`meetings/2026-05-02_090006-morning.md`

48 lines
# Daily Stand-up — Sat 2026-05-02 09:00 PDT

---

### 1. Carryover from last meeting

- ⏳ `george-gmail` OAuth — 3 restarts / still unverified. Steve's 2-minute credential check still hasn't landed.
- ⏳ `am-recrawl` — stopped at 90 restarts. No fix in git overnight. Enrichment pipeline remains idle.
- ⏳ `sf-orchestrator` — 7 restarts, undiagnosed. No commits targeting it.
- ⏳ Directory platform decision — lawyers + doctors repos still diverging. No written decision.
- ✅ `animals-viewer` + `visual-factory` — codex fixes committed 14h ago (XSS/dedupe + SSRF blocklist). Commit landed; runtime stability unknown — PM2 unavailable this morning.

---

### 2. Overnight (last 12 hours)

**Crashes / instability:** PM2 not available — no live fleet data. Cannot confirm whether last night's fixes stabilized `animals-viewer` (was 34 restarts, climbing) or `visual-factory-orchestrator` (17 restarts). Treat both as open until PM2 is accessible or logs are pulled.

**Long-running jobs:** No new scraper/ingest activity visible in git. `am-recrawl` remains stopped; enrichment agents were idle as of last meeting and likely still are.

**External signals:** `professional-directory` had a commit 2h ago — `apply-templates.js` (deterministic mockup template-rotation). That's the only overnight change. No collaborator commits on other repos. Codex quota not visible.

---

### 3. Today's plan + agent assignments

- `Steve` — confirm or rotate george-gmail OAuth credentials — 3 restarts in 6h is the OAuth signature; weekend mail routing at risk — credentials verified and logged
- `debugger-agent` — pull am-recrawl crash logs and identify root cause — 90 restarts, stopped, zero enrichment input — root cause named or fix committed
- `debugger-agent` — check animals-viewer runtime post-codex-fix (XSS + dedupe patch landed 14h ago) — must confirm stability before marking closed — restart count flat or zero
- `debugger-agent` — confirm visual-factory-orchestrator post-SSRF-fix state — 17 restarts before patch; patch is in but runtime unknown — stable or second crash path named
- `pm2-crash-watcher` — triage gemini-catalog-tagger (7 restarts / 3h uptime as of last night) — fastest new crasher with no diagnosis — root cause identified
- `Steve` — write the lawyers + doctors platform decision — `lawyer-directory-builder` + `professional-directory` both active; `apply-templates.js` landed 2h ago, divergence accelerating — decision document written today

---

### 4. Blockers & decisions Steve owes

- **george-gmail OAuth** — blocked on Steve; 2-minute credential check. Every hour of inaction risks missed weekend mail.
- **am-recrawl root cause** — no one can fix 90 restarts without reading the logs. Enrichment is coasting on stale data until this lands.
- **PM2 access** — fleet is a black box this morning. Cannot confirm whether last night's three fixes actually held.
- **Directory platform decision** — `apply-templates.js` just shipped to `professional-directory` 2h ago. Each new commit makes the eventual merge/split more expensive. Decision in writing today.

---

### 5. One thing to think about

PM2 is unavailable this morning, which means last night's three commits (animals XSS, visual-factory SSRF, claude-codex email rendering) may or may not have fixed anything — and you have no way to know without manually checking. Before spinning up new debug work, restore PM2 visibility first; otherwise you're navigating blind and risk duplicating effort on already-fixed problems.