Compare commits
1 Commits
main
...
release/mo
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
96a9892717 |
@@ -1,70 +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 delivery fleet 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.
|
||||
|
||||
## 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.
|
||||
|
||||
## 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.
|
||||
|
||||
## 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 |
|
||||
|
||||
## 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 |
|
||||
|
||||
## 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.
|
||||
|
||||
## Spend
|
||||
|
||||
- **advisory:** true
|
||||
- No per-task token meter yet; budgets degrade to TTL. Spend is tracked only as an advisory projection alongside each card.
|
||||
@@ -1,169 +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 delivery fleet 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.
|
||||
|
||||
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.
|
||||
|
||||
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.
|
||||
|
||||
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
|
||||
|
||||
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]
|
||||
|
||||
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.'
|
||||
|
||||
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.
|
||||
@@ -1,53 +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.
|
||||
@@ -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).
|
||||
@@ -25,9 +25,7 @@ INSTALL_MODE="${MOSAIC_INSTALL_MODE:-prompt}"
|
||||
# User-created content in these paths survives rsync --delete.
|
||||
#
|
||||
# fleet/* — the framework SEEDS only fleet/examples, fleet/roles, and
|
||||
# fleet/roster.schema.json (synced normally — every fleet/roles/*.md role contract
|
||||
# lands automatically via this sync, so no per-file entry is needed). The user's
|
||||
# own fleet files MUST
|
||||
# fleet/roster.schema.json (synced normally). The user's own fleet files MUST
|
||||
# survive `mosaic update` (which runs this sync automatically): the active
|
||||
# roster (`fleet/roster.yaml` + any other `fleet/*.yaml`), per-agent env
|
||||
# (`fleet/agents/`), and heartbeat run dir (`fleet/run/`). Without these, an
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@mosaicstack/mosaic",
|
||||
"version": "0.0.45",
|
||||
"version": "0.0.43",
|
||||
"repository": {
|
||||
"type": "git",
|
||||
"url": "https://git.mosaicstack.dev/mosaicstack/stack.git",
|
||||
|
||||
@@ -1,199 +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 delivery fleet');
|
||||
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');
|
||||
});
|
||||
});
|
||||
@@ -27,6 +27,7 @@ import {
|
||||
enableFleetUnits,
|
||||
FLEET_PROFILES,
|
||||
HEARTBEAT_IDLE_THRESHOLD_SECONDS,
|
||||
HEARTBEAT_STUCK_THRESHOLD_SECONDS,
|
||||
generateAgentEnv,
|
||||
getDefaultOperatorSourceLabel,
|
||||
getDefaultTenantAndHost,
|
||||
@@ -47,6 +48,7 @@ import {
|
||||
resolvePresetFilename,
|
||||
RUNTIME_ACCEPTABLE_COMMANDS,
|
||||
serializeRosterToYaml,
|
||||
stuckThresholdSeconds,
|
||||
VERIFY_DEFAULT_TIMEOUT_MS,
|
||||
VERIFY_POLL_INTERVAL_MS,
|
||||
type AgentPsRow,
|
||||
@@ -853,7 +855,7 @@ describe('fleet ps — command construction', () => {
|
||||
'-t',
|
||||
'=canary-pi:0.0',
|
||||
'-F',
|
||||
'#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity} #{window_activity} #{session_activity}',
|
||||
'#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity}',
|
||||
]);
|
||||
});
|
||||
|
||||
