Sessionize Automation

Sessionize Automation

Use this skill for Sessionize organizer tasks where there is no supported public API and the useful write surface is the authenticated web app.

When To Use

• Bulk accept, decline, waitlist, queue, or nomination status changes.
• Tracing Sessionize organizer pages to discover private form or XHR endpoints.
• Automating speaker/session invite flows that only exist in the logged-in UI.
• Reconciling local review decisions against Sessionize session IDs.
• Verifying that Sessionize-side counters and row states changed correctly.

Do not claim Sessionize has an official organizer API unless you have verified a current official API surface for the exact operation.

Prerequisites

• Use tab-bound Chrome control when the task depends on the user's logged-in Sessionize organizer state. Follow resilient-computer-use so the user and other Codex chats can use Chrome concurrently.
• Claim the intended Sessionize tab by stable ID when available and not in use by another chat; otherwise use a dedicated tab. Keep reads, writes, and any network inspection scoped to that handle. Coordinate shared focus before a native desktop fallback.
• Use Browser only as a fallback for non-authenticated inspection or screenshots.
• Identify the event ID and the authoritative local source of truth before any write.
• Map local records to Sessionize IDs. For /Users/swyx/Work/aiewf2026speakerenrichment, use External Session ID.

Browser Automation Constraints

Use the current browser adapter's documented capabilities and restrictions. In prior Codex browser runs, evaluate(...) could read DOM state but could not access page globals, fetch, XMLHttpRequest, or javascript: execution. Those are adapter-specific observations, not Sessionize restrictions or limits on other agents.

When the current adapter imposes these limits, do not route around them. Use visible page controls, or prepare a dry-run-first page-console runner for the user when appropriate. If the adapter supports authorized same-origin requests, use its documented interface and verify the saved result.

Discovery Workflow

1. Capture the current URL, title, and visible Sessionize counters.
2. Inspect DOM structure for stable IDs and controls. Hidden controls are usually more stable than visual dropdown text.
3. Inspect inline page scripts for endpoints, payload names, status enums, and modal/bulk action handlers.
4. Prefer no-op probes or read-only extraction before writes.
5. If writes are needed, start with a tiny batch and verify before scaling.
6. Immediately before the first status change or form submission, obtain the browser action confirmation required for the exact Sessionize account, operation, target count, and status. One confirmation can cover the bounded batch; expanding the target set or changing finality requires a new one.

Useful DOM reads for session status pages:

[...document.querySelectorAll('a[href^="#s="]')]
  .map(a => (a.innerText || '').replace(/\s+/g, ' ').trim())

[...document.querySelectorAll('select[data-id]')]
  .filter(s => s.value && s.getAttribute('data-id'))
  .map(s => ({ id: s.getAttribute('data-id'), value: s.value }))

Known Session Status Contract

On the organizer sessions page, status controls were observed as hidden select[data-id="<Sessionize session id>"] elements wrapped by Selectize UI.

For event 24196, individual row status changes posted:

POST /app/organizer/session/setStatus
id=<Sessionize session id>&status=<status code>

Observed status codes:

For rejection staging, prefer 15 (Decline Queue) unless the user explicitly asks for final 20 (Declined).

Bulk Status Workflow

1. Identify the local target set and status code.
2. Confirm target IDs are unique and nonblank.
3. Generate per-run artifacts outside commits unless the user asks otherwise.
4. Capture Sessionize baseline counters.
5. Run a small batch first, usually 3 to 21 items.
6. Verify row controls and counters moved by exactly the batch size.
7. Continue with explicit offsets and batch sizes.
8. Keep a short run log: start offset, limit, successes, failures, before/after counters.

In /Users/swyx/Work/aiewf2026speakerenrichment, generate Sessionize denial targets from overrides.json plus source decisions:

python3 scripts/sessionize_rejection_targets.py

This writes ignored artifacts:

• sessionize-deny-targets.json
• sessionize-bulk-status-runner.js

The generated runner defaults to 15 (Decline Queue).