Compare commits

..

1 Commits

Author SHA1 Message Date
05a2962c8b docs(framework): P3.1 fast-follow — governance wording + gate scope + bare-launch note
All checks were successful
ci/woodpecker/pr/ci Pipeline was successful
ci/woodpecker/push/ci Pipeline was successful
Non-blocking items from the #575 dual-engine review:
- CONSTITUTION.md: state explicitly there is NO CONSTITUTION.local.md and hard
  gates are not locally overridable (clarity vs LAYER-MODEL overlay-eligibility)
- verify-sanitized.sh: expand identity scan to *.yml/*.yaml/*.toml/*.env/*.service
  (operator data could hide in shipped configs) — gate green, no new hits
- AGENTS.md: clarify the intentional bare-launch stop-if-missing strictness vs the
  launcher's readOptional tolerance (which keeps pre-upgrade hosts working)

Refs #542, closes #576

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-20 22:22:50 -05:00
27 changed files with 76 additions and 5275 deletions

View File

@@ -25,10 +25,12 @@ steps:
commands: commands:
- apk add --no-cache bash - apk add --no-cache bash
- bash packages/mosaic/framework/tools/quality/scripts/verify-sanitized.sh - bash packages/mosaic/framework/tools/quality/scripts/verify-sanitized.sh
# Resident line-count ceiling over framework-owned resident files # L0 resident-token budget: keep the Constitution + dispatcher small.
# (Constitution + dispatcher + each RUNTIME.md slice). See DESIGN §7 / R9. - |
- bash packages/mosaic/framework/tools/quality/scripts/check-resident-budget.sh --self-test for f in CONSTITUTION.md AGENTS.md; do
- bash packages/mosaic/framework/tools/quality/scripts/check-resident-budget.sh n=$(wc -l < "packages/mosaic/framework/defaults/$f")
if [ "$n" -gt 120 ]; then echo "L0 budget exceeded: defaults/$f is $n lines (max 120)"; exit 1; fi
done
typecheck: typecheck:
image: *node_image image: *node_image

View File

@@ -45,7 +45,3 @@ Active workstream is **W1 — Federation v1**. Workers should:
- Status: PR open, awaiting maintainer merge ratification (fleet-governing change). - Status: PR open, awaiting maintainer merge ratification (fleet-governing change).
- Cut always-injected contract AGENTS+TOOLS+RUNTIME 8,827→4,122 tok (53%); all 12 hard gates intact. - Cut always-injected contract AGENTS+TOOLS+RUNTIME 8,827→4,122 tok (53%); all 12 hard gates intact.
- Validation: deterministic gate-checklist PASS; headless A/B thin 7/9 vs monolith 5/9. Detail: scratchpads/contract-thin-core.md. - Validation: deterministic gate-checklist PASS; headless A/B thin 7/9 vs monolith 5/9. Detail: scratchpads/contract-thin-core.md.
## P6 — Docs, compliance matrix, alpha tag (#606) — feat/p6-docs-compliance-alpha
- Status: in-repo deliverables done (CONTRIBUTING.md + harness×gate compliance matrix + check-resident-budget.sh + CI wiring). Remaining: aiguide reconcile (separate repo), alpha tag (Lead, post-merge). Detail: scratchpads/p6-docs-compliance-alpha.md.

View File

@@ -1,75 +0,0 @@
# Constitution Alpha — Definition-of-Done checklist + release notes
Drafted for the `v0.0.39-alpha` tag (Lead cuts after P5 #605 → P6 #607 → aiguide #8 merge).
Maps every DoD §8 acceptance criterion to its merged evidence. Legend:
**✅ merged on main** · **⏳ review-ready PR (pending merge)** · **🔲 Lead action**.
## DoD §8 green-checklist
| # | Acceptance criterion (DESIGN §8) | Status | Evidence / PR |
| --- | ------------------------------------------------------------------------------------------------------ | ------ | ----------------- |
| 1 | MIT `LICENSE` (root + framework) + `"license":"MIT"` in package.json | ✅ | P0 #570 |
| 2 | Three credential-path sites + hook URL fast-failed (no private paths in `*.sh`/hooks) | ✅ | P0 #570 |
| 3 | `verify-sanitized.sh` (two-class, `*.sh`+`*.md`, self-tested) wired **blocking** in CI | ✅ | P1 #572 |
| 4 | Operator data purged from the full set (guides / tools / init-generator) | ✅ | P2 #572 |
| 5 | `rails/``tools/` in **both** template families | ✅ | P2 #572 |
| 6 | `jarvis-loop.json` deleted; `defaults/SOUL.md`**neutral sanitized persona** (Q10 decision) | ✅ | P2 #572 |
| 7 | `CONSTITUTION.md` extracted (gates one place, capability-verb, §1.4 split, no false "already loaded") | ✅ | P3 #575 / #577 |
| 8 | `AGENTS.md`/`STANDARDS.md` out of `PRESERVE_PATHS` + seed-semantics → overwrite in **both** installers | ✅ | P4 #590 |
| 9 | Snapshot + v2→v3 migration moving user edits to `.local`/`.bak`; `FRAMEWORK_VERSION=3` | ✅ | P4 #590 / #593 |
| 10 | `mosaic-init --non-interactive` fail-closed persona | ✅ | P4 #590 |
| 11 | **5-fixture migration matrix** green against **both** installers asserting **injected bytes** | ✅ | P4 #590 / #593 |
| 12 | `compose-contract` built + composer unit test (per-tier anchor + Tier-3 byte-equality) | ⏳ | P5 #605 |
| 13 | Resident line-count ceiling enforced (framework-owned resident files) | ⏳ | P6 #607 |
| 14 | `CONTRIBUTING.md` + harness×gate compliance matrix | ⏳ | P6 #607 |
| 15 | `aiguide` reconciled with the Constitution | ⏳ | aiguide #8 |
| 16 | Each phase PR CI-green; alpha tag pushed + Gitea release published | 🔲 | Lead (post-merge) |
**Note on #6:** the DoD's literal "delete `defaults/SOUL.md`" was superseded by the resolved
**Q10** decision — ship a _neutral, operator-agnostic_ example persona instead of deleting it. Main
carries the sanitized 2.6 KB neutral SOUL.md ("Mosaic agent", no operator identity); the sanitization
gate confirms it is PII-clean. Criterion met in spirit (no operator persona leaks) via the better option.
**Gate to flip 1214 → ✅:** merge P5 #605 → P6 #607 (rebase auto-drops the dup format fix
`adc7df2`/`9f6da92`) → aiguide #8, with `ci.yml` terminal-green on the merged head.
---
## Release notes — `v0.0.39-alpha` (Mosaic Framework Constitution, alpha)
### Mosaic Framework Constitution — Alpha
This release makes the Mosaic framework a **safe-to-open-source, fork-and-customize agent
operating layer**. It separates the non-negotiable law from operator identity, makes
customization survive upgrades, and wires the guarantees into CI.
**Highlights**
- **Constitution (L0).** The hard gates now live in one place — `CONSTITUTION.md` — authored in
capability verbs, with a thin `AGENTS.md` dispatcher that references the law instead of restating
it. Governance model in `constitution/LAYER-MODEL.md`.
- **Public & sanitized.** MIT-licensed; all operator identity, private paths, and credential sites
removed from shipped files. A self-tested `verify-sanitized.sh` gate (two rule classes) runs
**blocking** in CI so re-contamination can't merge.
- **Upgrade-safe customization.** Framework-owned files overwrite cleanly on upgrade while
`SOUL.md`/`USER.md`/`*.local.md`/`credentials` are preserved. The v2→v3 migration snapshots first
and moves any user-edited `AGENTS.md`/`STANDARDS.md` to `.pre-constitution.bak`/`.local.md`
never silently lost. Verified by a 5-fixture matrix across **both** installers.
- **Operator overlays.** `mosaic compose-contract <harness>` merges your `*.local.md` deltas into
the contract per harness, so customization reaches the model as one pre-merged blob.
- **Cross-harness.** Single L0 source referenced (never restated) by Claude / Codex / OpenCode / Pi;
tiered injection with a byte-equal Tier-3 fallback read.
- **Guardrails in CI.** Resident line-count ceiling over framework-owned resident files; composer
unit test; sanitization gate — all blocking.
- **Docs.** `CONTRIBUTING.md` with the layer model, dual-installer parity rule, and a harness×gate
**compliance matrix** (the Codex/OpenCode/Pi hook-parity gap is tracked for v2).
**Known limitations (accepted, documented in `CONTRIBUTING.md` §9)**
- Bare launches that bypass `mosaic` get base contracts only (no `*.local` overlays) and are not
drift-checked by `mosaic doctor` — mitigated by the unconditional Tier-3 self-load + a nudge.
- Codex/OpenCode/Pi mechanical hook parity, `policy/*.md` composition, and live-launch cross-harness
verification are **v2**.
**Phase lineage:** P0 #570 · P1+P2 #572 · P3 #575/#577 · P4 #590/#593 · P5 #605 · P6 #607 ·
aiguide #8 (umbrella #542).

View File

@@ -1,109 +0,0 @@
# PRD — Mosaic Fleet Suite (init, configure, operate)
> **Workstream:** W-FLEET (Fleet) under mission `mvp-20260312` · **Phase:** 3→4 productization
> **North star:** [docs/fleet/north-star.md](./north-star.md) · prior: Phase-2 observability (#579), durable launch (#581), real-agent enablement (#583/#584/#586), releases 0.0.350.0.37
> **Lead:** Jarvis @ `w-jarvis`. **Collaborator:** coder agent @ `dragon-lin` (jwoltje@10.1.10.37:coder0-0).
> Owner of this file: Fleet workstream lead. Does not modify MVP single-writer control-plane files.
## Mission
Turn the proven fleet primitives into a **user-installable, AI-free-configurable fleet product**:
a user runs `mosaic fleet init`, answers a few questions (general / coding / research / hybrid),
gets a recommended set of agents plus one always-on orchestrator wired for chat-ops, and can
operate, mutate, re-create, and observe the fleet — over tmux today and Matrix tomorrow — from
CLI/TUI and (designed-for) the webUI.
**Immediate tangible goal:** the **"Mos"** orchestrator agent running on `w-jarvis`, reachable
in **Discord channel `1517622518662434996`** (server `1112631390438166618`). Once the fleet is
functional, we use the fleet itself to continue the work.
## Requirements
### A. Configure-without-AI CLI
| ID | Requirement |
| --- | ------------------------------------------------------------------------------------------------------------- |
| R1 | `mosaic fleet` command set is functional end-to-end (init/install/start/stop/status/ps/verify + agent verbs). |
| R2 | `mosaic fleet init` is an interactive, **AI-free** CLI wizard. |
| R3 | Init asks the **configuration type**: `general`, `coding`, `research`, `hybrid`, … (extensible). |
| R4 | Based on the answer, the fleet is populated with a **recommended set of agents** (a preset). |
| R5 | **Exactly one main orchestrator agent** is always configured, regardless of type. |
| R10 | A set of **recommended configurations (presets)** ships for easy duplication. |
| R8 | User can **re-create** the fleet when config needs change (idempotent re-init / reconfigure). |
| R17 | Fleet controls are **simple and intuitive**. |
### B. Comms & orchestrator chat-ops
| ID | Requirement |
| --- | --------------------------------------------------------------------------------------------------------------------------------- |
| R6 | Init can wire the orchestrator to a chat connector — **Telegram / Discord / Matrix / Slack** — for command + comms. |
| R7 | Designed with the end-goal of **Matrix comms on a locally-controlled server**. |
| R16 | Fleet supports **tmux AND Matrix** comms, **user-configurable** at init or any time. Not all users want Matrix. |
| R19 | **"Mos" orchestrator on Discord** (`chan 1517622518662434996` / `srv 1112631390438166618`) on `w-jarvis` — the first live target. |
### C. Runtime, health, lifecycle
| ID | Requirement |
| --- | ---------------------------------------------------------------------------------- |
| R9 | Fleet is **mutable by the orchestrator agent** — add/remove agents per need. |
| R13 | Fleet **gracefully handles Pi + Claude harness updates** — keep harnesses current. |
| R14 | The **Pi harness is customized** for proper tool usage, etc. |
| R15 | **Agent heartbeat** properly configured for **Claude AND GPT/Pi** agents. |
### D. Surfaces, testing, docs
| ID | Requirement |
| --- | ----------------------------------------------------------------------------------- |
| R18 | Fleet built so the **webUI can view / monitor / terminate / butt-in** on a session. |
| R11 | Installed and **tested on both `w-jarvis` and `dragon-lin`**. |
| R12 | **Documentation**: how to install, configure, and use the fleet. |
## Architecture / approach
- **Config model:** `roster.yaml` is the source of truth (already exists). Add **presets** (`general`/`coding`/`research`/`hybrid`) as shipped example rosters; `init` selects a preset, always injects the orchestrator, and writes the roster. Re-init = regenerate roster (preserve user/site overrides — mirrors install env-merge from #567).
- **Orchestrator agent:** always present; carries the chat connector config (connector type + target IDs) so it can be commanded over chat. tmux is the substrate; the connector bridges chat ↔ the orchestrator session.
- **Comms layers (R16):** (1) **tmux** inter-agent (`agent-send`, proven) — default, always available. (2) **chat connector** for human↔orchestrator (Discord now; Matrix the strategic target). (3) **Matrix** as the locally-controlled cross-agent bus (future). Connector is pluggable + reconfigurable.
- **Heartbeat (R15):** runtime-agnostic launcher sidecar already covers pi/claude/codex (#584). Refine per-runtime (native HB) with the **custom Pi harness** (R14) + a Claude path.
- **Updates (R13):** `mosaic update` (CLI) + a fleet-aware harness-update step that refreshes pi/claude/codex and re-launches agents safely (drain → update → relaunch via the durable launcher).
- **webUI (R18):** the fleet exposes machine-readable state (`fleet ps --json` already carries tenant/host/heartbeat/managed) + control verbs (start/stop/watch/send); webUI consumes these (control plane rides federation per north star). Ensure a stable JSON contract + a terminate/attach(butt-in) path.
## Phases (incremental, each shippable)
| Phase | Deliverable | Notes |
| --------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------- |
| **F1 Presets + init wizard** | preset rosters (general/coding/research/hybrid) + always-orchestrator + AI-free `fleet init` selecting a preset; re-init idempotent | R1R5, R8, R10, R17 |
| **F2 Connector + Mos-on-Discord** | orchestrator chat-connector config (Discord first) + **Mos live on Discord `1517…`/`1112…`** on w-jarvis | R6, R19, partial R16 |
| **F3 Heartbeat + harness** | HB confirmed for claude + pi/gpt; **custom Pi harness** (tool usage, native HB, model self-report); graceful harness updates | R13, R14, R15 |
| **F4 Matrix + comms toggle** | Matrix connector (local server) + user toggle tmux/Matrix at init/anytime | R7, R16 |
| **F5 Orchestrator-mutable fleet** | orchestrator can add/remove agents at runtime | R9 |
| **F6 webUI hooks** | stable JSON contract + terminate/attach surface for webUI view/monitor/terminate/butt-in | R18 |
| **F7 Test + docs** | install+test on w-jarvis AND dragon-lin; user docs (install/configure/use) | R11, R12 (runs alongside every phase) |
## Work division (proposed — confirm with dragon-lin)
- **Jarvis @ w-jarvis (Lead):** F1 presets+wizard, F2 connector+Mos-on-Discord, F5 mutability, F6 webUI hooks; merge authority + dual-engine reviews; co-testing on w-jarvis.
- **coder @ dragon-lin:** F3 custom Pi harness + harness-update flow (pi/codex-savvy); plus its in-flight constitution P4P6 (P4 installer rework underpins `fleet init`/updates — coordinate the install path). Co-testing on dragon-lin (R11).
- **Shared:** F4 Matrix (whoever has bandwidth); F7 testing/docs continuous.
## Immediate target: Mos on Discord (F2 first slice)
The discord plugin is available (`~/.claude.json`). Path: configure the **orchestrator** as a durable
fleet session running Claude Code with the discord plugin bridged to channel `1517622518662434996`
(server `1112631390438166618`) on w-jarvis, with the existing Discord Bridge Protocol (ack within
~3s, reply via `mcp__discord__reply`, no `AskUserQuestion`). Heartbeat via the launcher sidecar.
## Success criteria
- A non-AI user can `mosaic fleet init`, pick a type, and get a working fleet + orchestrator.
- **Mos answers in Discord `1517…`** on w-jarvis.
- Fleet runs + is observable (`fleet ps`) on **both** w-jarvis and dragon-lin.
- Harness updates handled gracefully; HB healthy for claude + pi/gpt agents.
- Docs let a new operator install/configure/use the fleet.
- Re-init + orchestrator mutation work.
## Assumptions (veto-able)
- `ASSUMPTION:` presets ship as example rosters under the framework (`fleet/examples/*.yaml`), selected by `init`.
- `ASSUMPTION:` chat connectors are pluggable; Discord first (target exists), Matrix is the strategic default later.
- `ASSUMPTION:` "Mos" = a Claude Code orchestrator session with the discord plugin (reuses the documented Discord Bridge Protocol).
- `ASSUMPTION:` per north star, runtimes default to Codex/pi-on-Codex for workers; the orchestrator "Mos" runs Claude Code (in Claude Code, which is allowed).

