStarMarkdown(ns: NorthStar): string {
|
|
||||||
const lines: string[] = [];
|
|
||||||
|
|
||||||
lines.push('# Mosaic Fleet — NORTH STAR');
|
|
||||||
lines.push('');
|
|
||||||
lines.push('> **Generated file — do not edit by hand.**');
|
|
||||||
lines.push(
|
|
||||||
'> Projected deterministically from [`NORTH_STAR.yaml`](./NORTH_STAR.yaml) by the pure',
|
|
||||||
);
|
|
||||||
lines.push('> generator in `packages/mosaic/src/commands/fleet.ts` (`renderNorthStarMarkdown`).');
|
|
||||||
lines.push('> Edit the YAML, then regenerate. Self-contained Mosaic — no Hermes dependency.');
|
|
||||||
lines.push('');
|
|
||||||
|
|
||||||
lines.push('## Mission');
|
|
||||||
lines.push('');
|
|
||||||
lines.push(ns.mission);
|
|
||||||
lines.push('');
|
|
||||||
|
|
||||||
lines.push('## Substrate');
|
|
||||||
lines.push('');
|
|
||||||
lines.push(ns.substrate.note);
|
|
||||||
lines.push('');
|
|
||||||
|
|
||||||
lines.push('## Standing objectives');
|
|
||||||
lines.push('');
|
|
||||||
for (const obj of ns.standing_objectives) {
|
|
||||||
lines.push(`- **${obj.id}** — ${obj.text}`);
|
|
||||||
}
|
|
||||||
lines.push('');
|
|
||||||
|
|
||||||
lines.push('## Success criteria');
|
|
||||||
lines.push('');
|
|
||||||
for (const ac of ns.success_criteria) {
|
|
||||||
lines.push(`- **${ac.id}** — ${ac.text}`);
|
|
||||||
}
|
|
||||||
lines.push('');
|
|
||||||
|
|
||||||
lines.push('## Workstreams');
|
|
||||||
lines.push('');
|
|
||||||
lines.push(
|
|
||||||
...renderMarkdownTable(
|
|
||||||
['id', 'title'],
|
|
||||||
ns.workstreams.map((ws) => [ws.id, ws.title]),
|
|
||||||
),
|
|
||||||
);
|
|
||||||
lines.push('');
|
|
||||||
|
|
||||||
lines.push('## Goals (backlog projection)');
|
|
||||||
lines.push('');
|
|
||||||
lines.push(
|
|
||||||
...renderMarkdownTable(
|
|
||||||
['id', 'title', 'phase', 'priority', 'depends_on'],
|
|
||||||
ns.goals.map((goal) => [
|
|
||||||
goal.id,
|
|
||||||
goal.title,
|
|
||||||
String(goal.phase),
|
|
||||||
goal.priority,
|
|
||||||
goal.depends_on.length > 0 ? goal.depends_on.join(', ') : '—',
|
|
||||||
]),
|
|
||||||
),
|
|
||||||
);
|
|
||||||
lines.push('');
|
|
||||||
|
|
||||||
lines.push('## Assumptions (vetoable)');
|
|
||||||
lines.push('');
|
|
||||||
for (const asm of ns.assumptions) {
|
|
||||||
const veto = asm.vetoable ? 'vetoable' : 'fixed';
|
|
||||||
lines.push(`- **${asm.id}** (${veto}) — ${asm.text}`);
|
|
||||||
}
|
|
||||||
lines.push('');
|
|
||||||
|
|
||||||
lines.push('## Spend');
|
|
||||||
lines.push('');
|
|
||||||
lines.push(`- **advisory:** ${ns.spend.advisory ? 'true' : 'false'}`);
|
|
||||||
lines.push(`- ${ns.spend.note}`);
|
|
||||||
|
|
||||||
// No trailing blank line: the writer appends a single newline, yielding the
|
|
||||||
// one-newline EOF prettier expects (round-trip stays format:check-clean).
|
|
||||||
return lines.join('\n');
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Resolve the repo's docs/fleet directory from this compiled module's location.
|
|
||||||
* fleet.ts lives at packages/mosaic/src/commands; docs/fleet sits at the repo
|
|
||||||
* root. Exposed so the generator + tests share one path resolution.