@@ -938,33 +940,42 @@ describe('fleet ps — heartbeat parsing', () => {
|
||||
|
||||
describe('fleet ps — readiness thresholds', () => {
|
||||
const savedIdle = process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD;
|
||||
const savedStuck = process.env.MOSAIC_HEARTBEAT_STUCK_THRESHOLD;
|
||||
|
||||
afterEach(() => {
|
||||
if (savedIdle === undefined) delete process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD;
|
||||
else process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD = savedIdle;
|
||||
if (savedStuck === undefined) delete process.env.MOSAIC_HEARTBEAT_STUCK_THRESHOLD;
|
||||
else process.env.MOSAIC_HEARTBEAT_STUCK_THRESHOLD = savedStuck;
|
||||
});
|
||||
|
||||
it('uses the default activity threshold when env is unset', () => {
|
||||
it('uses default readiness thresholds when env is unset', () => {
|
||||
delete process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD;
|
||||
delete process.env.MOSAIC_HEARTBEAT_STUCK_THRESHOLD;
|
||||
|
||||
expect(idleThresholdSeconds()).toBe(HEARTBEAT_IDLE_THRESHOLD_SECONDS);
|
||||
expect(stuckThresholdSeconds()).toBe(HEARTBEAT_STUCK_THRESHOLD_SECONDS);
|
||||
});
|
||||
|
||||
it('honors a positive integer activity threshold from env', () => {
|
||||
it('honors positive integer readiness thresholds from env', () => {
|
||||
process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD = '120';
|
||||
process.env.MOSAIC_HEARTBEAT_STUCK_THRESHOLD = '480';
|
||||
|
||||
expect(idleThresholdSeconds()).toBe(120);
|
||||
expect(stuckThresholdSeconds()).toBe(480);
|
||||
});
|
||||
|
||||
it('falls back to the default for invalid activity thresholds', () => {
|
||||
it('falls back to defaults for invalid readiness thresholds', () => {
|
||||
process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD = '0';
|
||||
process.env.MOSAIC_HEARTBEAT_STUCK_THRESHOLD = 'not-a-number';
|
||||
|
||||
expect(idleThresholdSeconds()).toBe(HEARTBEAT_IDLE_THRESHOLD_SECONDS);
|
||||
expect(stuckThresholdSeconds()).toBe(HEARTBEAT_STUCK_THRESHOLD_SECONDS);
|
||||
});
|
||||
});
|
||||
|
||||
describe('fleet ps — readiness classification', () => {
|
||||
const thresholds = { idleThresholdSeconds: 300 };
|
||||
const thresholds = { idleThresholdSeconds: 300, stuckThresholdSeconds: 900 };
|
||||
|
||||
it('reports dead when the pane is not alive', () => {
|
||||
expect(
|
||||
@@ -993,7 +1004,7 @@ describe('fleet ps — readiness classification', () => {
|
||||
).toBe('stale');
|
||||
});
|
||||
|
||||
it('reports working when heartbeat status is busy, even after the activity threshold', () => {
|
||||
it('reports working when heartbeat status is busy, even past stuck threshold', () => {
|
||||
expect(
|
||||
classifyReadiness(
|
||||
{ paneAlive: true, hbHealth: 'healthy', hbStatus: 'busy', idleSeconds: 2_000 },
|
||||
@@ -1002,7 +1013,7 @@ describe('fleet ps — readiness classification', () => {
|
||||
).toBe('working');
|
||||
});
|
||||
|
||||
it('reports working when pane idle seconds are null', () => {
|
||||
it('reports working when pane idle seconds are unavailable', () => {
|
||||
expect(
|
||||
classifyReadiness(
|
||||
{ paneAlive: true, hbHealth: 'healthy', hbStatus: 'ok', idleSeconds: null },
|
||||
@@ -1011,31 +1022,25 @@ describe('fleet ps — readiness classification', () => {
|
||||
).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', () => {
|
||||
it('reports stuck at the stuck threshold boundary', () => {
|
||||
expect(
|
||||
classifyReadiness(
|
||||
{ paneAlive: true, hbHealth: 'healthy', hbStatus: 'ok', idleSeconds: Number.NaN },