View File

@@ -1,109 +0,0 @@
# PRD — Fleet Phase 2: Operator Observability
> **Workstream:** W-FLEET under `mvp-20260312` · **Phase:** 2
> **North star:** [docs/fleet/north-star.md](./north-star.md)
> **Source umbrella PRD:** [docs/PRD.md](../PRD.md) (Mosaic Stack v0.1.0)
> **Tracks task:** `fleet-observability-1` — restore operator observability into fleet agent sessions.
## Problem
The durable tmux fleet runs on the isolated `mosaic-factory` socket. That isolation
(which protects the operator's default tmux) makes the fleet **invisible** to default
tooling, and truth is split across three planes no single command joins — systemd
(`systemctl --user`), tmux (`-L mosaic-factory`), and the process tree (`pstree`).
`agent tail` (`capture-pane`) returns **blank for full-screen TUIs**, and `agent send`
confirms only keystroke injection, not acceptance. Net: the operator has near-zero
observability and no safe way to watch a session.
## Goals
1. One command shows the **whole fleet's** real state, joining all three planes.
2. **Liveness is truthful**: healthy = answered a heartbeat, not "pane alive".
3. The operator can **watch** any session read-only without disrupting it.
4. `send` reports **delivered-and-accepted**, not just injected.
5. Every record/address carries **`tenant_id` + `host`** (zero foreclosure for multi-tenant/multi-host).
## Non-goals (this phase)
- No webUI (Phase 5; rides federation for cross-host).
- No `fleetd` daemon or persistent history store.
- No real-runtime swap (Phase 3) — instrument the live **dogfood stub** fleet.
- No cross-host aggregation yet (addressing is host-tagged but queries stay local).
## Functional requirements
| ID | Requirement |
| ---- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| FR-1 | `mosaic fleet ps [--json]` prints one row per roster agent joining: name · tenant · host · runtime · systemd(active/enabled) · pane(alive/dead) · pid · idle · **last-heartbeat age** · **drift** flag (roster runtime ≠ actual pane command) · **boot-enable** warning (active but `UnitFileState=disabled`). |
| FR-2 | **Heartbeat protocol v1** (see below); `dogfood-agent.py` implements the responder. `fleet ps` issues probes (or reads last-seen) and reports health per FR-1. |
| FR-3 | `mosaic agent watch <name>` opens a **read-only** view of the pane (grouped session or `tmux attach -r`) that cannot send keystrokes and does not shrink the agent's window. |
| FR-4 | `mosaic agent attach <name>` remains the **explicit** interactive-takeover path (separate verb, documented as the only one that can type). |
| FR-5 | `mosaic agent send <name> --verify` confirms the message was **accepted** (not left as an unsubmitted draft) and returns non-zero if delivery cannot be verified. |
| FR-6 | All structured output (`--json`) includes `tenant_id` and `host` fields. |
## Heartbeat protocol v1
- **Probe:** operator/`fleet ps` writes a sentinel line to the agent's input or a
well-known per-agent heartbeat file path `~/.config/mosaic/fleet/run/<agent>.hb`.
- **Response:** the runtime updates `<agent>.hb` with `ts=<iso8601> pid=<pid> status=<ok|busy>`
on a fixed interval (default 15s) and on demand when probed.
- **Health rule:** `healthy` if `now - ts <= 3 × interval`; else `stale`; missing file = `unknown`.
- **Contract:** every runtime (dogfood stub now; claude/codex/pi/opencode in Phase 3)
MUST emit the heartbeat. The protocol is file-based so it works for headless stubs and
full-screen TUIs alike (no `capture-pane` dependency).
- `ASSUMPTION:` file-based heartbeat (vs in-pane echo) — chosen because it is TUI-safe and
uid-scoped, fitting per-tenant isolation. Open to an OTEL-span variant in Phase 3 (MVP-X6).
## Acceptance criteria
- `mosaic fleet ps` shows all 5 live sessions on `mosaic-factory` with correct
pane/pid/idle and flags the dogfood **drift** (`canary-pi` runtime=pi but pane runs
`dogfood-agent.py`) and the **boot-enable** gap (active but disabled).
- Killing one agent's pane flips its row to dead/stale within one `interval`.
- `agent watch` shows live output and provably cannot type into the pane; detaching
leaves the agent's window size unchanged.
- `agent send --verify` returns success on an accepting pane and non-zero on a wedged/draft pane.
- Quality gates green: `pnpm typecheck`, `pnpm lint`, `pnpm format:check`, plus
`pnpm --filter @mosaicstack/mosaic test`.
- Independent review passed; dogfood evidence captured against the live fleet.
## Test plan
- Unit/CLI specs in `packages/mosaic/src/commands/fleet.spec.ts` (and a new
`fleet-ps`/`watch`/`send-verify` spec) using the injected `CommandRunner` to assert
exact tmux/systemd command construction and JSON shape (tenant+host present).
- Situational: run against the live `mosaic-factory` fleet; capture `fleet ps` output,
a kill-and-detect cycle, a read-only `watch`, and a `send --verify` pass/fail pair.
## Known limitations
- **Verify heuristic is best-effort:** `agent send --verify` uses a `>` -prefix draft
heuristic that is specific to pi/claude TUIs. Draft detection for codex and opencode
TUIs is best-effort only; those runtimes may not use the same input-line indicator.
- **Pane-change check is the best Phase-2 signal; verify now polls up to a bounded
timeout:** `agent send --verify` captures a BEFORE snapshot, sends the message, then
polls `capture-pane` every ~400 ms up to a configurable total timeout (default ~6 s,
controlled by `--verify-timeout <ms>`). On each poll it runs classifySendResult: if
the pane shows 'accepted' or 'draft' the loop exits immediately; while the result is
'unverifiable' (no pane change yet) it keeps polling. After the timeout with no
definitive result, it fails closed: exit 1 with "no pane change after send". This
eliminates false 'unverifiable' failures for slow/loaded TUIs that were previously
caused by the old fixed 300 ms single-capture. Definitive acceptance ultimately
requires a runtime acknowledgement (Phase-3 heartbeat-ack); the bounded pane-change
poll is the best signal available against an opaque TUI for Phase-2.
- **Blank AFTER capture fails closed:** Full-screen TUIs (claude, codex, opencode, pi)
render blank for `tmux capture-pane`. When the AFTER snapshot is empty, `send --verify`
returns non-zero with an "unverifiable" message rather than silently succeeding. This
is an intentional fail-closed design (FR-5).
- **`agent watch` uses a grouped viewer session:** `tmux attach -r` directly against the
agent session lets the viewer terminal shrink the agent's window. `agent watch` instead
creates a throwaway grouped session (`tmux new-session -d -t '=<agent>' -s
'<agent>-watch-<pid>'`), attaches read-only to that session, and kills it on detach.
The grouped session shares the agent's windows but has independent sizing, so the
agent's window is never affected. `tmux attach` is still interactive and requires
inherited stdio; the `interactiveRunner` handles TTY passthrough.
## Surfaces & parity (MVP-X1)
CLI lands this phase. TUI surface follows in the `packages/mosaic` wizard; webUI in
Phase 5 via federation. PRD records the parity debt explicitly so it is not lost.

View File

@@ -1,27 +0,0 @@
# Tasks — W-FLEET (Fleet) Phase 2: Observability
> Workstream task file for the Fleet. Single-writer: Fleet workstream lead (orchestrator).
> Workers read but never modify. This is **not** the MVP rollup (`docs/TASKS.md`) — a
> rollup row is proposed to the MVP orchestrator, not written here.
>
> Mission: `mvp-20260312` · PRD: [docs/fleet/PRD.md](./PRD.md) · North star: [docs/fleet/north-star.md](./north-star.md)
> Status: `not-started` | `in-progress` | `done` | `blocked` | `failed`
| id | status | description | depends_on | agent | pr | notes |
| ------------- | ----------- | ------------------------------------------------------------------------------------------------------------------ | --------------------- | ----------- | --- | ----------------------------------------------------------------------------------------------------------------------------- |
| FLEET-OBS-000 | done | Plan: north-star + Phase-2 PRD + workstream scaffolding | — | lead | — | persisted 2026-06-20 on `feat/fleet-observability` |
| FLEET-OBS-001 | done | Heartbeat protocol v1 spec finalized in PRD + framework doc | FLEET-OBS-000 | lead | — | file-based `~/.config/mosaic/fleet/run/<agent>.hb`; spec in PRD |
| FLEET-OBS-002 | in-progress | Implement heartbeat responder in `dogfood-agent.py` | FLEET-OBS-001 | fleet-coder | — | dispatched to ad-hoc `mosaic yolo` fleet agent (dogfood) |
| FLEET-OBS-003 | done | `mosaic fleet ps` — join systemd+tmux+proc+idle+heartbeat; tenant+host tagged; drift + boot-enable flags; `--json` | FLEET-OBS-001 | worker | — | commit ab47831; LIVE-verified on mosaic-factory; caught canary-pi DRIFT + BOOT-ENABLE. Polish: idleSeconds parse returns null |
| FLEET-OBS-004 | done | `mosaic agent watch <name>` — read-only join (no resize, no keystrokes) | FLEET-OBS-000 | worker | — | `attach -r`; verb wired |
| FLEET-OBS-005 | done | `mosaic agent send --verify` — delivery/acceptance receipt | FLEET-OBS-000 | worker | — | --verify flag; draft-heuristic verify |
| FLEET-OBS-006 | done | CLI specs for ps/watch/send-verify (tenant+host shape, command construction) | FLEET-OBS-003,004,005 | worker | — | 62 tests green (31 new); re-verified by lead |
| FLEET-OBS-007 | not-started | Framework doc: fleet observability guide + verbs | FLEET-OBS-003,004,005 | lead | — | `docs/guides/` or `framework/tools/.../README` |
| FLEET-OBS-008 | not-started | Independent review + dogfood verification on live fleet | FLEET-OBS-002..007 | reviewer | — | author ≠ reviewer; capture evidence in scratchpad |
| FLEET-OBS-009 | not-started | Open PR → green CI (queue guard) → squash-merge → close `fleet-observability-1` | FLEET-OBS-008 | lead | — | trunk merge; no direct push to main |
## Proposed MVP rollup row (for the MVP orchestrator — not written by this workstream)
```
| W-FLEET | in-progress | Fleet (agent-session execution layer) | Phase 2/5 | docs/fleet/TASKS.md | observability dogfooded on live stub fleet; control plane rides federation (W1) |
```

