docs(.memory): QA agent reference + Web Designer self-logging/QA-loop update

This commit is contained in:
Carlos Arias 2026-07-24 07:12:29 -04:00
parent 57dee86981
commit 74c6445e0e
2 changed files with 153 additions and 1 deletions

132
.memory/qa-agent.md Normal file
View file

@ -0,0 +1,132 @@
# The QA agent — automated site testing with a self-healing loop
**Status:** Implemented · **Date:** 2026-07-24
**Related:** [webdesigner.md](webdesigner.md) · [../.claude/skills/qa/SKILL.md](../.claude/skills/qa/SKILL.md) · [../agents/console/SETUP.md](../agents/console/SETUP.md) · [../agents/console/PLAN.md](../agents/console/PLAN.md)
---
## What it is
The QA agent tests the live site (carlosarias.co) — links, images, the contact form, the
API, SEO/meta, and accessibility — records findings in the admin, and **auto-fixes the safe
ones** by feeding the [Web Designer](webdesigner.md) queue. It runs on a **heartbeat** (hourly)
and on demand from `/admin/qa`.
**The honest architecture.** The confined agent (`claude -p`, no Bash/WebFetch) *cannot make
HTTP requests or drive a browser*, and no headless browser is usable by the runner. Since the
site is **static** (Astro → baked HTML), that's fine: a **deterministic Node crawler inside
the console runner** does the actual testing (Node 22 global `fetch`, zero deps), findings are
stored via **PHP CLI + DB** (the runner has no DB driver), and a **thin LLM step** writes a
plain-English summary using the `qa` skill. The crawl is the source of truth; the LLM only
triages.
## The closed loop
```
heartbeat (hourly) ──► runQa (crawl) ──► cja_qa_findings
├─ safe findings (alt, internal links)
│ └─ qa-autofix.php → cja_tasks (queued)
│ └─ Web Designer fixes → publishes
│ └─ self-logs to /changelog
│ └─ next QA run: green
└─ judgment calls (external links, etc.)
└─ shown in /admin/qa with an
instructions box → you dispatch a fix
```
The site went 14 warnings → 0 through this loop (sitemap, résumé portrait alt, blog cover alt
auto-fixed; GitHub link removed by hand).
## What the crawler checks
| check_type | Verifies | Severity |
|---|---|---|
| `page` | every route returns 200 + HTML | error |
| `link` | every internal `<a href>` resolves | error |
| `image` | every `<img>`/og:image/icon loads | error |
| `external` | off-site links reachable | warning (bot-blocking is common) |
| `form` | `/api/contact/submit` alive (honeypot probe → 200) + rejects bad input (→ 422) | error/warning |
| `health` | `/api/health` → 200 & `db:"connected"` (read at `data.db` — API wraps in `{ok,data,error}`) | error |
| `seo` | each page has `<title>` + description; canonical host = carlosarias.co; no duplicate titles | warning (error on wrong canonical) |
| `sitemap` | every route is in `sitemap.xml` | warning |
| `a11y` | images have alt — **empty/bare `alt` is flagged too** (valid only for decorative images) | warning |
Route set = static list + DB slugs (`qa-routes.php`) + sitemap + discovered internal links.
HTML parsed with regex (clean static HTML). Each finding carries a templated `fix_hint`.
## Auto-fix (safe findings)
- Runs after every QA pass when `QA_AUTOFIX``0` (default **on**). `qa-autofix.php` queues a
Web Designer `cja_tasks` row for each **open** finding in a **safe category**
`['a11y', 'link']` (see `SAFE` in that file) — then the runner kicks `drainTasks()`.
- **Dedup:** skips a finding if a same-title task is queued/running *or was created in the last
6 hours* — so hourly heartbeats never spam or loop on the same issue.
- Judgment calls (`external`, `image`, `seo`, `sitemap`, `form`, `health`, `page`) are **not**
auto-fixed — they wait in `/admin/qa` for a human decision.
## Report + instructions (the human path)
`/admin/qa` lists runs (counts, summary) and the latest run's findings grouped by severity.
Each open finding has:
- **Create fix task** → queues a Web Designer fix (uses the `fix_hint`).
- an **instructions input** → type how to handle it ("remove it", "use https://…", "reword")
and that becomes the Web Designer's brief instead of the default hint. This is where
decisions like a wrong external URL get made — in the admin, not in chat.
- **Ignore** → mark the finding handled.
## Heartbeat
In-process timer in `server.mjs` (the runner is always up, so no cron needed):
- `QA_HEARTBEAT_MIN` (default **60**, `0` disables) — set in the systemd unit.
- One pulse ~90s after each restart; then every N minutes.
- **Triage is gated** to save tokens: a scheduled run with 0 errors gets a cheap templated
summary (no LLM call); only manual runs or runs with errors get an LLM summary.
## Storage & pruning
- `cja_qa_runs` (status, trigger manual/scheduled, summary, counts JSON, timestamps)
- `cja_qa_findings` (run_id, check_type, severity, url, detail, fix_hint, status
open/fix_queued/ignored) — migration `api/db/migrations/013_create_cja_qa.sql`.
- `qa-finish.php` prunes to the **50 most recent runs** (hourly runs accumulate).
## Files
| File | Role |
|---|---|
| `agents/console/server.mjs` | `runQa`, `qaTriage`, `runQaFlow`, `POST /devconsole/qa/run`, heartbeat, `QA_AUTOFIX`/`QA_HEARTBEAT_MIN` |
| `api/db/migrations/013_create_cja_qa.sql` | runs + findings tables |
| `api/cli/qa-start.php` | open a run → run_id |
| `api/cli/qa-finish.php` | store findings (temp JSON file) + prune |
| `api/cli/qa-routes.php` | DB-driven slugs for the crawl |
| `api/cli/qa-autofix.php` | queue Web Designer fixes for safe findings (6h dedup) |
| `api/public/controllers/adminqa.php` | runs / findings / fix (optional instructions) / ignore |
| `app/src/pages/admin/qa.astro` | report page + instructions box + "Run QA now" |
| `.claude/skills/qa/SKILL.md` | what QA checks, severity model, gotchas |
## Operating it
- **Run now:** the "Run QA now" button, or `curl -s -X POST http://127.0.0.1:3011/devconsole/qa/run`.
- **Change cadence / disable heartbeat:** `QA_HEARTBEAT_MIN` in the unit (`0` = off), then
`systemctl daemon-reload && systemctl restart astroagent-console.service`.
- **Disable auto-fix:** `QA_AUTOFIX=0` in the unit env.
- **View:** `/admin/qa`.
## Safety & gotchas
- **Read-only against the live site** — no git, no build, no writes. The two contact-form
probes write nothing (the honeypot `company` field is filled on purpose; the validation
probe is rejected with 422). Verified: a full run leaves `cja_contact` untouched.
- **Fixes only ever go through the Web Designer queue** — build-gated, scoped commit,
git-revertable, self-logged. Auto-fix ≠ unsafe; a bad fix is one `git revert` away.
- **External links = warnings, never errors** (403/429/timeouts are usually bot-blocking; only
a clear 404/410/DNS failure is flagged).
- **Empty alt IS a finding.** `alt=""`/bare `alt` is valid only for *decorative* images; a
content image (photo, cover, screenshot) needs descriptive alt. (An earlier version wrongly
treated empty alt as a pass — corrected.)
- **Health check reads `data.db`** — the API wraps every response in `{ok, data, error}`.
- **Site-coupling:** `QA_BASE`, the static route list, and `carlosarias.co` are hard-coded in
`runQa` — same site-agnosticism gap noted for the Web Designer; parameterise from config for
a clean clone.
- **Timezone:** the server (and thus the runner's timestamps) is `America/New_York` as of
2026-07-24 (was UTC). New Web Designer changelog stamps are Eastern.