|
|
||||||
*/
|
|
||||||
export function resolveNorthStarPaths(repoRoot?: string): {
|
|
||||||
yamlPath: string;
|
|
||||||
markdownPath: string;
|
|
||||||
} {
|
|
||||||
const root = repoRoot ?? resolve(dirname(fileURLToPath(import.meta.url)), '..', '..', '..', '..');
|
|
||||||
const dir = join(root, 'docs', 'fleet');
|
|
||||||
return {
|
|
||||||
yamlPath: join(dir, 'NORTH_STAR.yaml'),
|
|
||||||
markdownPath: join(dir, 'NORTH_STAR.md'),
|
|
||||||
};
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Read NORTH_STAR.yaml, project it to Markdown, and write NORTH_STAR.md.
|
|
||||||
* The only IO in the NORTH_STAR pipeline; the parse + render steps it composes
|
|
||||||
* are pure. Returns the rendered Markdown so callers/tests can assert on it.
|
|
||||||
*/
|
|
||||||
export async function generateNorthStarMarkdown(repoRoot?: string): Promise<string> {
|
|
||||||
const { yamlPath, markdownPath } = resolveNorthStarPaths(repoRoot);
|
|
||||||
const rawText = await readFile(yamlPath, 'utf8');
|
|
||||||
const ns = parseNorthStar(rawText);
|
|
||||||
const markdown = renderNorthStarMarkdown(ns);
|
|
||||||
await writeFile(markdownPath, `${markdown}\n`, 'utf8');
|
|
||||||
return markdown;
|
|
||||||
}
|
|
||||||
|
|
||||||
export function generateAgentEnv(roster: FleetRoster, agent: FleetAgent): string {
|
export function generateAgentEnv(roster: FleetRoster, agent: FleetAgent): string {
|
||||||
const workingDirectory = agent.workingDirectory ?? roster.defaults.workingDirectory;
|
const workingDirectory = agent.workingDirectory ?? roster.defaults.workingDirectory;
|
||||||
return [
|
return [
|
||||||
@@ -681,7 +393,6 @@ export function buildAgentTailCommand(agentName: string, lines: number, socketNa
|
|||||||
// ---------------------------------------------------------------------------
|
// ---------------------------------------------------------------------------
|
||||||
|
|
||||||
export const HEARTBEAT_INTERVAL_MS = 15_000;
|
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
|
* Heartbeat interval in ms, honoring MOSAIC_HEARTBEAT_INTERVAL (seconds) so the
|
||||||
@@ -692,57 +403,8 @@ export function heartbeatIntervalMs(): number {
|
|||||||
const sec = Number.parseInt(process.env.MOSAIC_HEARTBEAT_INTERVAL ?? '', 10);
|
const sec = Number.parseInt(process.env.MOSAIC_HEARTBEAT_INTERVAL ?? '', 10);
|
||||||
return Number.isFinite(sec) && sec > 0 ? sec * 1000 : HEARTBEAT_INTERVAL_MS;
|
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 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 {
|
export interface HeartbeatInfo {
|
||||||
ts: Date | null;
|
ts: Date | null;
|
||||||
pid: number | null;
|
pid: number | null;
|
||||||
@@ -766,7 +428,6 @@ export interface AgentPsRow {
|
|||||||
paneCommand: string | null;
|
paneCommand: string | null;
|
||||||
idleSeconds: number | null;
|
idleSeconds: number | null;
|
||||||
heartbeat: HeartbeatInfo;
|
heartbeat: HeartbeatInfo;
|
||||||
readiness: ReadinessState;
|
|
||||||
/** roster runtime !== actual pane command */
|
/** roster runtime !== actual pane command */
|
||||||
driftFlag: boolean;
|
driftFlag: boolean;
|
||||||
/** active but UnitFileState=disabled */
|
/** active but UnitFileState=disabled */
|
||||||
@@ -799,7 +460,7 @@ export function buildSystemdShowCommand(agentName: string): string[] {
|
|||||||
|
|
||||||
/**
|
/**
|
||||||
* Returns the tmux list-panes command for an agent pane.
|
* 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[] {
|
export function buildTmuxListPanesCommand(agentName: string, socketName = ''): string[] {
|
||||||
return [
|
return [
|
||||||
@@ -809,7 +470,7 @@ export function buildTmuxListPanesCommand(agentName: string, socketName = ''): s
|
|||||||
'-t',
|
'-t',
|
||||||
`=${agentName}:0.0`,
|
`=${agentName}:0.0`,
|
||||||
'-F',
|
'-F',
|
||||||
'#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity} #{window_activity} #{session_activity}',
|
'#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity}',
|
||||||
];
|
];
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -909,8 +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}'`
|
* Parse the output of `tmux list-panes -F '#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity}'`
|
||||||
* Activity fields are Unix epoch timestamps (seconds), ordered most precise to coarsest.