View File

@@ -1,133 +0,0 @@
# Mosaic Fleet — North Star
> **Workstream:** W-FLEET (Fleet) under mission `mvp-20260312`
> **Umbrella:** [docs/MISSION-MANIFEST.md](../MISSION-MANIFEST.md) · [docs/PRD.md](../PRD.md) (Mosaic Stack v0.1.0)
> **Status:** doctrine — authored 2026-06-20. Owner of this file: Fleet workstream lead.
> This document does **not** modify the MVP rollup; a rollup row is proposed, not written here.
## Vision
A **customizable, multi-tenant fleet of always-on AI agents** — each defined by role,
materialized as a durable, joinable runtime session, coordinated by the proven
orchestrator/worker model, and observable end-to-end across hosts. Coding today;
finance, analytics, research as roster entries tomorrow — same primitives, different
roster. The fleet is the **agent-session execution layer** of the Mosaic Stack MVP:
the thing federation makes reachable across hosts and the webUI/TUI/CLI make visible.
The USC tmux PoC (durable sessions + `agent-send` comms) proved the model. This
workstream makes it an official, observable, multi-tenant Mosaic Stack capability.
## The Fleet as means of production (bootstrapping)
The Fleet has a **dual role**, and that is the point:
- **As product** — a multi-tenant agent-fleet capability of Mosaic Stack (this workstream).
- **As means of production** — the orchestrator/worker fleet that _actually builds the
entire MVP_ (federation W1, webUI, TUI, CLI, and the Fleet itself).
We are **building the system that builds the system.** Every other MVP workstream is
delivered _by_ the fleet, so fleet observability and control are not merely product
features — they are the **operational floor of the whole delivery effort**. If we cannot
see and steer the agents, we cannot trust what they ship. This is why Phase 2
(observability) leads: it is the instrument panel for the factory, dogfooded on the live
fleet that is, recursively, building Mosaic Stack.
The discipline that makes great power safe is the same gate chain the fleet enforces:
independent review before merge, green CI, honest completion, decide-and-inform cadence,
and no irreversible action without authority. The bootstrap is only as trustworthy as
those gates.
## Alignment with MVP cross-cutting requirements
The Fleet inherits — does not re-invent — the MVP's hard requirements:
| MVP req | What it means for the Fleet |
| ----------------------------- | ----------------------------------------------------------------------------------------------------------------------- |
| MVP-X1 three-surface parity | fleet observability/control reachable via **CLI + TUI + webUI** (CLI first; webUI is required for parity, not optional) |
| MVP-X2 multi-tenant isolation | one tenant = one **Linux uid** (own `systemd --user`, socket, `~/.config/mosaic`); no cross-tenant leakage |
| MVP-X3 auth (BetterAuth/SSO) | operator→fleet and cross-host views are auth-gated through the platform's existing auth |
| MVP-X4 quality gates | `pnpm typecheck`/`lint`/`format:check` green before any push |
| MVP-X5 federated topology | cross-host fleet visibility rides the **federation** boundary (W1), not a bespoke broker |
| MVP-X6 OTEL tracing | heartbeats, sends, and lifecycle events emit spans; `traceparent` crosses the federation boundary |
| MVP-X7 trunk merge | branch from `main`, squash-merge via PR, never push to `main` |
## The stack — where every concern lives
One **definition** is the source of truth; the **session** is how it runs.
| Layer | Owner | Phase-2 reality | Destination |
| -------------------------------- | ------------------------------------------------------------------------------------------- | ------------------------------------------------------ | ------------------------------------------------------- |
| **Definition + identity + auth** | gateway / `mosaic-as` (scoped tokens, #541) | `roster.yaml` (tenant-tagged) | one definition; `mosaic agent --new` materializes it |
| **Tenancy boundary** | **Linux uid per tenant** (linger, own `systemd --user`, own socket, own `~/.config/mosaic`) | one tenant: `jarvis` = tenant zero | uid-per-tenant; federation aggregates across hosts |
| **Runtime** | per-tenant tmux session on isolated socket | dogfood stub sessions (live now on `mosaic-factory`) | claude/codex/pi/opencode TUIs |
| **Liveness** | **heartbeat protocol** every runtime answers | protocol defined + dogfood stub answers it | all runtimes answer; "healthy" ≠ "pane alive" |
| **Observation** | read-only `watch` (native tmux) + `pipe-pane` stream | CLI `watch`/`ps`; explicit opt-in `attach` for control | + auth-gated webUI streams |
| **Control plane** | **federation** across hosts × tenants | records already carry `tenant_id` + `host` | federated gateways expose fleet state; webUI in Phase 5 |
## Operating model (inherited, not reinvented)
The AI-guide law stands: one accountable **orchestrator**, isolated **workers** that
stop at PR-open, the serialized **gate chain** (independent review → green CI →
diff-sanity → squash-merge → verify), **decide-and-inform** cadence, and a durable
**board** so missions survive session death. The Fleet is the infrastructure _under_
this model. See `mosaicstack-aiguide` whitepapers 01 (inter-agent comms) and 03
(orchestration model) for the rationale.
## Invariants — "maximal vision, incremental delivery, zero foreclosure"
Every artifact, starting Phase 2, MUST:
1. Carry **`tenant_id` + `host`** in schema and message addressing — even with one of each today.
2. Treat **isolation socket ≠ invisibility** — anything isolated is surfaced by one command.
3. Define **healthy = answered a heartbeat within N seconds**, never just "pane alive".
4. Make **observation read-only by default**; control is an explicit, separate, opt-in verb.
## Observation model
| Verb | Behavior |
| ----------------------------------- | -------------------------------------------------------------------------------------------------- |
| `mosaic fleet ps` | one table joining systemd + tmux + process + idle + last-heartbeat, with drift + boot-enable flags |
| `mosaic agent watch <name>` | **read-only** join (grouped session / `-r`), no resize tyranny, no keystrokes |
| `mosaic agent attach <name>` | explicit interactive takeover (the only path that can type) |
| `mosaic agent send <name> --verify` | confirms message **accepted**, not merely keystroke-injected |
> Why the current PoC blocks observation: sessions live on the isolated `mosaic-factory`
> socket (invisible to default `tmux ls`), the only sanctioned read is `capture-pane`
> (blank for full-screen TUIs), and `attach` is read-write + resizes the session. The
> verbs above restore "join and observe" safely.
## Phased roadmap
| Phase | Outcome | Status |
| ---------------------- | -------------------------------------------------------------------------------------------------------------------------------------------- | ------- |
| 01 | tmux PoC, hardening, published CLI v0.0.34 (#565#568) | ✅ done |
| **2 — Observability** | `fleet ps` (host+tenant aware join), heartbeat protocol + dogfood stub answers it, `agent watch` (read-only), `agent send --verify` receipts | ▶ now |
| 3 — Real runtimes | claude/codex/pi/opencode answer heartbeat; **hybrid lifecycle** (core always-on: orchestrator+reviewer; ephemeral workers per lane) | planned |
| 4 — Unified definition | one agent schema in gateway; `mosaic agent --new` → materialized per-tenant session; uid-tenant provisioning | planned |
| 5 — Control plane | federation-backed cross-host × cross-tenant fleet view; **webUI** (surface chosen then) for MVP-X1 parity | planned |
## Decisions of record (2026-06-20, with Jason)
- Agent model: **config defines, session runs** (gateway = definition/identity/auth; tmux = runtime).
- Tenancy: **multi-tenant from the start**; isolation = **per-tenant Linux uid**.
- Health: **heartbeat required** (dogfood stub implements the protocol now).
- Lifecycle: **hybrid** — core always-on + ephemeral workers per lane.
- Observation: **read-only default, opt-in takeover**.
- Multi-host: **designed-for from day one**; control plane **rides federation (W1)**.
- Delivery: **CLI-first now**, dogfood against the live stub fleet; webUI deferred to Phase 5.
- Runtimes: fleet agents default to **Codex / pi-on-Codex**; **Claude is reserved for Claude
Code only** (avoid alternate-harness API pricing). Validated durable recipe:
`mosaic yolo pi --model openai-codex/gpt-5.5:high`. Durable detached launch requires the
runtime-bin on PATH (baked into the pane command) + boot-survival (`enable` + linger),
which `fleet init` should automate.
## Assumptions (veto-able)
- `ASSUMPTION:` first-class runtimes = claude, codex, pi, opencode; a "role" (analyst,
finance, researcher) = persona + skills + tools on top of a runtime, shipped as a
starter role library in the framework.
- `ASSUMPTION:` the cross-host control plane is the **federation** layer (W1), not a
separate `fleetd` daemon.
- `ASSUMPTION:` Fleet is workstream **W-FLEET** under `mvp-20260312`; a rollup row in
`docs/TASKS.md` and a workstream declaration in `MISSION-MANIFEST.md` are proposed to
the MVP orchestrator, not written by this workstream.

View File

@@ -1,100 +0,0 @@
# Scratchpad — Fleet Phase 2: Observability (W-FLEET)
> Append-only. Mission `mvp-20260312` / workstream W-FLEET.
> Lead: Jarvis (Claude) at `W-jarvis:mos-claude-18`. Coordinating with `jwoltje@dragon-lin:coder0-0`.
## Mission prompt (2026-06-20)
Establish the north star for the Mosaic Fleet feature and prepare Phase-2 observability
for delivery. The USC tmux PoC is the proven base. Jason granted lead authority:
"The fleet is a great way to actually build the MVP — we are building the system that
builds the system." Dogfood actual agent construction + ad-hoc deployment; coordinate
with a second agent on `dragon-lin`.
## Decisions of record (with Jason, 2026-06-20)
- Agent model: config defines, session runs (gateway = definition/identity/auth; tmux = runtime).
- Tenancy: multi-tenant from the start; isolation = per-tenant Linux uid.
- Health: heartbeat required; dogfood stub implements protocol now.
- Lifecycle: hybrid (core always-on + ephemeral workers).
- Observation: read-only default, opt-in takeover.
- Multi-host: designed-for day one; control plane rides federation (W1), not a bespoke broker.
- Delivery: CLI-first, dogfood on the live stub fleet; webUI deferred to Phase 5.
- Fleet is dual-role: product AND means of production (bootstrapping the MVP).
- Code review = **dual-engine**: Claude **and** gpt-5.5/Codex, run together (Jason: the
combination produces the best results). Launch reviewers via `mosaic yolo pi` / `codex`
(proven path) or `~/.config/mosaic/tools/codex/codex-code-review.sh`. Applies to all
code-review gates incl. FLEET-OBS-008. Per Jason 2026-06-20.
- Worktree discipline: do fleet work in `~/src/mosaicstack-stack-worktrees/<branch>`, NOT
the shared main checkout — concurrent processes mutate `main` there (learned 2026-06-20).
## Environment facts (verified 2026-06-20)
- Fleet is live on `W-jarvis` (uid 1000, `jarvis`, `Linger=yes`) on tmux socket
`mosaic-factory`: `_holder`, `canary-pi`, `dogfood-coder`, `dogfood-orchestrator`,
`dogfood-reviewer`. All panes run `~/.config/mosaic/fleet/dogfood-agent.py` (stub),
including `canary-pi` (roster says runtime=pi → **drift**).
- Holder + `mosaic-agent@*` units are `active (exited)` but `UnitFileState=disabled`
(reboot loses fleet → boot-enable gap to surface).
- Observation blocked by: isolated socket (hidden from default `tmux ls`), `capture-pane`
blank for TUIs, `attach` being read-write + resizing.
- Second agent: `jwoltje@dragon-lin`, session `coder0-0` (group `coder0`), running `node`,
default socket. ssh forward reach confirmed.
## Governance / collision-safety
- `mosaicstack-stack` has active mission `mvp-20260312` with single-writer locks on
`docs/MISSION-MANIFEST.md`, `docs/TASKS.md`, `docs/scratchpads/mvp-20260312.md`.
- This workstream touches NONE of those. All Fleet docs scoped under `docs/fleet/` +
this scratchpad. Rollup row proposed, not written.
## Session log
- 2026-06-20: Researched AI guide + fleet code + live state. Established north star with
Jason (8 forks decided). Branched `feat/fleet-observability`. Persisted
`docs/fleet/{north-star.md,PRD.md,TASKS.md}` + this scratchpad. Next: establish comms
with dragon-lin coder, commit docs, begin Phase-2 delivery (heartbeat + `fleet ps`).
- 2026-06-20 (session 2): Built Phase-2 CLI via worker (commit ab47831): `fleet ps`,
`agent watch`, `agent send --verify`, 62 tests. LIVE-verified `fleet ps` on
mosaic-factory — correctly flagged canary-pi DRIFT + BOOT-ENABLE, tenant_id+host in JSON.
Heartbeat responder added to dogfood-agent.py (FLEET-OBS-002) — `fleet ps` HB now
`healthy` for all 4 agents.
- Coordination: dual-engine-reviewed (Claude+Codex) and merged framework PRs #572
(sanitization gate) + #575 (CONSTITUTION extraction) as Lead. Codex caught an Alpine
blocker on #572 (refuted by CI); Claude caught a CI-breaking format failure on #575.
- **FINDINGS (north-star / Phase-3 blockers):**
1. Ad-hoc `mosaic yolo {codex,pi}` via `start-agent-session.sh` DIE immediately in a
detached tmux pane (codex: "stdin is not a terminal"; pi: same). Only the python stub
survives. => Real runtimes have NEVER run durably in the fleet. Launch path (PATH/TTY
in the detached shell) must be fixed before Phase-3 real-runtime swap. `fleet ps`
caught both dead panes instantly (tool validated).
2. `MOSAIC_AGENT_NAME` (set in systemd EnvironmentFile) is NOT propagated into tmux's
global env, so agents defaulted to `unknown`. Worked around in dogfood-agent.py via
tmux session-name fallback; the systemd/tmux env handoff needs a real fix.
- Next: rebase on merged main, open Phase-2 PR, dual-engine review, merge, close
`fleet-observability-1`. Defer launch-path + env-propagation fixes to Phase 3.
- 2026-06-21 (session 3): Phase-2 PR #579 merged (3 dual-engine rounds hardened
verify+watch). Then closed the launch-path question with Jason's input — CORRECTING
earlier findings:
- The ad-hoc launch deaths were NOT a fundamental TTY blocker: (a) codex was a stale
version (Jason updated it); (b) pi was misconfigured to Claude auth (Jason removed it;
default is now Codex). The REAL durable-launch bug is **PATH**: the detached tmux
launch shell is login+non-interactive, so it misses `~/.npm-global/bin` (added only in
`~/.bashrc`) -> `mosaic: command not found` (127) -> pane dies. tmux panes inherit the
tmux _server_ env, so PATH must be baked into the pane command.
- **Durable real-agent recipe (validated live on gpt-5.5, Claude-free):**
`mosaic yolo pi --model openai-codex/gpt-5.5:high` — pi tolerates detached tmux; a raw
interactive TUI (codex CLI) exits without an attached client. Status line confirmed
`(openai-codex) gpt-5.5 • high`.
- PATH fix landed in `start-agent-session.sh` (commit 32efc13, branch
feat/fleet-launch-path): derive runtime-bin prefix (MOSAIC_RUNTIME_BIN | npm prefix |
~/.npm-global/bin | ~/.local/bin), bake `export PATH=...; exec <cmd>` into the pane;
`exec` also fixes the drift false-positive. Live-tested under stripped PATH -> durable.
- Boot-survival: Jason ran `systemctl --user enable` (+ linger). TODO: auto-enable in
**fleet init** so operators never have to remember it (agentic-enhancement cycle).
- Future custom Pi harness build: pi cannot self-report its model (track
runtime/model/effort as fleet metadata); drift detection should recognize `node` as
pi's pane command (a node-wrapped pane can currently read as drift).
- Findings recorded in AI Guide playbooks/tmux-fleet.md (aiguide PR #7, merged).
- Policy: avoid Claude outside Claude Code (API pricing for alt-harness use) — fleet
runtimes default to Codex / pi-on-Codex; Claude stays in Claude Code only.

View File

@@ -1,29 +0,0 @@
# P6 — Docs, compliance matrix, alpha tag (constitution capstone)
- **Issue:** #606 · **Branch:** `feat/p6-docs-compliance-alpha` · **Lineage:** #542
- **Requirements:** R9 (resident line-count ceiling) + R10 (CONTRIBUTING + compliance matrix + aiguide) + alpha tag
## Delivered (in-repo)
- `framework/CONTRIBUTING.md` — layer model, operator-hygiene/PII prohibition, dedup rule, resident
budget, **dual-installer parity rule**, adding-a-harness, re-contamination rule, **harness×gate
compliance matrix** (hook-parity gap marked ⚠️ tracked-v2), known-limitations (§9 residuals), PR checklist.
- `framework/tools/quality/scripts/check-resident-budget.sh` — line-count ceiling over framework-owned
resident files (CONSTITUTION + AGENTS + each runtime/\*/RUNTIME.md); `--self-test`; replaces the crude
inline ci.yml loop. Wired blocking in `.woodpecker/ci.yml`.
- Composer unit test (R9) already runs via `pnpm test`; `verify-sanitized.sh` (P1) already wired.
## Verification
- Sanitization gate green (CONTRIBUTING is operator-neutral). Resident-budget self-test + real run green.
- prettier clean. Current resident counts: CONSTITUTION 96, AGENTS 83, RUNTIME max 75 — all < ceiling.
## Remaining
- [ ] `aiguide` reconcile (separate repo `~/src/aiguide` / mosaicstack/aiguide) — consistency pass vs Constitution.
- [ ] Alpha tag `mosaic-vX.Y.Z-alpha` — propose version; Lead cuts after full DoD §8 green + all phases merged.
## Notes
- Alpha DoD (DESIGN §8): all phases P0P6 merged + CI green. P5 (#605) pending merge after 0.0.38 publish.
- Hook parity (codex/opencode/pi) = tracked v2 gap, documented in the matrix, not closed here.