|
||||
{ paneAlive: true, hbHealth: 'healthy', hbStatus: 'ok', idleSeconds: 900 },
|
||||
thresholds,
|
||||
),
|
||||
).toBe('working');
|
||||
).toBe('stuck');
|
||||
});
|
||||
|
||||
it('reports available at the activity threshold boundary', () => {
|
||||
it('reports idle at the idle threshold boundary', () => {
|
||||
expect(
|
||||
classifyReadiness(
|
||||
{ paneAlive: true, hbHealth: 'healthy', hbStatus: 'ok', idleSeconds: 300 },
|
||||
thresholds,
|
||||
),
|
||||
).toBe('available');
|
||||
).toBe('idle');
|
||||
});
|
||||
|
||||
it('reports working below the activity threshold', () => {
|
||||
it('reports working below the idle threshold', () => {
|
||||
expect(
|
||||
classifyReadiness(
|
||||
{ paneAlive: true, hbHealth: 'healthy', hbStatus: 'ok', idleSeconds: 299 },
|
||||
@@ -1044,14 +1049,13 @@ describe('fleet ps — readiness classification', () => {
|
||||
).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');
|
||||
it('checks stuck before idle when thresholds are inverted', () => {
|
||||
expect(
|
||||
classifyReadiness(
|
||||
{ paneAlive: true, hbHealth: 'healthy', hbStatus: 'ok', idleSeconds: 350 },
|
||||
{ idleThresholdSeconds: 900, stuckThresholdSeconds: 300 },
|
||||
),
|
||||
).toBe('stuck');
|
||||
});
|
||||
});
|
||||
|
||||
@@ -1075,11 +1079,9 @@ describe('fleet ps — systemd show parsing', () => {
|
||||
describe('fleet ps — tmux list-panes parsing', () => {
|
||||
const NOW_MS = 1_700_000_000_000;
|
||||
|
||||
it('uses pane_activity when present', () => {
|
||||
const paneActivityEpoch = Math.floor((NOW_MS - 30_000) / 1000); // 30s ago
|
||||
const windowActivityEpoch = Math.floor((NOW_MS - 60_000) / 1000); // 60s ago
|
||||
const sessionActivityEpoch = Math.floor((NOW_MS - 90_000) / 1000); // 90s ago
|
||||
const output = `12345 claude 0 ${paneActivityEpoch} ${windowActivityEpoch} ${sessionActivityEpoch}\n`;
|
||||
it('parses alive pane with pid, command, and idle time', () => {
|
||||
const activityEpoch = Math.floor((NOW_MS - 30_000) / 1000); // 30s ago
|
||||
const output = `12345 claude 0 ${activityEpoch}\n`;
|
||||
const result = parseTmuxListPanes(output, NOW_MS);
|
||||
expect(result.pid).toBe(12345);
|
||||
expect(result.command).toBe('claude');
|
||||
@@ -1087,45 +1089,8 @@ describe('fleet ps — tmux list-panes parsing', () => {
|
||||
expect(result.idleSeconds).toBe(30);
|
||||
});
|
||||
|
||||
it('uses window_activity when pane_activity is empty', () => {
|
||||
const windowActivityEpoch = Math.floor((NOW_MS - 45_000) / 1000); // 45s ago
|
||||
const sessionActivityEpoch = Math.floor((NOW_MS - 90_000) / 1000); // 90s ago
|
||||
const output = `12345 node 0 ${windowActivityEpoch} ${sessionActivityEpoch}\n`;
|
||||
expect(output).toContain('0 '); // empty pane_activity preserves index alignment
|
||||
const result = parseTmuxListPanes(output, NOW_MS);
|
||||
expect(result.pid).toBe(12345);
|
||||
expect(result.command).toBe('node');
|
||||
expect(result.dead).toBe(false);
|
||||
expect(result.idleSeconds).toBe(45);
|
||||
});
|
||||
|
||||
it('uses session_activity when pane_activity and window_activity are empty', () => {
|
||||
const sessionActivityEpoch = Math.floor((NOW_MS - 75_000) / 1000); // 75s ago
|
||||
const output = `12345 node 0 ${sessionActivityEpoch}\n`;
|
||||
const result = parseTmuxListPanes(output, NOW_MS);
|
||||
expect(result.idleSeconds).toBe(75);
|
||||
});
|
||||
|
||||
it('reports null idleSeconds when all activity sources are empty', () => {
|
||||
const output = '12345 node 0 \n';
|