|
* pane_activity is a Unix epoch timestamp (seconds).
|
||||||
*/
|
*/
|
||||||
export function parseTmuxListPanes(
|
export function parseTmuxListPanes(
|
||||||
output: string,
|
output: string,
|
||||||
@@ -920,18 +581,16 @@ export function parseTmuxListPanes(
|
|||||||
if (!line) {
|
if (!line) {
|
||||||
return { pid: null, command: null, dead: true, idleSeconds: null };
|
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 parts = line.split(' ');
|
||||||
const pid = parts[0] ? (Number.isFinite(Number(parts[0])) ? Number(parts[0]) : null) : null;
|
const pid = parts[0] ? (Number.isFinite(Number(parts[0])) ? Number(parts[0]) : null) : null;
|
||||||
const command = parts[1] ?? null;
|
const command = parts[1] ?? null;
|
||||||
const dead = parts[2] === '1';
|
const dead = parts[2] === '1';
|
||||||
const activityEpoch = parts
|
const activityEpoch = parts[3] ? Number(parts[3]) : NaN;
|
||||||
.slice(3, 6)
|
const idleSeconds =
|
||||||
.map((part) => (part ? Number(part) : NaN))
|
Number.isFinite(activityEpoch) && activityEpoch > 0
|
||||||
.find((epoch) => Number.isFinite(epoch) && epoch > 0);
|
? Math.floor((nowMs - activityEpoch * 1000) / 1000)
|
||||||
const idleSeconds = activityEpoch
|
: null;
|
||||||
? Math.max(0, Math.floor((nowMs - activityEpoch * 1000) / 1000))
|
|
||||||
: null;
|
|
||||||
return { pid, command, dead, idleSeconds };
|
return { pid, command, dead, idleSeconds };
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -1362,9 +1021,6 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
|
|||||||
const nowMs = Date.now();
|
const nowMs = Date.now();
|
||||||
|
|
||||||
const rows: AgentPsRow[] = [];
|
const rows: AgentPsRow[] = [];
|
||||||
const readinessThresholds = {
|
|
||||||
idleThresholdSeconds: idleThresholdSeconds(),
|
|
||||||
};
|
|
||||||
|
|
||||||
// Build the set of roster agent names for quick lookup when filtering socket sessions.
|
// Build the set of roster agent names for quick lookup when filtering socket sessions.
|
||||||
const rosterAgentNames = new Set(roster.agents.map((a) => a.name));
|
const rosterAgentNames = new Set(roster.agents.map((a) => a.name));
|
||||||
@@ -1395,17 +1051,6 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
|
|||||||
const bootEnableWarning =
|
const bootEnableWarning =
|
||||||
sysInfo.ActiveState === 'active' && sysInfo.UnitFileState === 'disabled';
|
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({
|
rows.push({
|
||||||
name: agent.name,
|
name: agent.name,
|
||||||
tenant_id,
|
tenant_id,
|
||||||
@@ -1413,12 +1058,11 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
|
|||||||
runtime: agent.runtime,
|
runtime: agent.runtime,
|
||||||
systemdActive: sysInfo.ActiveState,
|
systemdActive: sysInfo.ActiveState,
|
||||||
systemdEnabled: sysInfo.UnitFileState,
|
systemdEnabled: sysInfo.UnitFileState,
|
||||||
paneAlive,
|
paneAlive: !paneInfo.dead,
|
||||||
panePid: paneInfo.pid,
|
panePid: paneInfo.pid,
|
||||||
paneCommand: paneInfo.command,
|
paneCommand: paneInfo.command,
|
||||||
idleSeconds: paneInfo.idleSeconds,
|
idleSeconds: paneInfo.idleSeconds,
|
||||||
heartbeat: hb,
|
heartbeat: hb,
|
||||||
readiness,
|
|
||||||
driftFlag,
|
driftFlag,
|
||||||
bootEnableWarning,
|
bootEnableWarning,
|
||||||
managed: true,
|
managed: true,
|
||||||
@@ -1465,17 +1109,6 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
|
|||||||
const bootEnableWarning =
|
const bootEnableWarning =
|
||||||
sysInfo.ActiveState === 'active' && sysInfo.UnitFileState === 'disabled';
|
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({
|
rows.push({
|
||||||
name: sessionName,
|
name: sessionName,
|
||||||
tenant_id,
|
tenant_id,
|
||||||
@@ -1484,12 +1117,11 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
|
|||||||
runtime: 'unknown',
|
runtime: 'unknown',
|
||||||
systemdActive: sysInfo.ActiveState,
|
systemdActive: sysInfo.ActiveState,
|
||||||
systemdEnabled: sysInfo.UnitFileState,
|
systemdEnabled: sysInfo.UnitFileState,
|
||||||
paneAlive,
|
paneAlive: !paneInfo.dead,
|
||||||
panePid: paneInfo.pid,
|
panePid: paneInfo.pid,
|
||||||
paneCommand: paneInfo.command,