View File

@@ -1,185 +0,0 @@
# Contributing to the Mosaic Framework
The Mosaic framework is the open-source agent-operating layer that deploys to
`~/.config/mosaic/`. It is designed to be **forked and customized** — but the
shared core must stay operator-neutral, deduplicated, and upgrade-safe. This
guide is the contract for changing framework-owned files.
> Governance model and layer rationale: `constitution/LAYER-MODEL.md` (source-only).
> Requirements & phase history: `docs/design/framework-constitution/`.
---
## 1. The layer model (where does my change go?)
| Layer | What | Owner | On upgrade | File(s) |
| ------ | ------------------------------------------------------------- | ---------------- | --------------------------------------- | -------------------------------------------- |
| **L0** | Constitution — the non-negotiable law (hard gates) | Framework | **Overwritten** | `CONSTITUTION.md` |
| **L1** | Standards & guides — how to do the work well | Framework | Overwritten; user delta → `*.local.md` | `STANDARDS.md`, `guides/*` |
| **L2** | Persona (SOUL) — agent name, tone, role | User (init) | **Never overwritten** | `SOUL.md` (+ optional `SOUL.local.md`) |
| **L3** | Operator (USER) — human identity, prefs, policy | User (init) | **Never overwritten** | `USER.md` (+ optional `USER.local.md`) |
| **L4** | Project / runtime mechanism — per-repo deltas; harness wiring | Repo / framework | Project user-owned; runtime overwritten | `<repo>/AGENTS.md`, `runtime/<h>/RUNTIME.md` |
**The one sentence a user can rely on:** edit `SOUL.md` / `USER.md` and the
`.local.md` overlays — they survive every upgrade. To change framework behavior,
add a `.local.md` overlay; never edit a framework-owned file in place.
---
## 2. Operator hygiene (PII / secrets prohibition) — **blocking**
Framework-owned files ship publicly. They **must not** contain:
- Operator or personal identity (names, handles, pronouns, accessibility notes).
- Private `$HOME` paths, private hostnames, or domains.
- Secrets, tokens, or credentials (use `~/.config/mosaic/credentials.json`; the
hook URL soft-degrades via `${OPENBRAIN_URL}`).
This is enforced by `tools/quality/scripts/verify-sanitized.sh`, wired **blocking**
in CI (`.woodpecker/ci.yml`). It runs two rule classes: structural (private-`$HOME`
defaults, dead paths, unrendered tokens) and a labeled current-contaminant denylist.
Run it locally before pushing:
```bash
bash packages/mosaic/framework/tools/quality/scripts/verify-sanitized.sh
```
Operator-specific behavior belongs in **your** `SOUL.md`/`USER.md`/`*.local.md`,
never in the shared core. (The "framework-PR firewall" in `CONSTITUTION.md` §4
states this as law for agents opening framework PRs.)
---
## 3. Dedup rule — one source, everyone references it
Hard gates live in **`CONSTITUTION.md` (L0) only**. `AGENTS.md`, `STANDARDS.md`,
and every `runtime/<h>/RUNTIME.md` **reference** the law — they never restate it.
Restating a gate is a defect: it creates two sources that drift. If you find a
gate duplicated outside L0, delete the copy and point to L0.
`AGENTS.md` is a thin dispatcher (load order + guide router + the tier-aware
self-load). Keep it that way; new procedure goes in `guides/*` (on-demand), not
in the resident core.
---
## 4. Resident line-count ceiling — **blocking**
The framework-owned files injected by value (`CONSTITUTION.md`, `AGENTS.md`, each
`runtime/<h>/RUNTIME.md`) are budgeted by **line count** — never by word count
(a word cap forces paraphrasing the law, the exact drift vector we removed).
```bash
bash packages/mosaic/framework/tools/quality/scripts/check-resident-budget.sh
```
Wired blocking in CI. Gate **wording** stays intact; if a file legitimately needs
more lines, raise its ceiling in the script deliberately (in the same PR, with
rationale). The per-harness _total_ resident prompt (which also sums the user's
`SOUL.md`/`USER.md`) is a `mosaic doctor` runtime advisory — CI cannot see user
files, so it is out of CI scope by design (DESIGN §7).
---
## 5. Dual-installer parity rule
Two installers seed and migrate `~/.config/mosaic/`:
- **`framework/install.sh`** (bash) — the canonical installer.
- **`packages/mosaic/src/config/file-adapter.ts`** (TS) — the wizard path.
**Any change to seed lists, overwrite/preserve semantics, or migration MUST land
in BOTH**, validated by the **shared fixture suite**:
- `framework/tools/quality/scripts/test-install-migration.sh` (bash matrix)
- `packages/mosaic/src/config/file-adapter.test.ts` (vitest)
Both assert the same behavior: framework-owned files overwrite (backup-once to
`*.pre-constitution.bak`); user-seeded files seed-if-absent; `SOUL.md`/`USER.md`/
`*.local.md`/`credentials` are preserved. A change in one installer without the
other (and its fixtures) is incomplete.
---
## 6. Adding a harness adapter
A harness (runtime) is wired by:
1. `runtime/<h>/RUNTIME.md`**mechanism only** (subagent syntax, hook/MCP wiring,
injection method). No restated gates (see §3).
2. Launcher emission in `src/commands/launch.ts` — how the composed contract reaches
the harness (system-prompt append vs. instructions file). Add the harness to the
`RuntimeName` union and the runtime-path map.
3. `mosaic compose-contract <harness>` works automatically once the runtime path
exists (it composes base + `*.local.md` overlays for that harness).
Then add a row to the compliance matrix (§8) and mark which gates are mechanical
vs. resident-only for the new harness.
---
## 7. Re-contamination rule
A green sanitization gate is not permanent. Before every PR:
- Do not reintroduce operator identity, private paths, or secrets (§2).
- Do not copy a gate out of L0 (§3).
- Do not add an unrendered template token or a dead path to a shipped file.
If `verify-sanitized.sh` goes red, that diff **is** your worklist — fix it, don't
suppress it.
---
## 8. Harness × gate compliance matrix
How each gate is enforced per harness. **Mechanical** = a hook/CI check the agent
cannot bypass. **Resident** = injected contract prose (strong, but not a hard stop).
**CI** = repo-side, harness-independent.
| Gate / mechanism | Claude | Codex | OpenCode | Pi |
| --------------------------------------------- | ----------- | ---------------- | ---------------- | ---------------- |
| Contract injection (resident-by-value) | append SP | instructions | `AGENTS.md` | append SP |
| Operator overlays (`*.local`, composed) | ✅ | ✅ | ✅ | ✅ |
| Bare-launch self-load (Tier-3, read L0) | ✅ | ✅ | ✅ | ✅ |
| Sanitization (no PII) — `verify-sanitized` | CI ✅ | CI ✅ | CI ✅ | CI ✅ |
| Resident budget ceiling | CI ✅ | CI ✅ | CI ✅ | CI ✅ |
| Migration parity (5-fixture, both installers) | CI ✅ | CI ✅ | CI ✅ | CI ✅ |
| `no-memory-write` (PreToolUse hook) | **mech ✅** | resident-only ⚠️ | resident-only ⚠️ | resident-only ⚠️ |
| QA / typecheck (PostToolUse hooks) | **mech ✅** | resident-only ⚠️ | resident-only ⚠️ | resident-only ⚠️ |
| Native heartbeat (fleet `ps` model/status) | sidecar | sidecar | sidecar | **native ✅** |
⚠️ **Hook-parity gap (tracked, v2):** the mechanical PreToolUse/PostToolUse hooks
exist for Claude Code only. On Codex/OpenCode/Pi those gates are currently enforced
by the resident contract + CI, not by a per-tool hook. Closing hook parity is a
**v2** item, not part of this alpha.
---
## 9. Known limitations (accepted residual risks)
These are accepted with rationale (DESIGN §9); they are documented, not bugs:
- **Bare-launch overlays are base-only.** A harness started without `mosaic` never
ran the composer, so `*.local.md` overlays are not applied. Mitigated by the
unconditional Tier-3 self-load + the `mosaic doctor` nudge in `AGENTS.md`; not
eliminated. Relaunch via `mosaic <harness>` to pick up overlays.
- **Bare-launch drift is undetected by `mosaic doctor`** (the launcher never ran).
- **Codex/OpenCode/Pi hook parity** is a tracked v2 gap (§8).
- **Live-launch cross-harness verification** is v2; the alpha verifies the composer
by unit test (per-tier anchor + Tier-3 byte-equality), not a live launch.
**Deferred to v2 (explicit):** `constitution/` deploy directory; capability JSON
adapters; 3-way merge; `policy/*.md` composition; per-layer version stamps as a
migration driver.
---
## 10. PR checklist
- [ ] No operator identity / private paths / secrets (`verify-sanitized.sh` green).
- [ ] No gate restated outside `CONSTITUTION.md` (§3).
- [ ] Resident budget green (`check-resident-budget.sh`).
- [ ] Seed/migration changes landed in **both** installers + shared fixtures (§5).
- [ ] New harness → compliance-matrix row updated (§8).
- [ ] `prettier --check` + `pnpm lint` + `pnpm typecheck` + `pnpm test` green.

View File

@@ -1,32 +0,0 @@
version: 1
transport: tmux
tmux:
socket_name: mosaic-factory
holder_session: _holder
defaults:
working_directory: ~
runtimes:
claude:
reset_command: /clear
pi:
reset_command: /new
agents:
- name: orchestrator
runtime: claude
class: orchestrator
persistent_persona: true
- name: coder0
runtime: pi
class: implementer
model_hint: openai-codex/gpt-5.5:high
reset_between_tasks: true
- name: coder1
runtime: pi
class: implementer
model_hint: openai-codex/gpt-5.5:high
reset_between_tasks: true
- name: reviewer
runtime: pi
class: reviewer
model_hint: openai-codex/gpt-5.5:high
reset_between_tasks: true

View File

@@ -1,22 +0,0 @@
version: 1
transport: tmux
tmux:
socket_name: mosaic-factory
holder_session: _holder
defaults:
working_directory: ~
runtimes:
claude:
reset_command: /clear
pi:
reset_command: /new
agents:
- name: orchestrator
runtime: claude
class: orchestrator
persistent_persona: true
- name: generalist
runtime: pi
class: worker
model_hint: openai-codex/gpt-5.5:high
reset_between_tasks: true

View File

@@ -1,32 +0,0 @@
version: 1
transport: tmux
tmux:
socket_name: mosaic-factory
holder_session: _holder
defaults:
working_directory: ~
runtimes:
claude:
reset_command: /clear
pi:
reset_command: /new
agents:
- name: orchestrator
runtime: claude
class: orchestrator
persistent_persona: true
- name: coder0
runtime: pi
class: implementer
model_hint: openai-codex/gpt-5.5:high
reset_between_tasks: true
- name: researcher0
runtime: pi
class: researcher
model_hint: openai-codex/gpt-5.5:high
reset_between_tasks: true
- name: reviewer
runtime: pi
class: reviewer
model_hint: openai-codex/gpt-5.5:high
reset_between_tasks: true

View File

@@ -1,32 +0,0 @@
version: 1
transport: tmux
tmux:
socket_name: mosaic-factory
holder_session: _holder
defaults:
working_directory: ~
runtimes:
claude:
reset_command: /clear
pi:
reset_command: /new
agents:
- name: orchestrator
runtime: claude
class: orchestrator
persistent_persona: true
- name: researcher0
runtime: pi
class: researcher
model_hint: openai-codex/gpt-5.5:high
reset_between_tasks: true
- name: researcher1
runtime: pi
class: researcher
model_hint: openai-codex/gpt-5.5:high
reset_between_tasks: true
- name: analyst
runtime: pi
class: analyst
model_hint: openai-codex/gpt-5.5:high
reset_between_tasks: true