||||
const result = parseTmuxListPanes(output, NOW_MS);
|
||||
expect(result.idleSeconds).toBeNull();
|
||||
});
|
||||
|
||||
it('computes exact idle seconds from now minus epoch seconds', () => {
|
||||
const activityEpoch = 1_699_999_877;
|
||||
const result = parseTmuxListPanes(`12345 claude 0 ${activityEpoch} 0 0\n`, NOW_MS);
|
||||
expect(result.idleSeconds).toBe(123);
|
||||
});
|
||||
|
||||
it('clamps future activity epochs to 0 idle seconds', () => {
|
||||
const futureActivityEpoch = Math.floor((NOW_MS + 30_000) / 1000);
|
||||
const result = parseTmuxListPanes(`12345 claude 0 ${futureActivityEpoch} 0 0\n`, NOW_MS);
|
||||
expect(result.idleSeconds).toBe(0);
|
||||
});
|
||||
|
||||
it('reports dead pane when pane_dead=1', () => {
|
||||
const output = `0 bash 1 0 0 0\n`;
|
||||
const output = `0 bash 1 0\n`;
|
||||
const result = parseTmuxListPanes(output, NOW_MS);
|
||||
expect(result.dead).toBe(true);
|
||||
});
|
||||
@@ -1550,7 +1515,7 @@ describe('fleet ps — command sequences issued', () => {
|
||||
});
|
||||
|
||||
describe('fleet ps — readiness table output', () => {
|
||||
it('renders available in HB column without idle/stuck alarm flags', async () => {
|
||||
it('renders readiness in HB column and flags idle/stuck rows', async () => {
|
||||
const home = await mkdtemp(join(tmpdir(), 'mosaic-fleet-'));
|
||||
const rosterPath = join(home, 'fleet', 'roster.yaml');
|
||||
const runDir = join(home, 'fleet', 'run');
|
||||
@@ -1561,34 +1526,36 @@ describe('fleet ps — readiness table output', () => {
|
||||
'version: 1',
|
||||
'transport: tmux',
|
||||
'agents:',
|
||||
' - name: working-agent',
|
||||
' - name: idle-agent',
|
||||
' runtime: pi',
|
||||
' - name: available-agent',
|
||||
' - name: stuck-agent',
|
||||
' runtime: pi',
|
||||
].join('\n'),
|
||||
);
|
||||
|
||||
const nowMs = 1_700_000_000_000;
|
||||
const workingActivityEpoch = Math.floor((nowMs - 2_000) / 1000);
|
||||
const availableActivityEpoch = Math.floor((nowMs - 40_000) / 1000);
|
||||
const idleActivityEpoch = Math.floor((nowMs - 10_000) / 1000);
|
||||
const stuckActivityEpoch = Math.floor((nowMs - 40_000) / 1000);
|
||||
const hbTs = new Date(nowMs - 1_000).toISOString();
|
||||
await writeFile(join(runDir, 'working-agent.hb'), `ts=${hbTs}\npid=111\nstatus=ok\n`);
|
||||
await writeFile(join(runDir, 'available-agent.hb'), `ts=${hbTs}\npid=222\nstatus=ok\n`);
|
||||
await writeFile(join(runDir, 'idle-agent.hb'), `ts=${hbTs}\npid=111\nstatus=ok\n`);
|
||||
await writeFile(join(runDir, 'stuck-agent.hb'), `ts=${hbTs}\npid=222\nstatus=ok\n`);
|
||||
|
||||
const savedIdle = process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD;
|
||||
const savedStuck = process.env.MOSAIC_HEARTBEAT_STUCK_THRESHOLD;
|
||||
process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD = '5';
|
||||
process.env.MOSAIC_HEARTBEAT_STUCK_THRESHOLD = '30';
|
||||
|
||||
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 };
|
||||
return { stdout: 'idle-agent\nstuck-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('=idle-agent:0.0')) {
|
||||
return { stdout: `111 pi 0 ${idleActivityEpoch}\n`, stderr: '', exitCode: 0 };
|
||||
}
|
||||
if (full.includes('=available-agent:0.0')) {
|
||||
return { stdout: `222 pi 0 ${availableActivityEpoch}\n`, stderr: '', exitCode: 0 };
|
||||
if (full.includes('=stuck-agent:0.0')) {
|
||||
return { stdout: `222 pi 0 ${stuckActivityEpoch}\n`, stderr: '', exitCode: 0 };
|
||||
}
|
||||
if (full.includes('systemctl') && full.includes('show')) {
|
||||
return {
|
||||
