f9f77638da
Add model routing defaults, L2 role updates, convoy telemetry, and manifest tracking without touching unrelated in-progress work.
124 lines
4.5 KiB
Markdown
124 lines
4.5 KiB
Markdown
# Convoys
|
|
|
|
A **convoy** is a multi-PR work-stream coordinated by an agent pipeline. One convoy = one feature, bug fix, or epic. Each convoy is a Markdown file in this directory plus an optional sub-directory of implementer briefs.
|
|
|
|
## File layout
|
|
|
|
```
|
|
.convoys/
|
|
├── README.md (this file)
|
|
├── <slug>.md (the convoy file — written by role-conductor)
|
|
└── <slug>/
|
|
├── brief-1-<kebab-title>.md (written by role-architect)
|
|
├── brief-2-<kebab-title>.md
|
|
└── ...
|
|
```
|
|
|
|
## Convoy file format
|
|
|
|
Frontmatter (set by `role-conductor`, then appended-to by other roles):
|
|
|
|
```yaml
|
|
---
|
|
name: <kebab-slug>
|
|
classification: feature | hotfix | docs-only | infra-only | server-only | config-only
|
|
success_metric: <one sentence>
|
|
skip:
|
|
- <flag1>
|
|
status: open | in-progress | merged | shipped | abandoned
|
|
created: <YYYY-MM-DD>
|
|
model_policy:
|
|
default_session: auto
|
|
roles: { ... } # see docs/model-routing-policy.md
|
|
---
|
|
```
|
|
|
|
Body sections (added in order by the pipeline roles):
|
|
|
|
1. `## Why` (Conductor)
|
|
2. `## Scope` (Conductor)
|
|
3. `## Roles invoked` (Conductor)
|
|
4. `## Todos` (Conductor → refined by Architect)
|
|
5. `## IA` (IA Architect)
|
|
6. `## UX` (UX Reviewer)
|
|
7. `## Architecture` (Architect)
|
|
|
|
After Architect, briefs live in `.convoys/<slug>/brief-N-*.md`. Implementers read only their brief, not the whole convoy.
|
|
|
|
## Skip flags
|
|
|
|
The Conductor sets `skip:` based on classification. These flags map to pipeline stages that no-op when set:
|
|
|
|
| Flag | Skips |
|
|
| --- | --- |
|
|
| `ia` | IA Architect |
|
|
| `ux` | UX Reviewer |
|
|
| `arch` | Architect |
|
|
| `test` | Component tests |
|
|
| `review` | Reviewer |
|
|
| `visual` | Visual diff |
|
|
| `a11y` | A11y auditor |
|
|
| `design` | Design-system auditor |
|
|
| `smoke` | Staging smoke |
|
|
| `qa` | Manual QA |
|
|
| `docs` | Doc Writer |
|
|
| `flag` | Flag rollout |
|
|
|
|
Never skipped (mandatory human gates): `plan-approval`, `pr-merge`, `prod-promote`.
|
|
|
|
## Status lifecycle
|
|
|
|
- `open` — Conductor created the convoy; no work started.
|
|
- `in-progress` — At least one brief has an open or merged PR.
|
|
- `merged` — All briefs merged to umbrella; release PR to develop pending.
|
|
- `shipped` — Release to main complete; flag rollout (if any) underway.
|
|
- `abandoned` — Convoy closed without shipping; reason in convoy body.
|
|
|
|
Update status by editing the convoy frontmatter as you progress.
|
|
|
|
## Adding a new convoy
|
|
|
|
1. Open Cursor in this repo.
|
|
2. Prompt: *"Start a new convoy: <one-paragraph idea>. Success = <metric>."*
|
|
3. The `role-conductor` subagent writes `.convoys/<slug>.md`.
|
|
4. Run subsequent roles in order per the convoy's `Roles invoked` list.
|
|
|
|
See `.cursor/agents/role-conductor.md` for the Conductor's full spec.
|
|
|
|
## Multitask + worktrees (Cursor 3.2+)
|
|
|
|
[Cursor 3.2 (Apr 24, 2026)](https://cursor.com/changelog/04-24-26) added `/multitask` async subagents and native worktree management in the Agents Window. The pipeline uses both:
|
|
|
|
**Audit fan-out** — after an implementer ships a PR draft:
|
|
|
|
```
|
|
/multitask role-reviewer + role-design-system-auditor + role-a11y-auditor
|
|
```
|
|
|
|
All three read the same diff and emit independent comments. Use group id `audit-<convoy>-<pr>` so analytics can compute wall-clock savings.
|
|
|
|
**Implementer fleet** — after architect's plan is approved (gate 1), if `slice_dependencies:` declares parallel-safe briefs (`depends_on: []`, disjoint `files:`):
|
|
|
|
```
|
|
/multitask role-implementer briefs 1, 2, 3
|
|
```
|
|
|
|
Use Cursor's Agents Window to create a worktree per brief — one click each. The legacy `scripts/wt.sh` is now a deprecation stub.
|
|
|
|
See the [multitask playbook](https://github.com/varutasu/agent-pipeline/blob/main/docs/multitask-playbook.md) for the full guardrail set.
|
|
|
|
## Self-analytics
|
|
|
|
Each L2 role appends one event to `.convoys/.metrics.jsonl` via `scripts/log-convoy-event.sh`. The file is gitignored by default — events stay local. To opt-in to commit team-shared metrics, remove `.convoys/.metrics.jsonl` from `.gitignore`.
|
|
|
|
Aggregate across repos and render a dashboard with the [agent-pipeline analytics scripts](https://github.com/varutasu/agent-pipeline/tree/main/analytics):
|
|
|
|
```bash
|
|
cd ~/code/agent-pipeline/analytics
|
|
npx tsx analyze-convoys.ts <repo-path> [<repo-path>...]
|
|
npx tsx render-dashboard.ts
|
|
open ~/agent-pipeline-data/dashboard.html
|
|
```
|
|
|
|
Schema: [`analytics/schemas/convoy-event.json`](https://github.com/varutasu/agent-pipeline/blob/main/analytics/schemas/convoy-event.json). Model tiers: [`docs/model-routing-policy.md`](https://github.com/varutasu/agent-pipeline/blob/main/docs/model-routing-policy.md).
|
|
|