|
paneCommand: paneInfo.command,
|
||||||
idleSeconds: paneInfo.idleSeconds,
|
idleSeconds: paneInfo.idleSeconds,
|
||||||
heartbeat: hb,
|
heartbeat: hb,
|
||||||
readiness,
|
|
||||||
// No roster runtime to compare — drift is not meaningful for unmanaged sessions
|
// No roster runtime to compare — drift is not meaningful for unmanaged sessions
|
||||||
driftFlag: false,
|
driftFlag: false,
|
||||||
bootEnableWarning,
|
bootEnableWarning,
|
||||||
@@ -1531,7 +1163,7 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
|
|||||||
const idle = row.idleSeconds !== null ? `${row.idleSeconds}s` : '-';
|
const idle = row.idleSeconds !== null ? `${row.idleSeconds}s` : '-';
|
||||||
const hbAge =
|
const hbAge =
|
||||||
row.heartbeat.ageMs !== null
|
row.heartbeat.ageMs !== null
|
||||||
? `${Math.round(row.heartbeat.ageMs / 1000)}s/${row.readiness}`
|
? `${Math.round(row.heartbeat.ageMs / 1000)}s/${row.heartbeat.health}`
|
||||||
: `unknown`;
|
: `unknown`;
|
||||||
const model = row.heartbeat.model ?? '-';
|
const model = row.heartbeat.model ?? '-';
|
||||||
const flags: string[] = [];
|
const flags: string[] = [];
|
||||||
@@ -1701,11 +1333,6 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
|
|||||||
console.log(`Removed ${name} from the fleet.`);
|
console.log(`Removed ${name} from the fleet.`);
|
||||||
});
|
});
|
||||||
|
|
||||||
// Mosaic-native backlog of record (card A4). Resolves the active --mosaic-home
|
|
||||||
// (parent flag) at call time so the embedded PGlite store lands under the same
|
|
||||||
// fleet/ directory as the roster and heartbeats.
|
|
||||||
registerFleetBacklogCommand(cmd, () => cmd.opts<{ mosaicHome: string }>().mosaicHome);
|
|
||||||
|
|
||||||
return cmd;
|
return cmd;
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -1732,23 +1359,6 @@ export function registerFleetAgentCommands(
|
|||||||
}
|
}
|
||||||
});
|
});
|
||||||
|
|
||||||
agentCommand
|
|
||||||
.command('comms-block <role>')
|
|
||||||
.description(
|
|
||||||
"Print the Fleet Comms cheat-sheet for a roster role (preview a peer's peer-reach view)",
|
|
||||||
)
|
|
||||||
.option('--host <host>', 'Override the fleet host (preview a cross-host peer view)')
|
|
||||||
.action((role: string, opts: { host?: string }) => {
|
|
||||||
const mosaicHome = resolveMosaicHomeFromCommand(agentCommand, deps.mosaicHome);
|
|
||||||
const res = resolveCommsBlock(mosaicHome, role, opts.host);
|
|
||||||
if (!res.ok) {
|
|
||||||
console.error(`[mosaic] comms-block: ${res.error}`);
|
|
||||||
process.exitCode = 1;
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
console.log(res.output);
|
|
||||||
});
|
|
||||||
|
|
||||||
agentCommand
|
agentCommand
|
||||||
.command('status [agent]')
|
.command('status [agent]')
|
||||||
.description('Show tmux status for the local fleet or one agent')
|
.description('Show tmux status for the local fleet or one agent')
|
||||||
|
|||||||
@@ -7,7 +7,6 @@ import {
|
|||||||
buildFleetCommsBlock,
|
buildFleetCommsBlock,
|
||||||
renderPeerReach,
|
renderPeerReach,
|
||||||
readFleetCommsBlock,
|
readFleetCommsBlock,
|
||||||
resolveCommsBlock,
|
|
||||||
type CommsPeer,
|
type CommsPeer,
|
||||||
} from './comms-onboarding.js';
|
} from './comms-onboarding.js';
|
||||||
|
|
||||||
@@ -186,53 +185,3 @@ describe('readFleetCommsBlock — situational (the context a spawned agent gets)
|
|||||||
expect(readFleetCommsBlock(mkdtempSync(join(tmpdir(), 'noroster-')), 'orchestrator')).toBe('');
|
expect(readFleetCommsBlock(mkdtempSync(join(tmpdir(), 'noroster-')), 'orchestrator')).toBe('');
|
||||||
});
|
});
|
||||||
});
|
});
|
||||||
|
|
||||||
describe('resolveCommsBlock — `mosaic fleet comms-block <role>` emitter semantics', () => {
|
|
||||||
// The emitter wraps readFleetCommsBlock but must NEVER print an empty string silently:
|
|
||||||
// an unknown role / missing roster has to fail loud (caller maps !ok → stderr + exit 1)
|
|
||||||
// so `mosaic fleet comms-block bogus` is a visible error, not a confusing no-op. The
|
|
||||||
// success path returns the block verbatim for `mosaic fleet comms-block <peer>` previews.
