diff --git a/claude/memory/MEMORY.md b/claude/memory/MEMORY.md
index d870dc7..8a80b99 100644
--- a/claude/memory/MEMORY.md
+++ b/claude/memory/MEMORY.md
@@ -55,7 +55,7 @@ permalink: claude-memory/memory
 ## Canonical Workstream Trackers
 *Read the tracker for any active workstream at /wake-up before composing the briefing. Append substantive moves at /wrap-up — to the **chronological log**, not only "current state". Per `feedback-canonical-workstream-tracker-discipline.md`.*
 - **[Chamber as versioned releases](project-chamber-versioned-releases.md) — THE GOVERNING FRAME for all library work.** The 2000-year Chamber as versioned releases with soft borders, each serving a PURPOSE; scope every library bite through this. **Open decision: which purpose anchors V1.** Read the file, not this line — it holds the reframe that resolved the purpose/scope paralysis.
-- [Studium Engine](project-studium-engine.md) — canonical engine tracker; **read it, this line holds no state.** **fr cell: ONE STEP DONE, THE SECOND BLOCKED** (measured 2026-09-05, was "two steps from closing"). PENDING-134's disclosure is PLACED (`9221dd8`). ⚠ **CORRECTED 2026-09-05, same day: the pass HAD ALREADY RUN** — `docs/fr-reported-speech-identification-pass-2026-08-13.md`, commit `de1c34b`, authorized by REVIEWED-116 pt 5 as an identification pass that **writes nothing**. I read the absence of F4 markers as the absence of the act; a no-write pass leaves exactly that trace. Its finding: reported speech in **one** grounded span (L1551), reclassified out the same day (REVIEWED-119) — so within the grounded set P7's F4 tagging was **correct and complete**. Re-read independently 2026-09-05 across the enumerated **8**: zero reported speech, result reproduced. ⚠ **`ratio_A_to_B` therefore may be unblocked — that is for the ruling, not me — and is UNSPENT either way: REVIEWED-135 cond. 5 reserves the spend to its own steward act.** REVIEWED-116 pt 5 allows the single re-derivation only *after dispositions are recorded*; pt 6 rescoped that to **every fr grounded span read for reported speech**, and **no live `markers:` row carries F4** — the pass has never run. Blocker: **PENDING-133 + AMENDMENT 1, both open, awaiting steward authorization.** The one shot is unspent.
+- [Studium Engine](project-studium-engine.md) — canonical engine tracker; **read it, this line holds no state.** **fr cell: ONE STEP DONE, THE SECOND BLOCKED** (measured 2026-09-05, was "two steps from closing"). PENDING-134's disclosure is PLACED (`9221dd8`). ⚠ **CORRECTED 2026-09-05, same day: the pass HAD ALREADY RUN** — `docs/fr-reported-speech-identification-pass-2026-08-13.md`, commit `de1c34b`, authorized by REVIEWED-116 pt 5 as an identification pass that **writes nothing**. I read the absence of F4 markers as the absence of the act; a no-write pass leaves exactly that trace. Its finding: reported speech in **one** grounded span (L1551), reclassified out the same day (REVIEWED-119) — so within the grounded set P7's F4 tagging was **correct and complete**. Re-read independently 2026-09-05 across the enumerated **8**: zero reported speech, result reproduced. ✅ **SETTLED 2026-09-06 — REVIEWED-135 + AMENDMENT 1 placed.** Conditions 1–4 satisfied by that pass (replicated blind at n=8 with a LIVE positive control: L1551/L926 flag at 234/1144 ch vs a grounded max of 22). Cond. 6's three stale lines corrected (`c08bd10`); points 7–8 placed (`e55c112`). ⚠ **THE CELL IS ONE ACT FROM CLOSING: `ratio_A_to_B` is VOID, AVAILABLE, and UNSPENT — cond. 5 reserves the spend to a STEWARD act. It cannot be re-run.** ⚠ Also settled: **PENDING-134's doctrine governs ZERO spans and has never fired**; the F4 amendment moved no membership, the cell-constant one did and its direction is inference. REVIEWED-116 pt 5 allows the single re-derivation only *after dispositions are recorded*; pt 6 rescoped that to **every fr grounded span read for reported speech**, and **no live `markers:` row carries F4** — the pass has never run. Blocker: **PENDING-133 + AMENDMENT 1, both open, awaiting steward authorization.** The one shot is unspent.
 - [Studium engine telos — the chamber of voices](project-studium-engine-telos-chamber-of-voices.md) — **the ultimate goal, above the build plan**: the childhood chamber of hero-voices, rebuilt so the counsel is *accountably* theirs. Why verbatim fidelity is load-bearing.
 - [The Chamber touchstone — the *why*](~/_Dev/studium-engine/docs/the-chamber-touchstone.md) — seven questions to test work against when lost in the trees. **Read at Step 0 of any chamber work.** Holds no state; does not decay.
 - [The Chamber vision is NOT in one place](project-chamber-vision-is-not-in-one-place.md) — it lives in **seven** sources across two repos + memory. A single home would become an eighth unless it supersedes or points.