@@ -1617,17 +1584,19 @@ describe('fleet ps — readiness table output', () => {
|
||||
dateNow.mockRestore();
|
||||
if (savedIdle === undefined) delete process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD;
|
||||
else process.env.MOSAIC_HEARTBEAT_IDLE_THRESHOLD = savedIdle;
|
||||
if (savedStuck === undefined) delete process.env.MOSAIC_HEARTBEAT_STUCK_THRESHOLD;
|
||||
else process.env.MOSAIC_HEARTBEAT_STUCK_THRESHOLD = savedStuck;
|
||||
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/);
|
||||
const idleLine = lines.find((line) => line.includes('idle-agent'));
|
||||
const stuckLine = lines.find((line) => line.includes('stuck-agent'));
|
||||
expect(idleLine).toBeDefined();
|
||||
expect(idleLine).toContain('1s/idle');
|
||||
expect(idleLine).toMatch(/\bIDLE\b/);
|
||||
expect(stuckLine).toBeDefined();
|
||||
expect(stuckLine).toContain('1s/stuck');
|
||||
expect(stuckLine).toMatch(/\bSTUCK\b/);
|
||||
});
|
||||
});
|
||||
|
||||
|
||||
@@ -197,292 +197,6 @@ export function getRosterAgent(roster: FleetRoster, name: string): FleetAgent {
|
||||
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 {
|
||||
const workingDirectory = agent.workingDirectory ?? roster.defaults.workingDirectory;
|
||||
return [
|
||||
@@ -681,6 +395,7 @@ export function buildAgentTailCommand(agentName: string, lines: number, socketNa
|
||||
|
||||
export const HEARTBEAT_INTERVAL_MS = 15_000;
|
||||
export const HEARTBEAT_IDLE_THRESHOLD_SECONDS = 300;
|
||||
export const HEARTBEAT_STUCK_THRESHOLD_SECONDS = 900;
|
||||
|
||||
/**
|
||||
* Heartbeat interval in ms, honoring MOSAIC_HEARTBEAT_INTERVAL (seconds) so the
|
||||
@@ -692,14 +407,20 @@ export function heartbeatIntervalMs(): number {
|
||||
return Number.isFinite(sec) && sec > 0 ? sec * 1000 : HEARTBEAT_INTERVAL_MS;
|
||||
}
|
||||
|
||||
/** Activity threshold in seconds, honoring MOSAIC_HEARTBEAT_IDLE_THRESHOLD. */
|
||||
/** Idle 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;
|
||||
}
|
||||
|
||||
/** Stuck threshold in seconds, honoring MOSAIC_HEARTBEAT_STUCK_THRESHOLD. */
|
||||
export function stuckThresholdSeconds(): number {
|
||||
const sec = Number.parseInt(process.env.MOSAIC_HEARTBEAT_STUCK_THRESHOLD ?? '', 10);
|
||||
return Number.isFinite(sec) && sec > 0 ? sec : HEARTBEAT_STUCK_THRESHOLD_SECONDS;
|
||||
}
|
||||
export const HEARTBEAT_HEALTHY_MULTIPLIER = 3;
|
||||
|
||||
export type ReadinessState = 'working' | 'available' | 'stuck' | 'stale' | 'dead' | 'unknown';
|
||||
export type ReadinessState = 'working' | 'idle' | 'stuck' | 'stale' | 'dead' | 'unknown';
|
||||
|
||||
export interface ReadinessSignals {
|
||||
paneAlive: boolean;
|
||||
@@ -710,6 +431,7 @@ export interface ReadinessSignals {
|
||||
|
||||
export interface ReadinessThresholds {
|
||||
idleThresholdSeconds: number;
|
||||
stuckThresholdSeconds: number;
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -734,8 +456,12 @@ export function classifyReadiness(
|
||||
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';
|
||||
const stuckThreshold = Number.isFinite(thresholds?.stuckThresholdSeconds)
|
||||
? Number(thresholds?.stuckThresholdSeconds)
|
||||
: stuckThresholdSeconds();
|
||||
|
||||
if (idleSeconds >= stuckThreshold) return 'stuck';
|
||||
if (idleSeconds >= idleThreshold) return 'idle';
|
||||
return 'working';
|
||||
} catch {
|
||||
return 'unknown';
|
||||
@@ -798,7 +524,7 @@ export function buildSystemdShowCommand(agentName: string): string[] {
|
||||
|
||||
/**
|
||||
* Returns the tmux list-panes command for an agent pane.