View File

@@ -19,23 +19,13 @@ SOURCE_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
TARGET_DIR="${MOSAIC_HOME:-$HOME/.config/mosaic}" TARGET_DIR="${MOSAIC_HOME:-$HOME/.config/mosaic}"
INSTALL_MODE="${MOSAIC_INSTALL_MODE:-prompt}" INSTALL_MODE="${MOSAIC_INSTALL_MODE:-prompt}"
# Files/dirs protected from rsync --delete during sync. NOTE: framework-owned # Files/dirs preserved across upgrades (never overwritten).
# entries (CONSTITUTION/AGENTS/STANDARDS) ARE re-applied afterward by
# reconcile_framework_files (overwrite + backup-once); the rest stay user-owned.
# User-created content in these paths survives rsync --delete. # User-created content in these paths survives rsync --delete.
PRESERVE_PATHS=("CONSTITUTION.md" "AGENTS.md" "SOUL.md" "USER.md" "TOOLS.md" "STANDARDS.md" "memory" "sources" "credentials") PRESERVE_PATHS=("AGENTS.md" "SOUL.md" "USER.md" "TOOLS.md" "STANDARDS.md" "memory" "sources" "credentials")
# 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_SEEDED files are written once on first install, then owned by the user.
# Both lists are APPEND-FRIENDLY — add a new shipped framework file here and to the
# matching list in packages/mosaic/src/config/file-adapter.ts.
FRAMEWORK_OWNED=("CONSTITUTION.md" "AGENTS.md" "STANDARDS.md")
USER_SEEDED=("TOOLS.md")
# Current framework schema version — bump this when the layout changes. # Current framework schema version — bump this when the layout changes.
# The migration system uses this to run upgrade steps. # The migration system uses this to run upgrade steps.
FRAMEWORK_VERSION=3 FRAMEWORK_VERSION=2
# ─── colours ────────────────────────────────────────────────────────────────── # ─── colours ──────────────────────────────────────────────────────────────────
if [[ -t 1 ]]; then if [[ -t 1 ]]; then
@@ -50,47 +40,6 @@ warn() { echo -e " ${YELLOW}⚠${RESET} $1" >&2; }
fail() { echo -e " ${RED}${RESET} $1" >&2; } fail() { echo -e " ${RED}${RESET} $1" >&2; }
step() { echo -e "\n${BOLD}$1${RESET}"; } step() { echo -e "\n${BOLD}$1${RESET}"; }
# ─── snapshot / restore (crash safety for upgrades) ──────────────────────────
SNAPSHOT_DIR=""
make_snapshot() {
is_existing_install || return 0
SNAPSHOT_DIR="$(mktemp -d "${TMPDIR:-/tmp}/mosaic-snapshot-XXXXXX")"
cp -a "$TARGET_DIR/." "$SNAPSHOT_DIR/" 2>/dev/null || true
}
restore_snapshot() {
[[ -n "$SNAPSHOT_DIR" && -d "$SNAPSHOT_DIR" ]] || return 0
fail "Install interrupted/failed — restoring previous state from snapshot"
rm -rf "$TARGET_DIR"; mkdir -p "$TARGET_DIR"
cp -a "$SNAPSHOT_DIR/." "$TARGET_DIR/" 2>/dev/null || true
}
cleanup_snapshot() { [[ -n "$SNAPSHOT_DIR" && -d "$SNAPSHOT_DIR" ]] && rm -rf "$SNAPSHOT_DIR"; SNAPSHOT_DIR=""; }
# Reconcile contract files after sync: framework-owned overwrite (backup-once),
# user-seeded seed-if-absent.
reconcile_framework_files() {
local defaults="$TARGET_DIR/defaults" f
[[ -d "$defaults" ]] || return 0
for f in "${FRAMEWORK_OWNED[@]}"; do
[[ -f "$defaults/$f" ]] || continue
# Already current — skip to avoid mtime churn.
if [[ -f "$TARGET_DIR/$f" ]] && cmp -s "$TARGET_DIR/$f" "$defaults/$f"; then
continue
fi
if [[ -f "$TARGET_DIR/$f" && ! -f "$TARGET_DIR/${f}.pre-constitution.bak" ]]; then
cp "$TARGET_DIR/$f" "$TARGET_DIR/${f}.pre-constitution.bak"
warn "$f is now framework-owned and was updated; your previous copy is saved as ${f}.pre-constitution.bak — re-apply intended changes as a .local overlay or policy/ file (see CONSTITUTION.md / constitution/LAYER-MODEL.md)."
fi
cp "$defaults/$f" "$TARGET_DIR/$f"
done
for f in "${USER_SEEDED[@]}"; do
[[ -f "$defaults/$f" ]] || continue
if [[ ! -f "$TARGET_DIR/$f" ]]; then
cp "$defaults/$f" "$TARGET_DIR/$f"
ok "Seeded $f from defaults"
fi
done
}
# ─── helpers ────────────────────────────────────────────────────────────────── # ─── helpers ──────────────────────────────────────────────────────────────────
is_existing_install() { is_existing_install() {
@@ -164,14 +113,11 @@ sync_framework() {
fi fi
if command -v rsync >/dev/null 2>&1; then if command -v rsync >/dev/null 2>&1; then
local rsync_args=(-a --delete --exclude ".git" --exclude ".framework-version" --exclude "*.pre-constitution.bak") local rsync_args=(-a --delete --exclude ".git" --exclude ".framework-version")
if [[ "$INSTALL_MODE" == "keep" ]]; then if [[ "$INSTALL_MODE" == "keep" ]]; then
# Anchor to the transfer root (leading /) so we preserve the TOP-LEVEL
# ~/.config/mosaic/<file> without also excluding defaults/<file> from sync
# (reconcile_framework_files needs the freshly-synced defaults/ copies).
for path in "${PRESERVE_PATHS[@]}"; do for path in "${PRESERVE_PATHS[@]}"; do
rsync_args+=(--exclude "/$path") rsync_args+=(--exclude "$path")
done done
fi fi
@@ -191,7 +137,7 @@ sync_framework() {
done done
fi fi
find "$TARGET_DIR" -mindepth 1 -maxdepth 1 ! -name ".git" ! -name ".framework-version" ! -name "*.pre-constitution.bak" -exec rm -rf {} + find "$TARGET_DIR" -mindepth 1 -maxdepth 1 ! -name ".git" ! -name ".framework-version" -exec rm -rf {} +
cp -R "$SOURCE_DIR"/. "$TARGET_DIR"/ cp -R "$SOURCE_DIR"/. "$TARGET_DIR"/
rm -rf "$TARGET_DIR/.git" rm -rf "$TARGET_DIR/.git"
@@ -249,15 +195,10 @@ run_migrations() {
fi fi
fi fi
# ── Migration: v2 → v3 (Constitution split) ─────────────────────────────── # ── Future migrations go here ──────────────────────────────────────────────
# CONSTITUTION.md / AGENTS.md / STANDARDS.md become framework-owned (overwritten # if [[ "$from_version" -lt 3 ]]; then
# on upgrade). reconcile_framework_files() has already run before this point: it # ...
# backed up any user-edited copy to <file>.pre-constitution.bak and installed the # fi
# new framework version. Nothing further to do here — the advisory was emitted at
# reconcile time. (STANDARDS.local.md composition lands with the overlay composer.)
if [[ "$from_version" -lt 3 ]]; then
ok "Migrated to the Constitution layout (framework-owned CONSTITUTION/AGENTS/STANDARDS)"
fi
} }
# ═══════════════════════════════════════════════════════════════════════════════ # ═══════════════════════════════════════════════════════════════════════════════
@@ -275,25 +216,29 @@ else
ok "Install mode: overwrite" ok "Install mode: overwrite"
fi fi
# Snapshot before any destructive file operation; restore on interrupt/failure.
make_snapshot
trap 'restore_snapshot' ERR INT TERM
sync_framework sync_framework
# Ensure persistent directories exist # Ensure persistent directories exist
mkdir -p "$TARGET_DIR/memory" mkdir -p "$TARGET_DIR/memory"
mkdir -p "$TARGET_DIR/credentials" mkdir -p "$TARGET_DIR/credentials"
# Reconcile contract files from defaults/ into the framework root: framework-owned # Seed defaults — copy framework contract files from defaults/ to framework
# files (CONSTITUTION/AGENTS/STANDARDS) are overwritten every upgrade (a divergent # root if not already present. These ship with sensible defaults but must
# copy is backed up once); user-seeded files (TOOLS) are written on first install only. # never be overwritten once the user has customized them.
# #
# This list must match the framework-contract whitelist in # This list must match the framework-contract whitelist in
# packages/mosaic/src/config/file-adapter.ts (FileConfigAdapter.syncFramework). # packages/mosaic/src/config/file-adapter.ts (FileConfigAdapter.syncFramework).
# SOUL.md and USER.md are intentionally NOT seeded here — they are generated # SOUL.md and USER.md are intentionally NOT seeded here — they are generated
# by `mosaic init` from templates with user-supplied values. # by `mosaic init` from templates with user-supplied values.
reconcile_framework_files DEFAULTS_DIR="$TARGET_DIR/defaults"
if [[ -d "$DEFAULTS_DIR" ]]; then
for default_file in CONSTITUTION.md AGENTS.md STANDARDS.md TOOLS.md; do
if [[ -f "$DEFAULTS_DIR/$default_file" ]] && [[ ! -f "$TARGET_DIR/$default_file" ]]; then
cp "$DEFAULTS_DIR/$default_file" "$TARGET_DIR/$default_file"
ok "Seeded $default_file from defaults"
fi
done
fi
# Ensure tool scripts are executable # Ensure tool scripts are executable
find "$TARGET_DIR/tools" -name "*.sh" -exec chmod +x {} + 2>/dev/null || true find "$TARGET_DIR/tools" -name "*.sh" -exec chmod +x {} + 2>/dev/null || true
@@ -304,18 +249,6 @@ ok "Framework synced to $TARGET_DIR"
# Run migrations before post-install (migrations may remove old bin/ etc.) # Run migrations before post-install (migrations may remove old bin/ etc.)
run_migrations run_migrations
# File-system phase complete and consistent — clear the restore trap.
trap - ERR INT TERM
cleanup_snapshot
# Testability / minimal-install hook: stop after the file-system phase, before any
# environment-touching post-install steps (runtime linking, MCP setup, skills, doctor).
if [[ "${MOSAIC_SYNC_ONLY:-0}" == "1" ]]; then
write_framework_version
ok "Sync-only mode: file phase complete"
exit 0
fi
step "Post-install tasks" step "Post-install tasks"
SCRIPTS="$TARGET_DIR/tools/_scripts" SCRIPTS="$TARGET_DIR/tools/_scripts"

View File

@@ -9,16 +9,8 @@
* 4. Memory routing — remind agent to use ~/.config/mosaic/memory/ * 4. Memory routing — remind agent to use ~/.config/mosaic/memory/
*/ */
import type { ExtensionAPI, ExtensionContext } from '@earendil-works/pi-coding-agent'; import type { ExtensionAPI } from '@mariozechner/pi-coding-agent';
import { Type } from 'typebox'; import { existsSync, readFileSync, writeFileSync, unlinkSync, mkdirSync } from 'node:fs';
import {
existsSync,
readFileSync,
writeFileSync,
unlinkSync,
mkdirSync,
renameSync,
} from 'node:fs';
import { join, basename } from 'node:path'; import { join, basename } from 'node:path';
import { homedir } from 'node:os'; import { homedir } from 'node:os';
import { execSync, spawnSync } from 'node:child_process'; import { execSync, spawnSync } from 'node:child_process';
@@ -33,57 +25,6 @@ const MOSAIC_HOME = process.env['MOSAIC_HOME'] ?? join(homedir(), '.config', 'mo
// Helpers // Helpers
// --------------------------------------------------------------------------- // ---------------------------------------------------------------------------
// ---------------------------------------------------------------------------
// Native heartbeat (fleet R14/R15)
// ---------------------------------------------------------------------------
// When this agent runs under the Mosaic fleet (MOSAIC_AGENT_NAME set), the
// extension writes its OWN heartbeat in the same .hb contract `fleet ps` reads
// (ts/pid/status[/model]) and touches a `.hb.native` precedence marker so the
// shell sidecar defers. Native HB knows the real turn state (busy/ok), so it is
// more accurate than the pane-PID-only sidecar fallback.
const HB_AGENT_NAME = process.env['MOSAIC_AGENT_NAME'] ?? '';
const HB_RUN_DIR = process.env['MOSAIC_HEARTBEAT_RUN_DIR'] ?? join(MOSAIC_HOME, 'fleet', 'run');
const HB_INTERVAL_MS = (() => {
const s = Number.parseInt(process.env['MOSAIC_HEARTBEAT_INTERVAL'] ?? '', 10);
return Number.isFinite(s) && s > 0 ? s * 1000 : 15_000;
})();
function nativeHbEnabled(): boolean {
return HB_AGENT_NAME.length > 0;
}
function readModelId(ctx: ExtensionContext): string | null {
const m = ctx.model as unknown as { id?: string; name?: string } | undefined;
return m?.id ?? m?.name ?? null;
}
function writeNativeHeartbeat(status: 'ok' | 'busy', model: string | null): void {
if (!nativeHbEnabled()) return;
try {
mkdirSync(HB_RUN_DIR, { recursive: true });
const hb = join(HB_RUN_DIR, `${HB_AGENT_NAME}.hb`);
const lines = [`ts=${nowIso()}`, `pid=${process.pid}`, `status=${status}`];
if (model) lines.push(`model=${model}`);
const tmp = `${hb}.tmp.${process.pid}`;
writeFileSync(tmp, lines.join('\n') + '\n');
renameSync(tmp, hb); // atomic replace — fleet ps never reads a partial file
// Precedence marker: tells the shell sidecar that native HB is authoritative.
writeFileSync(join(HB_RUN_DIR, `${HB_AGENT_NAME}.hb.native`), nowIso() + '\n');
} catch {
// Best-effort: never let heartbeat I/O disrupt the Pi session.
}
}
function clearNativeMarker(): void {
if (!nativeHbEnabled()) return;
try {
const m = join(HB_RUN_DIR, `${HB_AGENT_NAME}.hb.native`);
if (existsSync(m)) unlinkSync(m); // native stopping — let the sidecar take over
} catch {
/* ignore */
}
}
function safeRead(filePath: string): string | null { function safeRead(filePath: string): string | null {
try { try {
return readFileSync(filePath, 'utf-8'); return readFileSync(filePath, 'utf-8');
@@ -246,9 +187,6 @@ function buildMissionSummary(cwd: string, mission: ActiveMission): string {
export default function register(pi: ExtensionAPI) { export default function register(pi: ExtensionAPI) {
let sessionCwd = process.cwd(); let sessionCwd = process.cwd();
let hbStatus: 'ok' | 'busy' = 'ok';
let hbModel: string | null = null;
let hbTimer: ReturnType<typeof setInterval> | null = null;
// ── Session Start ───────────────────────────────────────────────────── // ── Session Start ─────────────────────────────────────────────────────
pi.on('session_start', async (_event, ctx) => { pi.on('session_start', async (_event, ctx) => {
@@ -269,39 +207,10 @@ export default function register(pi: ExtensionAPI) {
} else { } else {
ctx.ui.notify('Mosaic framework loaded', 'info'); ctx.ui.notify('Mosaic framework loaded', 'info');
} }
// Native heartbeat: write immediately, then on an interval. Idle = 'ok';
// turn_start/turn_end flip the status so `fleet ps` reflects real activity.
if (nativeHbEnabled()) {
hbModel = readModelId(ctx);
writeNativeHeartbeat('ok', hbModel);
hbTimer = setInterval(() => writeNativeHeartbeat(hbStatus, hbModel), HB_INTERVAL_MS);
if (typeof hbTimer.unref === 'function') hbTimer.unref();
}
}); });
// ── Turn lifecycle → accurate busy/ok heartbeat ─────────────────────── // ── Session End ───────────────────────────────────────────────────────
pi.on('turn_start', async (_event, ctx) => { pi.on('session_end', async (_event, _ctx) => {
hbStatus = 'busy';
hbModel = readModelId(ctx) ?? hbModel;
writeNativeHeartbeat('busy', hbModel);
});
pi.on('turn_end', async (_event, ctx) => {
hbStatus = 'ok';
hbModel = readModelId(ctx) ?? hbModel;
writeNativeHeartbeat('ok', hbModel);
});
// ── Session Shutdown ──────────────────────────────────────────────────
// (The pi API event is 'session_shutdown'; the prior 'session_end' handler
// never fired — fixed here so repo hooks + lock cleanup actually run.)
pi.on('session_shutdown', async (_event, _ctx) => {
if (hbTimer) {
clearInterval(hbTimer);
hbTimer = null;
}
clearNativeMarker();
// Run repo session-end hook // Run repo session-end hook
runRepoHook(sessionCwd, 'session-end'); runRepoHook(sessionCwd, 'session-end');
@@ -343,32 +252,4 @@ export default function register(pi: ExtensionAPI) {
} }
}, },
}); });
// ── Register mosaic_mission_status tool (model-callable) ──────────────
// R14 "proper tool usage": give the agent a first-class tool to load its
// active Mosaic mission, milestone progress, task counts, and latest
// scratchpad — so it self-orients on in-flight work before planning,
// instead of shelling out or guessing. Mirrors the /mosaic-status command
// but returns the summary as tool output the LLM can read.
pi.registerTool({
name: 'mosaic_mission_status',
label: 'Mosaic Mission Status',
description:
'Return the active Mosaic mission, milestone progress, task counts, and latest scratchpad for the current project. Returns a note when no mission is active.',
promptSnippet: 'Read the active Mosaic mission + task state for the current project',
promptGuidelines: [
'Use mosaic_mission_status at the start of a session or task to load the active mission, milestone progress, and open tasks before planning work.',
],
parameters: Type.Object({}),
async execute(_toolCallId, _params, _signal, _onUpdate, _ctx) {
const mission = detectMission(sessionCwd);
const text = mission
? buildMissionSummary(sessionCwd, mission)
: 'No active Mosaic mission in this project.';
return {
content: [{ type: 'text', text }],
details: mission ? { ...mission } : { active: false },
};
},
});
} }

View File

@@ -274,13 +274,6 @@ detect_existing_config
echo "[mosaic-init] Generating SOUL.md — agent identity contract" echo "[mosaic-init] Generating SOUL.md — agent identity contract"
echo "" echo ""
# Fail-closed persona: in non-interactive mode the agent NAME must be supplied
# explicitly (--name) — never silently ship an agent named "Assistant".
if [[ $NON_INTERACTIVE -eq 1 && -z "$AGENT_NAME" ]]; then
echo "[mosaic-init] ERROR: --name (agent name) is required in non-interactive mode." >&2
exit 1
fi
prompt_if_empty AGENT_NAME "What name should agents use" "Assistant" prompt_if_empty AGENT_NAME "What name should agents use" "Assistant"
prompt_if_empty ROLE_DESCRIPTION "Agent role description" "execution partner and visibility engine" prompt_if_empty ROLE_DESCRIPTION "Agent role description" "execution partner and visibility engine"