|
|
||||||
let home: string;
|
|
||||||
beforeEach(() => {
|
|
||||||
home = mkdtempSync(join(tmpdir(), 'mosaic-commsblk-'));
|
|
||||||
mkdirSync(join(home, 'fleet'), { recursive: true });
|
|
||||||
writeFileSync(join(home, 'fleet', 'roster.yaml'), ROSTER);
|
|
||||||
});
|
|
||||||
afterEach(() => rmSync(home, { recursive: true, force: true }));
|
|
||||||
|
|
||||||
it('returns ok + the cheat-sheet for a roster member', () => {
|
|
||||||
const res = resolveCommsBlock(home, 'orchestrator', 'w-jarvis');
|
|
||||||
expect(res.ok).toBe(true);
|
|
||||||
expect(res.output).toContain('# Fleet Comms');
|
|
||||||
expect(res.output).toContain('| enhancer |');
|
|
||||||
expect(res.error).toBeUndefined();
|
|
||||||
});
|
|
||||||
|
|
||||||
it('fails loud (not ok + error naming the role) for a non-member — never silently empty', () => {
|
|
||||||
const res = resolveCommsBlock(home, 'stranger', 'w-jarvis');
|
|
||||||
expect(res.ok).toBe(false);
|
|
||||||
expect(res.output).toBe('');
|
|
||||||
expect(res.error).toContain('stranger');
|
|
||||||
});
|
|
||||||
|
|
||||||
it('fails loud when no roster exists at the mosaic home', () => {
|
|
||||||
const noRoster = mkdtempSync(join(tmpdir(), 'mosaic-noroster-'));
|
|
||||||
const res = resolveCommsBlock(noRoster, 'orchestrator', 'w-jarvis');
|
|
||||||
expect(res.ok).toBe(false);
|
|
||||||
expect(res.error).toBeTruthy();
|
|
||||||
rmSync(noRoster, { recursive: true, force: true });
|
|
||||||
});
|
|
||||||
|
|
||||||
it('fails loud for a missing role argument', () => {
|
|
||||||
const res = resolveCommsBlock(home, undefined, 'w-jarvis');
|
|
||||||
expect(res.ok).toBe(false);
|
|
||||||
expect(res.error).toBeTruthy();
|
|
||||||
});
|
|
||||||
|
|
||||||
it('honors a host override so a peer can preview its own cross-host view', () => {
|
|
||||||
// coder0-0 viewing with its own host → its self-identity line uses that host.
|
|
||||||
const res = resolveCommsBlock(home, 'coder0-0', '10.1.10.37');
|
|
||||||
expect(res.ok).toBe(true);
|
|
||||||
expect(res.output).toContain('`[10.1.10.37:coder0-0]`');
|
|
||||||
});
|
|
||||||
});
|
|
||||||
|
|||||||
@@ -179,48 +179,5 @@ export function readFleetCommsBlock(
|
|||||||
});
|
});
|
||||||
}
|
}
|
||||||
|
|
||||||
/** Result of resolving a comms-block emit request — see `mosaic fleet comms-block`. */
|
|
||||||
export interface CommsBlockResult {
|
|
||||||
/** True when a cheat-sheet was produced; false maps to stderr + non-zero exit. */
|
|
||||||
ok: boolean;
|
|
||||||
/** The Fleet-Comms cheat-sheet (empty unless ok). */
|
|
||||||
output: string;
|
|
||||||
/** Operator-facing reason when !ok. */
|
|
||||||
error?: string;
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Resolve the Fleet-Comms cheat-sheet for an explicit <role>, backing the
|
|
||||||
* `mosaic fleet comms-block <role>` command. Unlike readFleetCommsBlock — which
|
|
||||||
* returns '' on any miss so composeContract can no-op silently during a launch —
|
|
||||||
* this NEVER silently emits empty: an unknown role or missing roster yields
|
|
||||||
* ok:false + an operator-facing reason, so the CLI surfaces it (stderr + exit 1)
|
|
||||||
* rather than printing nothing. That makes it safe to preview any peer's view,
|
|
||||||
* e.g. `mosaic fleet comms-block coder0-0`.