|
||||
* Format: `#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity} #{window_activity} #{session_activity}`
|
||||
* Format: `#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity}`
|
||||
*/
|
||||
export function buildTmuxListPanesCommand(agentName: string, socketName = ''): string[] {
|
||||
return [
|
||||
@@ -808,7 +534,7 @@ export function buildTmuxListPanesCommand(agentName: string, socketName = ''): s
|
||||
'-t',
|
||||
`=${agentName}:0.0`,
|
||||
'-F',
|
||||
'#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity} #{window_activity} #{session_activity}',
|
||||
'#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity}',
|
||||
];
|
||||
}
|
||||
|
||||
@@ -908,8 +634,8 @@ export function parseSystemdShow(output: string): {
|
||||
}
|
||||
|
||||
/**
|
||||
* Parse the output of `tmux list-panes -F '#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity} #{window_activity} #{session_activity}'`
|
||||
* Activity fields are Unix epoch timestamps (seconds), ordered most precise to coarsest.
|
||||
* Parse the output of `tmux list-panes -F '#{pane_pid} #{pane_current_command} #{pane_dead} #{pane_activity}'`
|
||||
* pane_activity is a Unix epoch timestamp (seconds).
|
||||
*/
|
||||
export function parseTmuxListPanes(
|
||||
output: string,
|
||||
@@ -919,18 +645,16 @@ export function parseTmuxListPanes(
|
||||
if (!line) {
|
||||
return { pid: null, command: null, dead: true, idleSeconds: null };
|
||||
}
|
||||
// format: <pid> <command> <dead(0|1)> <pane_activity> <window_activity> <session_activity>
|
||||
// format: <pid> <command> <dead(0|1)> <activity_epoch>
|
||||
const parts = line.split(' ');
|
||||
const pid = parts[0] ? (Number.isFinite(Number(parts[0])) ? Number(parts[0]) : null) : null;
|
||||
const command = parts[1] ?? null;
|
||||
const dead = parts[2] === '1';
|
||||
const activityEpoch = parts
|
||||
.slice(3, 6)
|
||||
.map((part) => (part ? Number(part) : NaN))
|
||||
.find((epoch) => Number.isFinite(epoch) && epoch > 0);
|
||||
const idleSeconds = activityEpoch
|
||||
? Math.max(0, Math.floor((nowMs - activityEpoch * 1000) / 1000))
|
||||
: null;
|
||||
const activityEpoch = parts[3] ? Number(parts[3]) : NaN;
|
||||
const idleSeconds =
|
||||
Number.isFinite(activityEpoch) && activityEpoch > 0
|
||||
? Math.floor((nowMs - activityEpoch * 1000) / 1000)
|
||||
: null;
|
||||
return { pid, command, dead, idleSeconds };
|
||||
}
|
||||
|
||||
@@ -1363,6 +1087,7 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
|
||||
const rows: AgentPsRow[] = [];
|
||||
const readinessThresholds = {
|
||||
idleThresholdSeconds: idleThresholdSeconds(),
|
||||
stuckThresholdSeconds: stuckThresholdSeconds(),
|
||||
};
|
||||
|
||||
// Build the set of roster agent names for quick lookup when filtering socket sessions.
|
||||
@@ -1537,6 +1262,8 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
|
||||
if (!row.managed) flags.push('UNMANAGED');
|
||||
if (row.driftFlag) flags.push('DRIFT');
|
||||
if (row.bootEnableWarning) flags.push('BOOT-ENABLE');
|
||||
if (row.readiness === 'idle') flags.push('IDLE');
|
||||
if (row.readiness === 'stuck') flags.push('STUCK');
|
||||
|
||||
console.log(
|
||||
[
|
||||
|
||||
Reference in New Issue
Block a user