View File

@@ -6,8 +6,6 @@ MOSAIC_TMUX_SOCKET=${MOSAIC_TMUX_SOCKET:-mosaic-factory}
MOSAIC_AGENT_RUNTIME=${MOSAIC_AGENT_RUNTIME:-pi} MOSAIC_AGENT_RUNTIME=${MOSAIC_AGENT_RUNTIME:-pi}
MOSAIC_AGENT_WORKDIR=${MOSAIC_AGENT_WORKDIR:-$HOME} MOSAIC_AGENT_WORKDIR=${MOSAIC_AGENT_WORKDIR:-$HOME}
MOSAIC_AGENT_COMMAND=${MOSAIC_AGENT_COMMAND:-} MOSAIC_AGENT_COMMAND=${MOSAIC_AGENT_COMMAND:-}
MOSAIC_HEARTBEAT_RUN_DIR=${MOSAIC_HEARTBEAT_RUN_DIR:-${MOSAIC_HOME:-$HOME/.config/mosaic}/fleet/run}
MOSAIC_HEARTBEAT_INTERVAL=${MOSAIC_HEARTBEAT_INTERVAL:-15}
if [ -z "$AGENT_NAME" ]; then if [ -z "$AGENT_NAME" ]; then
echo "ERROR: agent name argument or MOSAIC_AGENT_NAME is required" >&2 echo "ERROR: agent name argument or MOSAIC_AGENT_NAME is required" >&2
@@ -28,132 +26,5 @@ if [ -z "$MOSAIC_AGENT_COMMAND" ]; then
MOSAIC_AGENT_COMMAND="mosaic yolo $MOSAIC_AGENT_RUNTIME" MOSAIC_AGENT_COMMAND="mosaic yolo $MOSAIC_AGENT_RUNTIME"
fi fi
# ── Derive a runtime-bin PATH prefix ─────────────────────────────────────────
# Precedence:
# 1. $MOSAIC_RUNTIME_BIN (explicit override)
# 2. $(npm config get prefix)/bin (if npm is on PATH)
# 3. Fallbacks: $HOME/.npm-global/bin and $HOME/.local/bin
#
# Only directories that already exist are included. The prefix is baked into
# the pane command regardless of what the LAUNCHER process's $PATH contains,
# because the tmux pane inherits the tmux SERVER environment (not this script's
# environment). A dir on the launcher's PATH may be absent from the server PATH,
# so every existing candidate must always be included. Dedup within the
# constructed prefix avoids listing the same dir twice.
_build_runtime_bin_prefix() {
local candidates=()
if [ -n "${MOSAIC_RUNTIME_BIN:-}" ]; then
candidates+=("$MOSAIC_RUNTIME_BIN")
fi
if command -v npm >/dev/null 2>&1; then
local npm_prefix
npm_prefix=$(npm config get prefix 2>/dev/null) || true
if [ -n "$npm_prefix" ]; then
candidates+=("${npm_prefix}/bin")
fi
fi
candidates+=("$HOME/.npm-global/bin")
candidates+=("$HOME/.local/bin")
local prefix=""
for dir in "${candidates[@]}"; do
[ -d "$dir" ] || continue
if [ -z "$prefix" ]; then
prefix="$dir"
else
case ":${prefix}:" in
*":${dir}:"*) ;; # already in our prefix — skip
*) prefix="${prefix}:${dir}" ;;
esac
fi
done
printf '%s' "$prefix"
}
MOSAIC_RUNTIME_BIN_PREFIX=$(_build_runtime_bin_prefix)
# ── Build the pane command ────────────────────────────────────────────────────
# The pane command must:
# - Export the augmented PATH so the runtime binary is found.
# - exec the agent command so the runtime is the pane's foreground process
# (makes `fleet ps` pane_current_command check reliable; no DRIFT false-positive).
#
# Quoting strategy: single-quote the inner shell snippet so that variable
# references in MOSAIC_AGENT_COMMAND are NOT expanded here — they expand inside
# the pane shell. However, MOSAIC_RUNTIME_BIN_PREFIX and PATH must be expanded
# NOW (in this script) because the pane shell inherits the tmux server
# environment, not this script's env.
#
# We build the snippet as a double-quoted here-string embedded in a printf call
# to avoid nested quoting problems.
#
# MOSAIC_AGENT_NAME must also be exported INTO the pane: panes inherit the tmux
# server environment (not this script's, and not the systemd unit's), so the
# name would otherwise be empty in-pane and the runtime's native heartbeat
# (which gates on MOSAIC_AGENT_NAME) would never fire. %q-quote it so it is a
# safe single bash token regardless of the name's characters.
AGENT_NAME_Q=$(printf '%q' "$AGENT_NAME")
if [ -n "$MOSAIC_RUNTIME_BIN_PREFIX" ]; then
PANE_SHELL_SNIPPET="export MOSAIC_AGENT_NAME=${AGENT_NAME_Q}; export PATH=\"${MOSAIC_RUNTIME_BIN_PREFIX}:\${PATH}\"; exec ${MOSAIC_AGENT_COMMAND}"
else
PANE_SHELL_SNIPPET="export MOSAIC_AGENT_NAME=${AGENT_NAME_Q}; exec ${MOSAIC_AGENT_COMMAND}"
fi
mkdir -p "$MOSAIC_AGENT_WORKDIR" mkdir -p "$MOSAIC_AGENT_WORKDIR"
exec tmux -L "$MOSAIC_TMUX_SOCKET" new-session -d -s "$AGENT_NAME" -c "$MOSAIC_AGENT_WORKDIR" "$MOSAIC_AGENT_COMMAND"
# ── Launch the tmux session (no exec — we continue to wire the heartbeat) ────
tmux -L "$MOSAIC_TMUX_SOCKET" new-session -d -s "$AGENT_NAME" -c "$MOSAIC_AGENT_WORKDIR" \
bash -c "$PANE_SHELL_SNIPPET"
# ── Resolve the pane PID (retry briefly to let the session initialise) ────────
PANE_PID=""
for _retry in 1 2 3 4 5; do
PANE_PID=$(tmux -L "$MOSAIC_TMUX_SOCKET" list-panes \
-t "=${AGENT_NAME}:0.0" -F '#{pane_pid}' 2>/dev/null || true)
[ -n "$PANE_PID" ] && break
sleep 0.2
done
# ── Spawn the heartbeat sidecar (detached, best-effort) ──────────────────────
# The sidecar writes ~/.config/mosaic/fleet/run/<AGENT>.hb atomically while the
# pane process is alive, then exits so the file goes stale (fleet ps shows stale
# then PANE=dead). It is runtime-agnostic: it only cares about the pane PID.
_start_heartbeat_sidecar() {
local agent="$1"
local pane_pid="$2"
local run_dir="$3"
local interval="$4"
local hb_file="${run_dir}/${agent}.hb"
mkdir -p "$run_dir"
# Write the sidecar as a self-contained bash one-liner so it carries no
# references to any variables from this script's environment.
local sidecar_script
sidecar_script=$(printf \
'hb=%q; pid=%q; iv=%q; mkdir -p "$(dirname "$hb")"; while kill -0 "$pid" 2>/dev/null; do nat="$hb.native"; if [ -f "$nat" ] && [ "$(( $(date +%%s) - $(stat -c %%Y "$nat" 2>/dev/null || echo 0) ))" -lt "$(( iv * 2 ))" ]; then sleep "$iv"; continue; fi; tmp="$hb.tmp.$$"; printf "ts=%%s\npid=%%s\nstatus=ok\n" "$(date +%%Y-%%m-%%dT%%H:%%M:%%S%%z)" "$pid" > "$tmp" && mv "$tmp" "$hb"; sleep "$iv"; done' \
"$hb_file" "$pane_pid" "$interval")
# setsid + disown ensures the sidecar survives this script exiting.
# stderr/stdout go to /dev/null; failures are non-fatal.
if command -v setsid >/dev/null 2>&1; then
setsid bash -c "$sidecar_script" </dev/null >/dev/null 2>&1 &
else
bash -c "$sidecar_script" </dev/null >/dev/null 2>&1 &
fi
disown $! 2>/dev/null || true
}
if [ -n "$PANE_PID" ]; then
# Guard: do not let sidecar startup failures abort the launcher (set -e).
_start_heartbeat_sidecar "$AGENT_NAME" "$PANE_PID" \
"$MOSAIC_HEARTBEAT_RUN_DIR" "$MOSAIC_HEARTBEAT_INTERVAL" || \
echo "WARNING: heartbeat sidecar could not be started for $AGENT_NAME" >&2
else
echo "WARNING: could not resolve pane PID for $AGENT_NAME — heartbeat sidecar not started" >&2
fi

