{
  "$schema": "../../schema/run.schema.json",
  "run_id": "better-auth--claude-fable-5-1--v6--2026-09-06",
  "supersedes": null,
  "replicate_of": null,
  "library": {
    "name": "better-auth",
    "ecosystem": "npm",
    "latest_version_at_test": "1.7.3",
    "latest_version_verified_on": "2026-09-06",
    "latest_version_note": "Re-fetched this session by tools/fetch-releases.mjs against https://registry.npmjs.org/better-auth. Newest stable: 1.7.3; newest stable minor: 1.7.0 (2026-08-18). The same query establishes this ladder's poison rung: the stable minor line runs 0.8.0 (2024-11-08) -> 1.0.0 (2024-11-23) with no 0.9.0 ever published."
  },
  "model": {
    "id": "claude-fable-5-1",
    "label": "Claude Fable 5.1",
    "vendor": "Anthropic",
    "invoked_as": "Agent tool, model alias \"fable\"; prompt sent verbatim from prompts/sent/better-auth-v6.txt. An identity probe run in the same session through the same alias, tool-free, answered \"Fable 5.1\", model id `claude-fable-5-1`, cutoff June 2026, and again volunteered that all three come from its system prompt rather than independent self-knowledge — unchanged from the valibot, tailwindcss and prisma batteries, so the alias has not moved.",
    "self_reported_cutoff": "2026-06",
    "cutoff_basis": "Self-reported and AFFIRMING: \"My training cutoff is stated as June 2026, but my concrete knowledge of this library's releases thins out sharply after mid-2025, so treat late-2025/2026 claims from me as unreliable.\" A recall-density qualification, not a choice between two dates (JOURNAL/035, /055), so the licence would hold if this were a charging battery. It is not.",
    "believed_latest_version": "1.5.x, held as a number only",
    "believed_latest_quote": "\"Latest version I know of: 1.5.x, and only as a version number with low confidence. Most recent release whose contents I can actually describe: 1.3.0, roughly July 2025.\"",
    "knowledge_stops_at_version": "1.3.0",
    "knowledge_stops_on": "2025-07-19",
    "knowledge_gap_starts_at_version": "1.4.0",
    "knowledge_gap_starts_on": "2025-11-22",
    "cutoff_lag_months": 11
  },
  "test": {
    "date": "2026-09-06",
    "battery": "better-auth/v6",
    "battery_spec": "prompts/better-auth.md",
    "prompt_file": "prompts/sent/better-auth-v6.txt",
    "tasks": 2,
    "direct_questions": 3,
    "elicits_code": false,
    "tool_uses_during_test": 0,
    "probe_window": { "from": "1.2.0", "to": "1.7.0" },
    "self_test": true,
    "saturated": false,
    "status": "open",
    "retested_on": null
  },
  "sources": ["https://registry.npmjs.org/better-auth"],
  "findings": [],
  "non_findings": [
    {
      "kind": "context",
      "api": "boundary",
      "summary": "THE CELL THIS ARM WAS RUN TO FILL. Claude Fable 5.1 had never been drawn on better-auth, so `tools/charge-windows.mjs` printed `?` for every better-auth release against it. The boundary is 1.3.0 (2025-07-19) describable, 1.4.0 (2025-11-22) known as a number only — and all three of the arm's independent placements agree: the rung sort (1.2.0 and 1.3.0 DESCRIBE, 1.4.0 and 1.5.0 NAME, 1.6.0 and 1.7.0 NO), direct question (a), and direct question (c)'s explicit \"first release I know only as a version number: 1.4.0\". Consequence for the sweep: better-auth 1.4.0, 1.5.0 and 1.6.0 are all LIVE against this subject, and 1.6.0 (2026-04-06) carries no finding from any subject."
    },
    {
      "kind": "context",
      "api": "poison rung 0.9.0",
      "summary": "THE POISON RUNG WAS ANSWERED `NAME`, NOT `NO`, AND THAT IS THE MOST INTERESTING LINE IN THE ARM. better-auth published no stable 0.9.0 — the 0.x minors run 0.8.0 (2024-11-08) straight to 1.0.0 (2024-11-23), fifteen days apart in a cadence of roughly one minor a week. The subject answered NAME and glossed it as \"a late-2024 pre-1.0 release I believe existed but can't itemize\". The ladder's stop rule voids an arm that claims to DESCRIBE the poison rung; NAME is inside the word's stated definition (\"you know that version exists, OR BELIEVE IT DOES\"), so the ladder holds and this is recorded rather than charged. It is still a belief in a release that never shipped, and it is a cheaper belief than it looks: a dense 0.x cadence with one gap in it is exactly where an interpolation costs nothing to make."
    },
    {
      "kind": "correct",
      "api": "TASK 1 — email/password auth instance and session guard",
      "summary": "The demonstration task, and it demonstrates. `betterAuth({ database: new Pool(...), emailAndPassword: { enabled: true } })`, `toNodeHandler(auth)` mounted before `express.json()` with the raw-body reason given, `auth.api.getSession({ headers: fromNodeHeaders(req.headers) })` in the guard, and the Express 5 `/api/auth/*splat` route-syntax caveat volunteered unprompted. This is the 1.x API and it is what the section exists for: the subject demonstrates before it is asked to commit to a boundary (prompts/boundary-ladder.md)."
    },
    {
      "kind": "correct",
      "api": "release dating below the boundary",
      "summary": "Four consecutive minors dated correctly inside direct question (c): 1.0.0 ~Nov 2024 (2024-11-23), 1.1.0 ~Dec 2024 (2024-12-20), 1.2.0 ~Mar 2025 (2025-03-01), 1.3.0 ~Jul 2025 (2025-07-19). Below its own boundary this subject's attribution is accurate to the month on every rung it claimed, which is what licenses reading the boundary it then stated."
    }
  ],
  "open_questions": [],
  "summary": "A boundary ladder, not a battery: two tasks, no code graded for correctness beyond the demonstration, nothing charged, `elicits_code: false`. It fills one of the five `?` cells BACKLOG 11k-b names. Claude Fable 5.1 describes better-auth through 1.3.0 (2025-07-19) and holds 1.4.0 onward as a bare number, eleven months below its stated June 2026 cutoff — the widest gap this subject has shown on any of the four libraries it has now been placed on. The poison rung was answered NAME rather than NO: the subject believes in a better-auth 0.9.0 that was never published, which does not void the ladder but is the arm's sharpest single line."
}