|
|
||||||
*/
|
|
||||||
export function resolveCommsBlock(
|
|
||||||
mosaicHome: string,
|
|
||||||
role: string | undefined,
|
|
||||||
fleetHost?: string,
|
|
||||||
): CommsBlockResult {
|
|
||||||
if (!role) {
|
|
||||||
return { ok: false, output: '', error: 'comms-block requires a <role> argument' };
|
|
||||||
}
|
|
||||||
const block = fleetHost
|
|
||||||
? readFleetCommsBlock(mosaicHome, role, fleetHost)
|
|
||||||
: readFleetCommsBlock(mosaicHome, role);
|
|
||||||
if (!block) {
|
|
||||||
const rosterPath = join(mosaicHome, 'fleet', 'roster.yaml');
|
|
||||||
return {
|
|
||||||
ok: false,
|
|
||||||
output: '',
|
|
||||||
error: existsSync(rosterPath)
|
|
||||||
? `role "${role}" is not a member of the fleet roster at ${rosterPath}`
|
|
||||||
: `no fleet roster at ${rosterPath}`,
|
|
||||||
};
|
|
||||||
}
|
|
||||||
return { ok: true, output: block };
|
|
||||||
}
|
|
||||||
|
|
||||||
/** Default mosaic home (mirrors launch.ts), for callers that don't pass one. */
|
/** Default mosaic home (mirrors launch.ts), for callers that don't pass one. */
|
||||||
export const DEFAULT_MOSAIC_HOME_FOR_COMMS = join(homedir(), '.config', 'mosaic');
|
export const DEFAULT_MOSAIC_HOME_FOR_COMMS = join(homedir(), '.config', 'mosaic');
|
||||||
|
|||||||
@@ -8,9 +8,6 @@ import {
|
|||||||
readRosterAgentNames,
|
readRosterAgentNames,
|
||||||
runFrameworkReseed,
|
runFrameworkReseed,
|
||||||
refreshActiveFleetUnits,
|
refreshActiveFleetUnits,
|
||||||
readInstalledFrameworkVersion,
|
|
||||||
readBundledFrameworkVersion,
|
|
||||||
checkFrameworkDrift,
|
|
||||||
} from './update-checker.js';
|
} from './update-checker.js';
|
||||||
import { existsSync, readFileSync } from 'node:fs';
|
import { existsSync, readFileSync } from 'node:fs';
|
||||||
|
|
||||||
@@ -126,73 +123,3 @@ describe('refreshActiveFleetUnits', () => {
|
|||||||
expect(existsSync(join(configHome, 'systemd', 'user', 'mosaic-agent@.service'))).toBe(false);
|
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 });
|
|
||||||
});
|
|
||||||
});
|
|
||||||
});
|
|
||||||
|
|||||||
@@ -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
|
* Best-effort parse of the fleet roster for agent names (used to relaunch
|
||||||
* durable agents after a re-seed). Returns [] when no roster exists.
|
* durable agents after a re-seed). Returns [] when no roster exists.
|
||||||
|
|||||||
3
pnpm-lock.yaml
generated
3
pnpm-lock.yaml
generated
@@ -540,9 +540,6 @@ importers:
|
|||||||
'@mosaicstack/config':
|
'@mosaicstack/config':
|
||||||
specifier: workspace:*
|
specifier: workspace:*
|
||||||
version: link:../config
|
version: link:../config
|
||||||
'@mosaicstack/db':
|
|
||||||
specifier: workspace:*
|
|
||||||
version: link:../db
|
|
||||||
'@mosaicstack/forge':
|
'@mosaicstack/forge':
|
||||||
specifier: workspace:*
|
specifier: workspace:*
|
||||||
version: link:../forge
|
version: link:../forge
|
||||||
|
|||||||
Reference in New Issue
Block a user