View File

@@ -6,43 +6,22 @@ START="$SCRIPT_DIR/start-agent-session.sh"
SOCKET="mosaic-agent-test-$RANDOM-$$" SOCKET="mosaic-agent-test-$RANDOM-$$"
AGENT="agent-$RANDOM" AGENT="agent-$RANDOM"
WORKDIR=$(mktemp -d) WORKDIR=$(mktemp -d)
trap 'tmux -L "$SOCKET" kill-server >/dev/null 2>&1 || true; rm -rf "$WORKDIR"' EXIT
# Keep a single cleanup trap that accumulates resources.
CLEANUP_DIRS=("$WORKDIR")
CLEANUP_SOCKETS=("$SOCKET")
trap '_cleanup' EXIT
_cleanup() {
for s in "${CLEANUP_SOCKETS[@]:-}"; do
tmux -L "$s" kill-server >/dev/null 2>&1 || true
done
for d in "${CLEANUP_DIRS[@]:-}"; do
rm -rf "$d"
done
}
fail() { fail() {
echo "FAIL: $*" >&2 echo "FAIL: $*" >&2
exit 1 exit 1
} }
# ── Test 1: basic session creation with workdir check ─────────────────────────
MOSAIC_TMUX_SOCKET="$SOCKET" \ MOSAIC_TMUX_SOCKET="$SOCKET" \
MOSAIC_AGENT_WORKDIR="$WORKDIR" \ MOSAIC_AGENT_WORKDIR="$WORKDIR" \
MOSAIC_AGENT_COMMAND='bash --noprofile --norc -i' \ MOSAIC_AGENT_COMMAND='bash --noprofile --norc -i' \
"$START" "$AGENT" "$START" "$AGENT"
tmux -L "$SOCKET" has-session -t "=$AGENT:0.0" || fail "agent session was not created" tmux -L "$SOCKET" has-session -t "=$AGENT:0.0" || fail "agent session was not created"
# Retry: pane_current_path briefly reflects the tmux server's cwd until the pane
# process establishes its own cwd (the -c start dir). Poll until it settles.
actual_dir=""
for _ in $(seq 1 30); do
actual_dir=$(tmux -L "$SOCKET" display-message -p -t "=$AGENT:0.0" '#{pane_current_path}') actual_dir=$(tmux -L "$SOCKET" display-message -p -t "=$AGENT:0.0" '#{pane_current_path}')
[ "$actual_dir" = "$WORKDIR" ] && break [ "$actual_dir" = "$WORKDIR" ] || fail "agent workdir mismatch: $actual_dir"
sleep 0.1
done
[ "$actual_dir" = "$WORKDIR" ] || fail "agent workdir mismatch: $actual_dir (expected $WORKDIR)"
# ── Test 2: idempotency (duplicate start prints 'already running') ─────────────
MOSAIC_TMUX_SOCKET="$SOCKET" \ MOSAIC_TMUX_SOCKET="$SOCKET" \
MOSAIC_AGENT_WORKDIR="$WORKDIR" \ MOSAIC_AGENT_WORKDIR="$WORKDIR" \
MOSAIC_AGENT_COMMAND='bash --noprofile --norc -i' \ MOSAIC_AGENT_COMMAND='bash --noprofile --norc -i' \
@@ -50,310 +29,4 @@ MOSAIC_AGENT_COMMAND='bash --noprofile --norc -i' \
grep -qF 'already running' /tmp/mosaic-start-agent-idempotent.out || fail "duplicate start was not idempotent" grep -qF 'already running' /tmp/mosaic-start-agent-idempotent.out || fail "duplicate start was not idempotent"
# ── Test 3: runtime-bin PATH prefix is baked into the pane command ────────────
#
# We capture the command the script would hand to tmux by injecting a fake
# 'tmux' shim into PATH. The shim:
# - Intercepts 'new-session' calls and records its arguments to a file.
# - For 'has-session' calls, exits 1 (session does not exist) so the script
# proceeds to launch instead of printing "already running".
# - For 'list-panes' calls, returns empty so PANE_PID stays unset and the
# heartbeat sidecar is NOT spawned (heartbeat is not the focus of this test;
# test 6 and 7 cover that path). This prevents any real-filesystem side
# effects or leaked background processes.
# - For all other subcommands, exits 0.
#
# Assertions:
# a) 'export PATH=' with the synthetic MOSAIC_RUNTIME_BIN prefix appears.
# b) 'exec' appears so the runtime replaces the wrapper shell.
# c) MOSAIC_AGENT_COMMAND with flags is forwarded intact.
FAKE_BIN=$(mktemp -d)
FAKE_RUNTIME_BIN=$(mktemp -d)
TMUX_ARGS_FILE=$(mktemp)
HB_RUN_DIR3=$(mktemp -d)
CLEANUP_DIRS+=("$FAKE_BIN" "$FAKE_RUNTIME_BIN" "$HB_RUN_DIR3")
# Write the fake tmux shim (uses only positional args, no sourced vars).
cat > "$FAKE_BIN/tmux" <<SHIM
#!/usr/bin/env bash
# Fake tmux: record new-session args; report has-session as missing.
subcmd="\$3" # argv: tmux -L <socket> <subcmd> ...
if [ "\$subcmd" = "has-session" ]; then
exit 1 # session not found → script will attempt new-session
fi
if [ "\$subcmd" = "new-session" ]; then
printf '%s\n' "\$@" > "$TMUX_ARGS_FILE"
exit 0
fi
if [ "\$subcmd" = "list-panes" ]; then
# Return empty: no sidecar spawned (heartbeat is not the focus of this test).
echo ""
exit 0
fi
exit 0
SHIM
chmod +x "$FAKE_BIN/tmux"
SOCKET3="mosaic-agent-test3-$RANDOM-$$"
AGENT3="agent3-$RANDOM"
WORKDIR3=$(mktemp -d)
CLEANUP_DIRS+=("$WORKDIR3")
PATH="$FAKE_BIN:$PATH" \
MOSAIC_TMUX_SOCKET="$SOCKET3" \
MOSAIC_AGENT_WORKDIR="$WORKDIR3" \
MOSAIC_AGENT_RUNTIME="pi" \
MOSAIC_RUNTIME_BIN="$FAKE_RUNTIME_BIN" \
MOSAIC_AGENT_COMMAND="mosaic yolo pi --model openai-codex/gpt-5.5:high" \
MOSAIC_HEARTBEAT_RUN_DIR="$HB_RUN_DIR3" \
"$START" "$AGENT3"
all_args=$(cat "$TMUX_ARGS_FILE" 2>/dev/null || true)
rm -f "$TMUX_ARGS_FILE"
echo "--- captured tmux new-session args ---"
echo "$all_args"
echo "--- end args ---"
# a) PATH prefix containing FAKE_RUNTIME_BIN must appear.
echo "$all_args" | grep -qF "export PATH=" || fail "pane command does not export PATH"
echo "$all_args" | grep -qF "$FAKE_RUNTIME_BIN" || fail "pane command does not include MOSAIC_RUNTIME_BIN in PATH prefix"
# b) exec must appear so the runtime replaces the wrapper shell.
echo "$all_args" | grep -qF "exec " || fail "pane command does not use exec"
# c) Full MOSAIC_AGENT_COMMAND (with flags) must be forwarded.
echo "$all_args" | grep -qF "mosaic yolo pi --model openai-codex/gpt-5.5:high" || \
fail "pane command does not forward MOSAIC_AGENT_COMMAND with flags intact"
# ── Test 4: when no extra runtime-bin dirs exist, exec still appears ───────────
TMUX_ARGS_FILE2=$(mktemp)
FAKE_BIN2=$(mktemp -d)
HB_RUN_DIR4=$(mktemp -d)
CLEANUP_DIRS+=("$FAKE_BIN2" "$HB_RUN_DIR4")
cat > "$FAKE_BIN2/tmux" <<SHIM2
#!/usr/bin/env bash
subcmd="\$3"
if [ "\$subcmd" = "has-session" ]; then exit 1; fi
if [ "\$subcmd" = "new-session" ]; then
printf '%s\n' "\$@" > "$TMUX_ARGS_FILE2"
exit 0
fi
if [ "\$subcmd" = "list-panes" ]; then
# Return empty: no sidecar spawned (heartbeat is not the focus of this test).
echo ""
exit 0
fi
exit 0
SHIM2
chmod +x "$FAKE_BIN2/tmux"
SOCKET4="mosaic-agent-test4-$RANDOM-$$"
AGENT4="agent4-$RANDOM"
WORKDIR4=$(mktemp -d)
CLEANUP_DIRS+=("$WORKDIR4")
# MOSAIC_RUNTIME_BIN points to a non-existent dir so prefix will be empty;
# .npm-global/bin and .local/bin may or may not exist but we just want exec.
PATH="$FAKE_BIN2:$PATH" \
MOSAIC_TMUX_SOCKET="$SOCKET4" \
MOSAIC_AGENT_WORKDIR="$WORKDIR4" \
MOSAIC_AGENT_RUNTIME="pi" \
MOSAIC_RUNTIME_BIN="/nonexistent-dir-$$" \
MOSAIC_AGENT_COMMAND="mosaic yolo pi" \
MOSAIC_HEARTBEAT_RUN_DIR="$HB_RUN_DIR4" \
"$START" "$AGENT4"
all_args4=$(cat "$TMUX_ARGS_FILE2" 2>/dev/null || true)
rm -f "$TMUX_ARGS_FILE2"
rm -rf "$WORKDIR4"
echo "$all_args4" | grep -qF "exec " || fail "pane command (no prefix dirs) does not use exec"
echo "$all_args4" | grep -qF "mosaic yolo pi" || fail "pane command does not include agent command when no prefix"
# ── Test 5: candidate dir already in LAUNCHER $PATH is still baked into pane ──
#
# Regression guard for the bug where _build_runtime_bin_prefix() used to skip
# a candidate because it was already present in the launcher process's $PATH.
# That check was wrong: the pane inherits the tmux SERVER environment, not the
# launcher's env. Even if a dir is on the launcher's PATH it must always be
# baked into the pane's PATH export.
#
# We prove this by setting PATH to include FAKE_RUNTIME_BIN5 (the candidate),
# then asserting the generated new-session command still exports it.
TMUX_ARGS_FILE5=$(mktemp)
FAKE_BIN5=$(mktemp -d)
FAKE_RUNTIME_BIN5=$(mktemp -d) # this dir IS on the launcher's PATH below
HB_RUN_DIR5=$(mktemp -d)
CLEANUP_DIRS+=("$FAKE_BIN5" "$FAKE_RUNTIME_BIN5" "$HB_RUN_DIR5")
cat > "$FAKE_BIN5/tmux" <<SHIM5
#!/usr/bin/env bash
subcmd="\$3"
if [ "\$subcmd" = "has-session" ]; then exit 1; fi
if [ "\$subcmd" = "new-session" ]; then
printf '%s\n' "\$@" > "$TMUX_ARGS_FILE5"
exit 0
fi
if [ "\$subcmd" = "list-panes" ]; then
# Return empty: no sidecar spawned (heartbeat is not the focus of this test).
echo ""
exit 0
fi
exit 0
SHIM5
chmod +x "$FAKE_BIN5/tmux"
SOCKET5="mosaic-agent-test5-$RANDOM-$$"
AGENT5="agent5-$RANDOM"
WORKDIR5=$(mktemp -d)
CLEANUP_DIRS+=("$WORKDIR5")
CLEANUP_SOCKETS+=("$SOCKET5")
# FAKE_RUNTIME_BIN5 is deliberately placed on the LAUNCHER PATH so that the
# old (buggy) code would have skipped it. The correct code must still include
# it in the pane PATH export.
PATH="$FAKE_BIN5:$FAKE_RUNTIME_BIN5:$PATH" \
MOSAIC_TMUX_SOCKET="$SOCKET5" \
MOSAIC_AGENT_WORKDIR="$WORKDIR5" \
MOSAIC_AGENT_RUNTIME="pi" \
MOSAIC_RUNTIME_BIN="$FAKE_RUNTIME_BIN5" \
MOSAIC_AGENT_COMMAND="mosaic yolo pi" \
MOSAIC_HEARTBEAT_RUN_DIR="$HB_RUN_DIR5" \
"$START" "$AGENT5"
all_args5=$(cat "$TMUX_ARGS_FILE5" 2>/dev/null || true)
rm -f "$TMUX_ARGS_FILE5"
rm -rf "$WORKDIR5"
echo "--- test 5: launcher-PATH candidate must still appear in pane export ---"
echo "$all_args5"
echo "--- end test 5 args ---"
echo "$all_args5" | grep -qF "export PATH=" || \
fail "test5: pane command does not export PATH when candidate is on launcher PATH"
echo "$all_args5" | grep -qF "$FAKE_RUNTIME_BIN5" || \
fail "test5: candidate dir (already on launcher PATH) was NOT baked into pane PATH — regression"
# ── Test 6: heartbeat sidecar — pane PID resolved + .hb file written ──────────
#
# Uses a real tmux session (same socket as test 1 which already has $AGENT) so
# list-panes returns a real pane PID. We override MOSAIC_HEARTBEAT_RUN_DIR to
# a temp dir and set a 1-second interval, then wait up to 3 s for the .hb file
# to appear and check its content.
HB_RUN_DIR=$(mktemp -d)
CLEANUP_DIRS+=("$HB_RUN_DIR")
# Re-use the session+agent created in Test 1 (still alive on $SOCKET / $AGENT).
# We need to invoke the script for a NEW agent on the same socket to exercise
# the heartbeat path with a real pane PID.
AGENT6="agent6-$RANDOM"
MOSAIC_TMUX_SOCKET="$SOCKET" \
MOSAIC_AGENT_WORKDIR="$WORKDIR" \
MOSAIC_AGENT_COMMAND='bash --noprofile --norc -i' \
MOSAIC_HEARTBEAT_RUN_DIR="$HB_RUN_DIR" \
MOSAIC_HEARTBEAT_INTERVAL="1" \
"$START" "$AGENT6"
HB_FILE="$HB_RUN_DIR/${AGENT6}.hb"
# Wait up to 5 seconds for the heartbeat file to appear.
_waited=0
until [ -f "$HB_FILE" ] || [ "$_waited" -ge 5 ]; do
sleep 0.5
_waited=$((_waited + 1))
done
[ -f "$HB_FILE" ] || fail "test6: heartbeat file not written at $HB_FILE within 5s"
hb_content=$(cat "$HB_FILE")
echo "--- test 6: heartbeat file content ---"
echo "$hb_content"
echo "--- end test 6 ---"
# Verify required fields are present.
echo "$hb_content" | grep -qE '^ts=[0-9]{4}-[0-9]{2}-[0-9]{2}T' || \
fail "test6: heartbeat ts field missing or malformed"
echo "$hb_content" | grep -qE '^pid=[0-9]+' || \
fail "test6: heartbeat pid field missing or malformed"
echo "$hb_content" | grep -qF 'status=ok' || \
fail "test6: heartbeat status=ok missing"
# ── Test 7: heartbeat sidecar — targets correct .hb path per agent name ────────
#
# Uses the fake-tmux shim approach (like tests 3-5) to capture the sidecar
# invocation without needing a real session. A fake setsid shim records its
# arguments so we can assert the sidecar script targets the expected .hb path
# and uses the configured interval.
FAKE_BIN7=$(mktemp -d)
FAKE_RUNTIME_BIN7=$(mktemp -d)
SETSID_ARGS_FILE=$(mktemp)
HB_RUN_DIR7=$(mktemp -d)
CLEANUP_DIRS+=("$FAKE_BIN7" "$FAKE_RUNTIME_BIN7" "$HB_RUN_DIR7")
AGENT7="my-fleet-agent-$RANDOM"
INTERVAL7="42"
# Fake tmux: has-session → not found; new-session → ok; list-panes → known PID.
cat > "$FAKE_BIN7/tmux" <<SHIM7
#!/usr/bin/env bash
subcmd="\$3"
if [ "\$subcmd" = "has-session" ]; then exit 1; fi
if [ "\$subcmd" = "new-session" ]; then exit 0; fi
if [ "\$subcmd" = "list-panes" ]; then echo "88888"; exit 0; fi
exit 0
SHIM7
chmod +x "$FAKE_BIN7/tmux"
# Fake setsid: capture the bash -c <script> argument for inspection, then
# background an actual bash subshell so disown succeeds in the caller.
cat > "$FAKE_BIN7/setsid" <<'SETSID_SHIM'
#!/usr/bin/env bash
# argv: setsid bash -c <sidecar_script>
# Record the full argument list to the capture file, then exit cleanly.
printf '%s\0' "$@" > __SETSID_ARGS_FILE__
exit 0
SETSID_SHIM
# Patch the placeholder with the real capture-file path (avoids heredoc expansion issues).
sed -i "s|__SETSID_ARGS_FILE__|${SETSID_ARGS_FILE}|g" "$FAKE_BIN7/setsid"
chmod +x "$FAKE_BIN7/setsid"
SOCKET7="mosaic-agent-test7-$RANDOM-$$"
WORKDIR7=$(mktemp -d)
CLEANUP_DIRS+=("$WORKDIR7")
PATH="$FAKE_BIN7:$PATH" \
MOSAIC_TMUX_SOCKET="$SOCKET7" \
MOSAIC_AGENT_WORKDIR="$WORKDIR7" \
MOSAIC_AGENT_RUNTIME="pi" \
MOSAIC_RUNTIME_BIN="$FAKE_RUNTIME_BIN7" \
MOSAIC_AGENT_COMMAND="mosaic yolo pi" \
MOSAIC_HEARTBEAT_RUN_DIR="$HB_RUN_DIR7" \
MOSAIC_HEARTBEAT_INTERVAL="$INTERVAL7" \
"$START" "$AGENT7"
# Give the background setsid shim a moment to finish writing the capture file.
sleep 0.5
setsid_args=$(cat "$SETSID_ARGS_FILE" 2>/dev/null | tr '\0' '\n' || true)
rm -f "$SETSID_ARGS_FILE"
rm -rf "$WORKDIR7"
echo "--- test 7: captured setsid args ---"
echo "$setsid_args"
echo "--- end test 7 ---"
# The sidecar script (bash -c <script>) must reference the correct .hb path.
expected_hb="${HB_RUN_DIR7}/${AGENT7}.hb"
echo "$setsid_args" | grep -qF "$expected_hb" || \
fail "test7: sidecar script does not reference correct .hb path ($expected_hb)"
# The sidecar script must use the configured interval.
echo "$setsid_args" | grep -qF "$INTERVAL7" || \
fail "test7: sidecar script does not reference configured interval ($INTERVAL7)"
echo "ok - start-agent-session" echo "ok - start-agent-session"

View File

@@ -1,93 +0,0 @@
#!/usr/bin/env bash
# check-resident-budget.sh — resident line-count ceiling (R9 / DESIGN §7).
#
# Budgets the *container* (line count) of the framework-owned files that are
# injected into every agent's context by value — the Constitution (L0), the
# AGENTS dispatcher, and each runtime RUNTIME.md slice. Gate *wording* is never
# capped (a word cap forces paraphrasing law — the exact drift vector P3 killed);
# only the file's line count is bounded, so prose creep is caught in review.
#
# This is the CI-enforceable half of the budget. The per-harness *total* resident
# prompt (which also includes user-generated SOUL.md/USER.md and the per-tier
# slice) is summed by `mosaic doctor` as a runtime advisory — CI cannot see user
# files, so it is deliberately out of scope here (DESIGN §7).
#
# Usage: check-resident-budget.sh [--self-test]
# Exit: 0 = all within budget · 1 = a file exceeds its ceiling · 2 = self-test failed
set -uo pipefail
FW="$(cd "$(dirname "${BASH_SOURCE[0]}")/../../.." && pwd)" # packages/mosaic/framework
# Per-file ceilings (lines). Headroom above current counts; tighten as files settle.
# Format: "<relative-path>:<max-lines>"
CEILINGS=(
"defaults/CONSTITUTION.md:120"
"defaults/AGENTS.md:120"
"runtime/claude/RUNTIME.md:90"
"runtime/codex/RUNTIME.md:90"
"runtime/opencode/RUNTIME.md:90"
"runtime/pi/RUNTIME.md:90"
)
# check_file <abs-path> <max> → echoes "<n>"; returns 0 if n<=max, 1 otherwise.
check_file() {
local path="$1" max="$2" n
n=$(wc -l <"$path" 2>/dev/null || echo 0)
n=$((n + 0))
echo "$n"
[ "$n" -le "$max" ]
}
run_budget() {
local fail=0 rel max abs n
printf '%-32s %8s %8s %s\n' "FILE" "LINES" "CEILING" "STATUS"
for entry in "${CEILINGS[@]}"; do
rel="${entry%%:*}"
max="${entry##*:}"
abs="$FW/$rel"
if [ ! -f "$abs" ]; then
printf '%-32s %8s %8s %s\n' "$rel" "-" "$max" "MISSING"
fail=1
continue
fi
n=$(check_file "$abs" "$max")
if [ "$n" -le "$max" ]; then
printf '%-32s %8s %8s %s\n' "$rel" "$n" "$max" "ok"
else
printf '%-32s %8s %8s %s\n' "$rel" "$n" "$max" "OVER BUDGET"
fail=1
fi
done
return "$fail"
}
self_test() {
local tmp rc
tmp=$(mktemp)
# 3 lines, ceiling 5 → within budget (rc 0)
printf 'a\nb\nc\n' >"$tmp"
check_file "$tmp" 5 >/dev/null
rc=$?
if [ "$rc" -ne 0 ]; then echo "self-test FAIL: under-budget file flagged"; rm -f "$tmp"; return 2; fi
# 6 lines, ceiling 5 → over budget (rc 1)
printf 'a\nb\nc\nd\ne\nf\n' >"$tmp"
check_file "$tmp" 5 >/dev/null
rc=$?
if [ "$rc" -ne 1 ]; then echo "self-test FAIL: over-budget file not flagged"; rm -f "$tmp"; return 2; fi
rm -f "$tmp"
echo "self-test OK"
return 0
}
if [ "${1:-}" = "--self-test" ]; then
self_test
exit $?
fi
if run_budget; then
echo "Resident budget: all framework-owned resident files within ceiling."
exit 0
else
echo "Resident budget EXCEEDED — trim prose or raise the ceiling deliberately (see DESIGN §7)." >&2
exit 1
fi