View file

@ -1,7 +1,7 @@
# The Web Designer — a core Astroagent console update
**Status:** Implemented · **Date:** 2026-07-24
**Related:** [../agents/console/PLAN.md](../agents/console/PLAN.md) · [../agents/console/SETUP.md](../agents/console/SETUP.md) · [../brand/BRAND.md](../brand/BRAND.md) · [../.claude/skills/brand/SKILL.md](../.claude/skills/brand/SKILL.md)
**Related:** [qa-agent.md](qa-agent.md) · [../agents/console/PLAN.md](../agents/console/PLAN.md) · [../agents/console/SETUP.md](../agents/console/SETUP.md) · [../brand/BRAND.md](../brand/BRAND.md) · [../.claude/skills/brand/SKILL.md](../.claude/skills/brand/SKILL.md) · [../.claude/skills/changelog/SKILL.md](../.claude/skills/changelog/SKILL.md)
---
@ -28,6 +28,26 @@ It coexists with two sibling surfaces built earlier in the same arc:
The Web Designer is the *freeform, queued* path for everything else.
## Added after first write (2026-07-24)
Two capabilities were added to the Web Designer after this doc's first version:
- **Self-logs every change to the changelog.** `buildDesignPrompt` instructs the agent, after
finishing, to add one entry to `api/cli/seed-changelog.php` via the `changelog` skill,
attributed to **`Website Designer Agent`**, with the current timestamp (injected by the
runner via `nowStamp()` — a headless agent can't read the clock). Because the confined agent
has no shell, **the runner reseeds** `cja_changelog` (`php api/cli/seed-changelog.php`) when
that file changed, before the build, so the entry goes live. Changelog entries carry a
`by`/`actor` field (migration 012): agents name themselves; human/CLI edits default to
`Carlos Arias`.
- **Fed by the QA agent.** QA findings become Web Designer tasks — auto-queued for safe
categories, or dispatched from the `/admin/qa` instructions box. A QA-origin task is just a
normal `cja_tasks` row, so it fixes, publishes, and self-logs like any other. See
[qa-agent.md](qa-agent.md) for the closed loop.
**Timezone note:** `nowStamp()` uses the runner's system timezone, set to `America/New_York`
on 2026-07-24 (was UTC, which mis-stamped early agent entries).
## Architecture
```