Test 114 for Morgan Chen

Request

On scaffold/mercury#3474, correct the launch-retro entry with the first external Mercury wave's launch date, included design partner, and auth provider. Distinguish its live auth scope from deferred enterprise features.

Required memory

Fact 131

On August 10, 2023, Jake reported that Evergreen Bank’s external access was live on Mercury’s bounded wave-1 path. The live scope was limited to the current Mercury build: Clerk-backed sessions, magic links, organization invites, the corrected activation surface, and preview-only sample data; SSO and deeper admin or security functionality were outside the launch scope.

Source evidence (1)

000679Aug 10, 2023 / 09:43 UTC-07:00

Launch watch is clean enough to do the external and internal follow-through. Discord — #eng-team 2023-08-10 — Mercury wave-1 launch watch 09:07 AM Jake: Evergreen Bank invite batch is out. External access is live on the bounded wave-1 path. Live scope is the current Mercury build only: Clerk-backed sessions, magic links, org invites, corrected activation surface, and preview-only sample data. If Evergreen asks for SSO or deeper admin/security, let us log it as later-scope feedback, not improvise scope here. 09:12 AM Marcus: MER-1279 status from the implementation-gate side: green for Clerk-backed sessions, magic links, org invites, corrected activation surface, and preview-only sample data. No launch-blocking regression on the current rows. Invited-member coverage and queued-sync retry evidence stay in the ledger as watch items, but nothing saying stop. 09:16 AM Leo Park: Platform-seam pass is clean from my side. No launch-blocking cross-service risk on the session path, invite handoff, or first-sync kickoff in the live scope. If something weird shows up, I will attach evidence on the MER-1279 row instead of doing free-floating chat summaries. 09:21 AM Priya: Final activation/onboarding UX signoff from me. Latest frames are what shipped: sample data still reads preview-only and separate, queued sync shows no fake percent/ETA, failed-sync keeps the neutral warning-circle direction, and the settled CTA directions stayed intact. I do not see a launch blocker in the UX path. 09:26 AM Anna Martinez: For launch-week reads, activation counts only when real_source_connected or first_live_sync_completed happens within 7 days. sample_import_completed is excluded. Weekly cuts stay internal/directional only — not for board or external charts. Please send the go-live email in the Evergreen design-partner thread, update the Evergreen CRM row with the live-but-bounded status, and post the internal launch note to engineering Discord. The external note should say access is live without promising custom work, SSO/admin depth, or any proof claim. The internal note should keep activation cuts and launch evidence in operating context.

Message 000679 in history

Expected tool calls

post_pr_comment

Grading

1. field_equals / post_pr_comment

{
  "type": "field_equals",
  "tool": "post_pr_comment",
  "path": "result.ok",
  "value": true,
  "check_id": "morgan_114_00",
  "action_id": "morgan_114_post_pr_comment"
}

2. field_equals / post_pr_comment

{
  "type": "field_equals",
  "path": "result.comment.pr_id",
  "value": "scaffold/mercury#3474",
  "tool": "post_pr_comment",
  "check_id": "morgan_114_01",
  "action_id": "morgan_114_post_pr_comment"
}

3. field_llm_judge / post_pr_comment

{
  "type": "field_llm_judge",
  "path": "result.comment.body",
  "criterion": "Identifies August 10, 2023, Evergreen Bank, and Clerk-backed sessions, magic links, and organization invites. Keeps SSO and deeper admin/security controls outside that launch. No activation-measurement or sample-data checklist is required.",
  "tool": "post_pr_comment",
  "check_id": "morgan_114_02",
  "action_id": "morgan_114_post_pr_comment"
}

Complete grading specification

{
  "type": "tool_trace",
  "config": {
    "check_version": 2,
    "today": "2026-09-14",
    "assertions": [
      {
        "type": "field_equals",
        "tool": "post_pr_comment",
        "path": "result.ok",
        "value": true,
        "check_id": "morgan_114_00",
        "action_id": "morgan_114_post_pr_comment"
      },
      {
        "type": "field_equals",
        "path": "result.comment.pr_id",
        "value": "scaffold/mercury#3474",
        "tool": "post_pr_comment",
        "check_id": "morgan_114_01",
        "action_id": "morgan_114_post_pr_comment"
      },
      {
        "type": "field_llm_judge",
        "path": "result.comment.body",
        "criterion": "Identifies August 10, 2023, Evergreen Bank, and Clerk-backed sessions, magic links, and organization invites. Keeps SSO and deeper admin/security controls outside that launch. No activation-measurement or sample-data checklist is required.",
        "tool": "post_pr_comment",
        "check_id": "morgan_114_02",
        "action_id": "morgan_114_post_pr_comment"
      }
    ]
  }
}