View File

@@ -1,67 +0,0 @@
#!/usr/bin/env bash
# test-install-migration.sh — fixture matrix for the v2→v3 (Constitution) upgrade
# migration in install.sh. Runs the installer against throwaway MOSAIC_HOME dirs
# with MOSAIC_SYNC_ONLY=1 (file phase only — no environment-touching post-install)
# and asserts the framework-owned-overwrite + user-preserve + backup semantics.
#
# Mirrors the TS fixture suite in packages/mosaic/src/config/file-adapter.test.ts;
# both installers MUST behave identically.
#
# Usage: bash test-install-migration.sh
set -uo pipefail
FW="$(cd "$(dirname "${BASH_SOURCE[0]}")/../../.." && pwd)" # packages/mosaic/framework
INSTALL="$FW/install.sh"
DEFA="$FW/defaults"
pass=0; fail=0
chk() { if eval "$2"; then echo "$1"; pass=$((pass + 1)); else echo "$1"; fail=$((fail + 1)); fi; }
run() { MOSAIC_HOME="$1" MOSAIC_INSTALL_MODE="$2" MOSAIC_SYNC_ONLY=1 bash "$INSTALL" >/dev/null 2>&1; }
echo "install.sh v2→v3 migration fixture matrix:"
# F1 — fresh install
T1=$(mktemp -d); run "$T1" overwrite
chk "F1 fresh: CONSTITUTION/AGENTS/STANDARDS/TOOLS seeded" \
"[ -f '$T1/CONSTITUTION.md' ] && [ -f '$T1/AGENTS.md' ] && [ -f '$T1/STANDARDS.md' ] && [ -f '$T1/TOOLS.md' ]"
chk "F1 fresh: AGENTS == shipped default" "cmp -s '$T1/AGENTS.md' '$DEFA/AGENTS.md'"
chk "F1 fresh: framework-version stamped 3" "[ \"\$(cat '$T1/.framework-version' 2>/dev/null)\" = 3 ]"
# F2 — legacy install with a user-edited AGENTS.md (the sanctioned pre-constitution customization)
T2=$(mktemp -d); mkdir -p "$T2/credentials"
printf '# user-edited AGENTS pre-constitution\n' > "$T2/AGENTS.md"
printf '# my persona\n' > "$T2/SOUL.md"
printf 'token\n' > "$T2/credentials/c.json"
echo 2 > "$T2/.framework-version"
run "$T2" keep
chk "F2 legacy-edited: AGENTS overwritten to framework version" "cmp -s '$T2/AGENTS.md' '$DEFA/AGENTS.md'"
chk "F2 legacy-edited: prior AGENTS saved to .pre-constitution.bak" \
"grep -q 'user-edited AGENTS pre-constitution' '$T2/AGENTS.md.pre-constitution.bak'"
chk "F2 legacy-edited: SOUL.md preserved" "grep -q 'my persona' '$T2/SOUL.md'"
chk "F2 legacy-edited: credentials preserved" "grep -q token '$T2/credentials/c.json'"
chk "F2 legacy-edited: CONSTITUTION.md installed" "[ -f '$T2/CONSTITUTION.md' ]"
run "$T2" keep
chk "F2 idempotent: .pre-constitution.bak preserved across a 2nd upgrade" \
"grep -q 'user-edited AGENTS pre-constitution' '$T2/AGENTS.md.pre-constitution.bak'"
# F3 — user-tuned STANDARDS.md
T3=$(mktemp -d); printf '# tuned standards\n' > "$T3/STANDARDS.md"; printf '# persona\n' > "$T3/SOUL.md"; echo 2 > "$T3/.framework-version"
run "$T3" keep
chk "F3 tuned-standard: STANDARDS overwritten" "cmp -s '$T3/STANDARDS.md' '$DEFA/STANDARDS.md'"
chk "F3 tuned-standard: tuned copy backed up" "grep -q 'tuned standards' '$T3/STANDARDS.md.pre-constitution.bak'"
# F4 — unattended / no TTY (stdin closed): must complete without hanging, default to keep
T4=$(mktemp -d); printf '# persona\n' > "$T4/SOUL.md"; printf '# old\n' > "$T4/AGENTS.md"; echo 2 > "$T4/.framework-version"
MOSAIC_HOME="$T4" MOSAIC_SYNC_ONLY=1 bash "$INSTALL" </dev/null >/dev/null 2>&1
chk "F4 no-TTY: completed, AGENTS updated" "cmp -s '$T4/AGENTS.md' '$DEFA/AGENTS.md'"
# F5 — failure path must not corrupt existing data (invalid mode rejected before any file op)
T5=$(mktemp -d); mkdir -p "$T5/credentials"; printf '# orig\n' > "$T5/SOUL.md"; printf 'keepme\n' > "$T5/credentials/c.json"; echo 2 > "$T5/.framework-version"
MOSAIC_HOME="$T5" MOSAIC_INSTALL_MODE=bogus MOSAIC_SYNC_ONLY=1 bash "$INSTALL" >/dev/null 2>&1; rc=$?
chk "F5 failure: invalid mode rejected (nonzero exit)" "[ $rc -ne 0 ]"
chk "F5 failure: SOUL + credentials intact" "grep -q orig '$T5/SOUL.md' && grep -q keepme '$T5/credentials/c.json'"
rm -rf "$T1" "$T2" "$T3" "$T4" "$T5"
echo
echo "RESULT: $pass passed, $fail failed"
[ "$fail" -eq 0 ]

View File

@@ -53,15 +53,9 @@ _selftest() {
local tmp; tmp="$(mktemp -d)" || return 1 local tmp; tmp="$(mktemp -d)" || return 1
printf 'contact jason.woltje at jarvis-brain (PDA-friendly)\n' > "$tmp/planted.md" printf 'contact jason.woltje at jarvis-brain (PDA-friendly)\n' > "$tmp/planted.md"
printf 'X="${VAR:-$HOME/src/whatever/x.json}"\n' > "$tmp/planted.sh" printf 'X="${VAR:-$HOME/src/whatever/x.json}"\n' > "$tmp/planted.sh"
printf 'name: jason-woltje\n' > "$tmp/planted.yaml"
printf '[Service]\nUser=jarvis\n' > "$tmp/planted.service"
local rc=0 local rc=0
grep -qIEi "$DENYLIST" "$tmp/planted.md" || { echo "✗ SELF-TEST: identity denylist regex broken" >&2; rc=1; } grep -qIEi "$DENYLIST" "$tmp/planted.md" || { echo "✗ SELF-TEST: identity denylist regex broken" >&2; rc=1; }
grep -qIE "$STRUCTURAL_SH" "$tmp/planted.sh" || { echo "✗ SELF-TEST: structural regex broken" >&2; rc=1; } grep -qIE "$STRUCTURAL_SH" "$tmp/planted.sh" || { echo "✗ SELF-TEST: structural regex broken" >&2; rc=1; }
# Prove the identity scan covers the config formats it claims to (yaml/service/etc).
local n_ext
n_ext=$(find "$tmp" -type f \( -name '*.yaml' -o -name '*.service' \) -print0 | xargs -0 -r grep -lIEi "$DENYLIST" 2>/dev/null | wc -l)
[[ "$n_ext" -eq 2 ]] || { echo "✗ SELF-TEST: identity scan does not cover .yaml/.service extensions" >&2; rc=1; }
rm -rf "$tmp"; return $rc rm -rf "$tmp"; return $rc
} }
_selftest || exit 2 _selftest || exit 2

View File

@@ -1,6 +1,6 @@
{ {
"name": "@mosaicstack/mosaic", "name": "@mosaicstack/mosaic",
"version": "0.0.37", "version": "0.0.34",
"repository": { "repository": {
"type": "git", "type": "git",
"url": "https://git.mosaicstack.dev/mosaicstack/stack.git", "url": "https://git.mosaicstack.dev/mosaicstack/stack.git",

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -99,8 +99,11 @@ describe('FileConfigAdapter.syncFramework — defaults seeding', () => {
); );
}); });
it('overwrites framework-owned files (backup-once) but preserves user-seeded files', async () => { it('preserves existing contract files — never overwrites user customization', async () => {
// Plant a root-level AGENTS.md in sourceDir so syncDirectory's preserve is exercised. // Also plant a root-level AGENTS.md in sourceDir so that `syncDirectory`
// itself (not just the seed loop) has something to try to overwrite.
// Without this, the test would silently pass even if preserve semantics
// were broken in syncDirectory.
writeFileSync(join(fixture.sourceDir, 'AGENTS.md'), '# shipped AGENTS from source root\n'); writeFileSync(join(fixture.sourceDir, 'AGENTS.md'), '# shipped AGENTS from source root\n');
writeFileSync(join(fixture.mosaicHome, 'TOOLS.md'), '# user-customized TOOLS\n'); writeFileSync(join(fixture.mosaicHome, 'TOOLS.md'), '# user-customized TOOLS\n');
@@ -109,50 +112,18 @@ describe('FileConfigAdapter.syncFramework — defaults seeding', () => {
const adapter = new FileConfigAdapter(fixture.mosaicHome, fixture.sourceDir); const adapter = new FileConfigAdapter(fixture.mosaicHome, fixture.sourceDir);
await adapter.syncFramework('keep'); await adapter.syncFramework('keep');
// User-seeded TOOLS.md is preserved.
expect(readFileSync(join(fixture.mosaicHome, 'TOOLS.md'), 'utf-8')).toBe( expect(readFileSync(join(fixture.mosaicHome, 'TOOLS.md'), 'utf-8')).toBe(
'# user-customized TOOLS\n', '# user-customized TOOLS\n',
); );
// Framework-owned AGENTS.md is overwritten from defaults/ ... expect(readFileSync(join(fixture.mosaicHome, 'AGENTS.md'), 'utf-8')).toBe(
expect(readFileSync(join(fixture.mosaicHome, 'AGENTS.md'), 'utf-8')).toBe('# AGENTS default\n');
// ... and the user's prior copy is backed up exactly once.
expect(readFileSync(join(fixture.mosaicHome, 'AGENTS.md.pre-constitution.bak'), 'utf-8')).toBe(
'# user-customized AGENTS\n', '# user-customized AGENTS\n',
); );
// Framework-owned STANDARDS.md (absent) gets installed. // And the missing contract file still gets seeded.
expect(readFileSync(join(fixture.mosaicHome, 'STANDARDS.md'), 'utf-8')).toContain( expect(readFileSync(join(fixture.mosaicHome, 'STANDARDS.md'), 'utf-8')).toContain(
'# STANDARDS default', '# STANDARDS default',
); );
}); });
it('backs up a divergent framework-owned file only once (idempotent across re-sync)', async () => {
writeFileSync(join(fixture.mosaicHome, 'AGENTS.md'), '# user-customized AGENTS\n');
const adapter = new FileConfigAdapter(fixture.mosaicHome, fixture.sourceDir);
await adapter.syncFramework('keep'); // 1st: backup created, AGENTS overwritten
await adapter.syncFramework('keep'); // 2nd: AGENTS already == default, no new backup
expect(readFileSync(join(fixture.mosaicHome, 'AGENTS.md.pre-constitution.bak'), 'utf-8')).toBe(
'# user-customized AGENTS\n',
);
});
it('preserves SOUL.md and credentials through a framework-owned overwrite', async () => {
writeFileSync(join(fixture.mosaicHome, 'SOUL.md'), '# my persona\n');
writeFileSync(join(fixture.mosaicHome, 'AGENTS.md'), '# user-customized AGENTS\n');
mkdirSync(join(fixture.mosaicHome, 'credentials'), { recursive: true });
writeFileSync(join(fixture.mosaicHome, 'credentials', 'c.json'), 'token\n');
const adapter = new FileConfigAdapter(fixture.mosaicHome, fixture.sourceDir);
await adapter.syncFramework('keep');
expect(readFileSync(join(fixture.mosaicHome, 'SOUL.md'), 'utf-8')).toBe('# my persona\n');
expect(readFileSync(join(fixture.mosaicHome, 'credentials', 'c.json'), 'utf-8')).toBe(
'token\n',
);
expect(readFileSync(join(fixture.mosaicHome, 'AGENTS.md'), 'utf-8')).toBe('# AGENTS default\n');
});
it('is a no-op for seeding when defaults/ dir does not exist', async () => { it('is a no-op for seeding when defaults/ dir does not exist', async () => {
rmSync(fixture.defaultsDir, { recursive: true }); rmSync(fixture.defaultsDir, { recursive: true });

View File

@@ -13,17 +13,12 @@ import { join } from 'node:path';
* This list must match the explicit seed loop in * This list must match the explicit seed loop in
* packages/mosaic/framework/install.sh. * packages/mosaic/framework/install.sh.
*/ */
// Framework-owned contract files: re-copied from defaults/ on every upgrade (a export const DEFAULT_SEED_FILES = [
// divergent existing copy is backed up once to <file>.pre-constitution.bak first). 'CONSTITUTION.md',
// MUST match FRAMEWORK_OWNED in packages/mosaic/framework/install.sh (append-friendly). 'AGENTS.md',
export const FRAMEWORK_OWNED_FILES = ['CONSTITUTION.md', 'AGENTS.md', 'STANDARDS.md'] as const; 'STANDARDS.md',
'TOOLS.md',
// User-seeded contract files: written once on first install, then owned by the user. ] as const;
// MUST match USER_SEEDED in packages/mosaic/framework/install.sh.
export const USER_SEEDED_FILES = ['TOOLS.md'] as const;
// Union, retained for callers/tests that assert the full seed set on a fresh install.
export const DEFAULT_SEED_FILES = [...FRAMEWORK_OWNED_FILES, ...USER_SEEDED_FILES] as const;
import type { ConfigService, ConfigSection, ResolvedConfig } from './config-service.js'; import type { ConfigService, ConfigSection, ResolvedConfig } from './config-service.js';
import type { SoulConfig, UserConfig, ToolsConfig, InstallAction } from '../types.js'; import type { SoulConfig, UserConfig, ToolsConfig, InstallAction } from '../types.js';
import { soulSchema, userSchema, toolsSchema } from './schemas.js'; import { soulSchema, userSchema, toolsSchema } from './schemas.js';
@@ -164,7 +159,6 @@ export class FileConfigAdapter implements ConfigService {
const preservePaths = const preservePaths =
action === 'keep' || action === 'reconfigure' action === 'keep' || action === 'reconfigure'
? [ ? [
'CONSTITUTION.md',
'AGENTS.md', 'AGENTS.md',
'SOUL.md', 'SOUL.md',
'USER.md', 'USER.md',
@@ -181,10 +175,10 @@ export class FileConfigAdapter implements ConfigService {
excludeGit: true, excludeGit: true,
}); });
// Reconcile framework-contract files from framework/defaults/ into the mosaic // Copy framework-contract files (AGENTS.md, STANDARDS.md, TOOLS.md)
// home root: framework-owned files (CONSTITUTION/AGENTS/STANDARDS) are overwritten // from framework/defaults/ into the mosaic home root if they don't
// every upgrade (backup-once); user-seeded files (TOOLS) are written on first // exist yet. These are written on first install only and are never
// install only. Mirrors reconcile_framework_files() in install.sh. // overwritten afterwards — the user may have customized them.
// //
// SOUL.md and USER.md are deliberately NOT seeded here. They are // SOUL.md and USER.md are deliberately NOT seeded here. They are
// generated from templates by the soul/user wizard stages with // generated from templates by the soul/user wizard stages with
@@ -192,22 +186,7 @@ export class FileConfigAdapter implements ConfigService {
// identity flow and leak placeholder content into the mosaic home. // identity flow and leak placeholder content into the mosaic home.
const defaultsDir = join(this.sourceDir, 'defaults'); const defaultsDir = join(this.sourceDir, 'defaults');
if (existsSync(defaultsDir)) { if (existsSync(defaultsDir)) {
// Framework-owned: overwrite from defaults/ every sync; back up a divergent for (const entry of DEFAULT_SEED_FILES) {
// existing copy ONCE to <file>.pre-constitution.bak before the first overwrite.
for (const entry of FRAMEWORK_OWNED_FILES) {
const src = join(defaultsDir, entry);
const dest = join(this.mosaicHome, entry);
if (!existsSync(src) || !statSync(src).isFile()) continue;
// Already current — skip to avoid mtime churn.
if (existsSync(dest) && readFileSync(src).equals(readFileSync(dest))) continue;
const bak = `${dest}.pre-constitution.bak`;
if (existsSync(dest) && !existsSync(bak)) {
copyFileSync(dest, bak);
}
copyFileSync(src, dest);
}
// User-seeded: write only if absent.
for (const entry of USER_SEEDED_FILES) {
const src = join(defaultsDir, entry); const src = join(defaultsDir, entry);
const dest = join(this.mosaicHome, entry); const dest = join(this.mosaicHome, entry);
if (existsSync(dest)) continue; if (existsSync(dest)) continue;